METHODS FOR REDUCING AND CORRECTING SENSING SYSTEM POLARIZATION, AND, AGRICULTURAL MACHINE

专利摘要:
A sensing system bias is reduced by a first agricultural machine and a second agricultural machine. A collection of agronomic data is accessed, which is indicative of an estimated crop yield. The collection that is accessed, for example, includes at least a first dataset sensed by the first farm machine and a second dataset sensed by the second farm machine. In addition, the first and second data sets can be scaled based on a yield correction factor. a bias between the first step data set and the second step data set is determined, and a rectification operation is performed on the first and second step data sets. for example, performing the rectifying operation may include generating a calibration correction factor based on the determined bias, removing bias between the first scaled data set and the second scaled data set to obtain a corrected yield data set. crop, and use the calibration correction factor when sensing the first data set on the first agricultural machine and the second data set on the second agricultural machine.
公开号:BR102017022222A2
申请号:R102017022222-5
申请日:2017-10-16
公开日:2018-05-29
发明作者:Blank Sebastian；A. Stevens Robert；W. Pfeiffer Dohn；W. Anderson Noel；J. Phelan James
申请人:Deere & Company；
IPC主号:

专利说明:

(54) Title: METHODS TO REDUCE AND CORRECT A POLARIZATION OF THE SENSORING SYSTEM, AND, AGRICULTURAL MACHINE (51) Int. Cl .: G05B 13/02 (52) CPC: G05B 13/024 (30) Unionist priority: 01 / 11/2016 US 15/340704 (73) Holder (s): DEERE & COMPANY (72) Inventor (s): SEBASTIAN BLANK; ROBERT A. STEVENS; DOHN W. PFEIFFER; NOEL W. ANDERSON; JAMES J. PHELAN (74) Attorney (s): KASZNAR LEONARDOS INTELLECTUAL PROPERTY (57) Summary: A polarization of the sensing system is reduced through a first agricultural machine and a second agricultural machine. A collection of agronomic data is accessed, which is indicative of an estimated crop yield. The collection that is accessed, for example, includes at least a first set of data sensed by the first agricultural machine and a second set of data sensed by the second agricultural machine. In addition, the first and second data sets can be scaled based on a yield correction factor. A polarization between the first set of scaled data and the second set of scaled data is determined, and a rectification operation is performed on the first and second set of scaled data. For example, performing the rectification operation may include generating a calibration correction factor based on the determined bias, removing the bias between the first set of scaled data and the second set of scaled data to obtain a corrected set of yield data from crop, and use the calibration correction factor when sensing the first.)
/ 56 “METHODS TO REDUCE AND CORRECT A POLARIZATION OF THE SENSORING SYSTEM, AND, AGRICULTURAL MACHINE”
DESCRIPTION FIELD [001] The present description in general refers to techniques for obtaining accurate measurements of spatial parameters. More specifically, but not by limitation, the present description refers to the correction of posterior calibration polarization in systems configured to measure agronomic parameters.
FUNDAMENTALS [002] There is a wide variety of agricultural machinery currently in use. Such machines include combined (combined) harvesters, planting machines, tillage machines, and nutrient applicators, among others. Many agricultural machines operate not only to perform certain machine functionality, but also to obtain information about the operation being performed.
[003] To obtain this information, machines can use one or more sensors during operation. These sensors can be calibrated at the time of manufacture or at any time before, during, or after the operation is performed.
[004] Calibration generally refers to an accounting method for inaccuracies in data measurements. To calibrate a system with one or more sensors, for example, a measured value is compared with a known precision value to determine a difference between the two. The determined difference is then used to adjust the system so that future data measurements are more accurate.
[005] The above discussion is purely provided for general knowledge information and is not intended to be used as an aid in determining the scope of the claimed matter.
Petition 870170078527, of 10/16/2017, p. 91/168 / 56
SUMMARY [006] A polarization of the sensing system is reduced through a first agricultural machine and a second agricultural machine. A collection of agronomic data is accessed, which is indicative of an estimated crop yield. The collection that is accessed, for example, includes at least a first set of data detected by the first agricultural machine and a second set of data detected by the second agricultural machine. In addition, the first and second data sets can be scaled based on a yield correction factor. A polarization between the first staggered data set and the second staggered data set is determined, and a straightening operation is performed on the first and second staggered data sets. For example, performing the rectification operation may include generating a calibration correction factor based on the determined bias, removing the bias between the first staggered data set and the second staggered data set to obtain a corrected data set yield, and using the calibration correction factor in sensing the first data set on the first agricultural machine and the second data set on the second agricultural machine.
[007] This summary is provided to introduce a selection of concepts in a simplified form which are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed matter, nor is it intended to be used as an aid in determining the scope of the claimed matter. The claimed matter is not limited to implementations that address any or all of the disadvantages noted in the pleas.
BRIEF DESCRIPTION OF THE DRAWINGS [008] FIG. 1A is a block diagram showing an example of
Petition 870170078527, of 10/16/2017, p. 92/168 / 56 an agricultural machine architecture.
[009] FIG. 1B is a block diagram showing an example of a calibration correction system in an agricultural machine environment. [0010] FIG. 2 is a flow diagram illustrating an example of the operation of a calibration correction system with multiple agricultural machines.
[0011] FIG. 3 is a flow diagram illustrating an example of the operation of the calibration correction system with a single agricultural machine.
[0012] FIG. 4 is a pictorial view of an example of an agricultural machine, such as a combine harvester.
[0013] FIG. 5A shows a pictorial view of a field graph representing a measured agronomic parameter such as crop yield.
[0014] FIG. 5B shows a pictorial view of a smooth field graph representing an adjusted agronomic parameter such as crop yield.
[0015] FIG. 6 is a pictorial view of an example of an agricultural machine such as a tillage machine.
[0016] FIG. 7 is a pictorial view of an example of an agricultural machine such as a planter.
[0017] FIG. 8 is a block diagram of an example of an agricultural machine distributed with a remote server architecture.
[0018] FIG. 9 is a block diagram of an example of a mobile computing device on which the present system (or parts thereof) can be distributed.
[0019] FIG. 10 shows an example of a mobile device such as a tablet computer on which the present system (or parts thereof) can be distributed.
Petition 870170078527, of 10/16/2017, p. 93/168 / 56 [0020] FIG. 11 shows an example of a mobile device on which the present system (or parts thereof) can be distributed.
[0021] FIG. 12 shows an example of a mobile device such as a smart phone on which the present system (or parts thereof) can be distributed.
[0022] FIG. 13 is an example of a computing environment in which the present system (or parts of it) can be distributed.
DETAILED DESCRIPTION [0023] Agricultural machines can use systems to capture information indicative of an agronomic parameter. Agronomic parameters can include a measurable form of information that refers to the properties of the agricultural operation being carried out. For example, machines can monitor agronomic parameters such as the amount of crop that is harvested, the amount of crop planted or the depth at which planting takes place, the depth of a soil crop, or the amount or type of nutrients provided, among others. Thus, the term “agronomic parameter” used here can refer to any measurable form of information such as, but not limited to, crop yield, planting depth, soil moisture level, and crop nutrient properties, among others.
[0024] As an example, agricultural combine harvesters harvest crops in a field. While harvesting, the combination can use a sensing system that includes a grain yield monitor, which measures a crop mass flow with an impact based mass flow sensor or other type of sensor. In this way, the sensing system monitors the amount of harvest that is being harvested from the relative field with the location where it was harvested. For the purposes of discussion, crop yield in general refers to the crop field per unit area of land that is cultivated and is typically measured in tones per
Petition 870170078527, of 10/16/2017, p. 94/168 / 56 hectare (t / ha) or bushels per acre (bu / ac). It is important that crop yield is accurate, as this information can provide valuable insight into how specific areas of land fared in relation to a given crop. In addition, crop yield can provide insight into the performance of the agricultural machine and the sensing system.
[0025] However, there may be inaccuracies in the measurements of the mass flow, and so the actual amount of harvest that is harvested will differ from the quality detected. It is also noted that similar measurement inaccuracies can occur in other sensing systems that obtain information indicative of any of the agronomic parameters mentioned above, or others.
[0026] In an attempt to ensure that detected measurements are accurate, sensing systems can be calibrated. In typical systems, a calibration is used to adjust a detected value based on a determined difference between the detected value and a value that is known to be accurate (or more accurate).
[0027] In order to calibrate the sensing systems such as a grain yield monitoring system, a series of manual steps is performed by an operator. Operators are often required to start and stop harvesting to manually record accurate measurements for comparison with detected measurements. With a harvest operation stopped, an operator can start a calibration sequence and briefly continue to collect a portion of the field in order to obtain sensor information that is indicative of an estimated harvest weight. The operator then moves the harvested crop to an accurate balance to obtain a real natural weight. The operator then manually enters the actual natural weight, such as a calculated weight, into the calibration system and the system uses the weight to determine a deviation from the detected crop yield to the actual crop yield. This provides a calibration deviation
Petition 870170078527, of 10/16/2017, p. 95/168 / 56 for a single charge. Multiple deviations for multiple loads are usually required to obtain an average deviation. The deviation can be used to calibrate the system.
[0028] However, this method of calibrating a sensing system may have deficiencies. One of them, for example, is that it is very time consuming. In general, it requires the operator to postpone the harvest, and perform multiple calibration field steps (to obtain multiple loads). In addition, this particular method can result in data inaccuracy. For example, inaccuracies can arise from the operator by manually entering crop yield information, using a variety of different machines (for example, multiple combined harvesting in the same field), variations in an accurate measuring device (for example, a scale ), and a variety of other factors.
[0029] In addition, typical calibration systems do not allow a calibration adjustment to be applied to previously obtained data (for example, historical data). This can result in induced calibration shifts on a single machine. That is, these will be a shift in the values of data collected before calibration (historical data) and these values collected after calibration. There can also be induced calibration shifts between multiple machines. For example, it can be beneficial for an operator to use multiple machines in a single field as this can decrease the amount of time it takes to harvest a crop. However, when a calibration is performed on each individual machine, there may be variances between the estimated total crop yield across all machines as the sensors on each machine can vary from machine to machine. Typical calibration operations may not apply the calibration adjustment for other machines.
[0030] Thus, there is a need for a system that accurately calibrates sensing systems and automatically corrects
Petition 870170078527, of 10/16/2017, p. 96/168 / 56 any deficiency after calibration. It will be noted that some examples of the present description include a system that reduces the number of manual steps involved in carrying out a calibration, decreases the operator time that is required to carry out a calibration sequence, reduces calibration-induced displacements within a single machine, reduces machine-to-machine calibration bias, and provides more accurate detected data, which leads to more accurate agronomic maps, improved agronomic decision making, and improved operational performance. [0031] FIG. 1 is a block diagram of an example of an agricultural machine 100. The agricultural machine 100 illustratively includes one or more processors 102, memory 104, communication system 105, user interface 108, control system 110, controllable subsystems 112, storage data 114, and other components 116. FIG. 1 also shows that, in one example, machine 100 may include an operating parameter monitoring system 118, a calibration system 132, a calibration correction system 138, and a data visualization system 148.
[0032] In one example, user interface 108 includes operator entry mechanisms and exit mechanisms. The output mechanisms can be mechanisms that carry information to the operator 166, such as visual display devices, audio devices, haptic response devices, etc. In one example, user interface 108 interacts with data visualization system 148 to produce a variety of output mechanisms that are indicative of monitored operations, which will be discussed in further detail below. The operator input mechanisms can include a wide variety of different mechanisms that can be operated by the operator 166 to control and manipulate various systems and subsystems (for example, controllable subsystems 112) of agricultural machine 100. The operator input mechanisms, for example, example,
Petition 870170078527, of 10/16/2017, p. 97/168 / 56 can include levers, steering wheels, pedals, joysticks, buttons, keyboards, touch-sensitive display devices, and user input mechanisms in user interface displays, among a wide variety of other input mechanisms.
[0033] Control system 110 can receive sensor signals from sensors 122 and generate control signals to control the various controllable subsystems 112. It is shown in FIG. 1 that sensors 122 are included in the operational parameter monitoring system 118. It is also noted that sensors 122 can be included in the general architecture of agricultural machine 100, and therefore are not limited to the sensing signals indicative of operational parameters. Controllable subsystems 112 may include a wide variety of computer and mechanical implemented systems of agricultural machine 100 that relate to the movement of the machine, the agricultural operation that is carried out, and other controllable features. Some examples are described below.
[0034] The operational parameter monitoring system 118 illustratively identifies an operational parameter associated with each of the sensor signals that is received from the sensors 122 and provides that information to the control system 110, so that control system 110 can accommodate various levels of signal variability obtained by sensors 122. Sensors 122 can include sensors that are configured to determine operational parameters such as grain mass flow, soil moisture, planting depth, crop depth, among a variety of others. Sensors 122 can also include a variety of other sensors such as a machine status sensor. Illustratively, it is shown that the operational parameter monitoring system 118 also includes the geospatial system 120. The geospatial system 120 includes at least one of a system receiver.
Petition 870170078527, of 10/16/2017, p. 98/168 / 56 global positioning (GPS), a LORAN system, an estimated navigation system, a cell triangulation system, or another positioning system. In one example, geospatial system 120 is configured to associate signals obtained by sensors 122 with a geographical location, such as an in-field location. In this way, a variety of different spatial parameter data can be obtained by sensors 122, by geospatial system 120, and identified by system 118. Modes described here can also be configured to perform loss of sensing, such as grain loss sensing .
[0035] The operational parameter monitoring system 118 additionally illustratively includes yield monitoring logic 124. The yield monitoring logic 124 is configured to use sensors 122, such as grain mass flow sensors, and geospatial system 120, to estimate crop yield at various locations in an operating environment (for example, a field with a planted crop that is harvested). In this way, the yield monitoring logic 124 can use information obtained by a sensing system to estimate a yield density for a harvesting session. The operational parameter monitoring system 118 can also include moisture monitoring logic 126, and planting depth monitoring logic 128, among other monitoring logic 130. Humidity monitoring logic 126 can use soil moisture sensors ( eg sensors 122) to estimate soil moisture content at various locations in the operating environment. Similarly, the planting depth logic 128 can use a planting implement depth sensor (for example, sensors 122) to estimate an average planting depth at various locations in the operating environment. Another monitoring logic 130 can be configured to monitor any other agronomic parameters
Petition 870170078527, of 10/16/2017, p. 99/168 / 56 discussed here and use the parameter information detected in association with geospatial information.
[0036] It is also noted that the information obtained by an operational parameter monitoring system 118, along with the other machine components 100, can be stored in a variety of locations including, but not limited to, memory 104 and / or storage 114. In addition, agricultural machine 100 can be in communication with one or more agricultural machines 162 and 164, and / or remote systems 160 over network 158. Network 158 can be any one of a wide area network (WAN) , local area network (LAN), or a wireless local area network (WLAN), among others.
[0037] Agricultural machines 162 and 164 can perform the same operation or a similar operation as that being performed by agricultural machine 100. For example, agricultural machines 100, 162, and 164 may include combine harvesters that are performing a harvest operation in different spatial regions of the same field. In this way, it can be beneficial to use information from each machine to determine accurate measurements and correct a single machine bias or multiple machine bias. Remote systems 160 can include any other system relevant to an agricultural operation being carried out or an agronomic parameter being monitored. For example, remote system 160 includes a remote agricultural management system, other agricultural machines, and an imaging system such as an aerial imaging drone, among others.
[0038] In the example shown in FIG. 1, the agricultural machine 100 also illustratively includes the calibration system 132. The calibration system 132 includes a manual calibration system 134 and a sensor interface 136. As briefly discussed above, at some point during the operation of the agricultural machine 100, operator 166 can initiate a
Petition 870170078527, of 10/16/2017, p. 100/168 / 56 calibration sequence. For example, operator 166 can actuate a calibration input mechanism that is generated by user interface 108. In response to the reception actuation of the calibration input mechanism, manual calibration component 134 initiates a calibration sequence. In one example, performing a calibration sequence with a manual calibration component 134 includes obtaining an indicative sample of an operational parameter and comparing that sample to a calculated value of the operating parameter. For example, when harvesting a crop in a field, operator 166 can start a manual calibration sequence with the manual calibration component 134 to compare an estimated crop yield to an actual crop yield, which can be obtained by weighing the sample with an accurate scale. The calibration component 134 then determines a calibration adjustment, based on the comparison, and provides this adjustment for sensor interface 136. Sensor interface 136 can instruct a variety of sensors 122 to adjust an emitted signal that is provided by the sensors . It is also noted that the calibration system 132 can be configured to perform a calibration adjustment automatically, such as in response to a predetermined calibration time, a specific indication provided by the operational parameter monitoring system 118, or other indication. By automatically it means, in an example, that it is performed without additional operator input, except perhaps to authorize or start the calibration adjustment.
[0039] FIG. 1A also illustratively shows that the agricultural machine 100 includes the data visualization system 148. The data visualization system 148 includes a field map generator 150, a corrected metric output 152, a calibration correction summary 154, and others data views 156. It may be beneficial for the operator 166 to be provided with a visualization of the performance monitoring system
Petition 870170078527, of 10/16/2017, p. 101/168 / 56 operational parameter 118. For example, the field map generator 150 can be configured to generate one or more field maps that include a graph of the parameters measured during operation. In one example, the field map generator 150 is configured to generate the crop yield graph that is displayed with the user interface 108. Before discussing other various features of the data visualization system 148, the correction system calibration 138 will now be discussed in further detail with respect to FIG. 1B [0040] FIG. 1B is a block diagram showing an example of a calibration correction system 138 in an agricultural machine architecture. The calibration correction system 138 illustratively includes a data aggregator 140, pre-processing logic 142, polarization correction logic 144, and other calibration logic 146. It is shown in FIG. 1B that data aggregator 140 can receive a variety of information regarding agricultural machine operation 100 from operational parameter monitoring system 118 and / or data storage 114. It is also noted that data aggregator 140 can be configured to track data storage 114 and analyze one or more data sets for use with calibration correction system 138. For example, in a mode where the operating parameter monitoring system 118 monitors crop yield during harvesting operation (for example, using yield monitoring logic 124), data aggregator 140 can receive or obtain data that is indicative of crop yield at various locations within a harvesting operation, where these locations are provided by the geospatial system 120. Of course, it is also noted that data aggregator 140 can obtain any of the data related to humidity 126, planting depth logic 128, other monitoring logic 130, and any other information that is obtained by geospatial system 120 and by
Petition 870170078527, of 10/16/2017, p. 102/168 / 56 sensors 122. The data aggregator 140 can then provide the sensor signal information obtained for the pre-processing logic 142.
[0041] The preprocessing logic 142 is configured to prepare the data obtained for use with polarization correction logic 144. At some point, it may be beneficial that the data that is aggregated to be filtered based on one or more filter criteria. The filter criteria can be defined by one or more pieces of filter logic. In this way, the preprocessing logic 142 includes a calibration data filter 168. The calibration data filter 168 illustratively includes path redundancy logic 170. Path redundancy logic 170 can filter the parameter data obtained by the data aggregator 140 removing any sensor signals from redundant geospatial locations. For example, during harvesting, a combine harvester or agricultural machine 100 can make a single pass through a field to harvest a crop in a row. In some cases, an operator may be required to make an additional pass over this same row to harvest any crop that was missing from the first pass. Similarly, an operator may need to pass over an already harvested row to reach a desired location within the field (for example, the operator is not harvesting when he passes over the already harvested row). Information from the subsequent pass can be filtered.
[0042] In addition, or alternatively, pre-processing logic can perform a fusion operation that combines information obtained. For example, the calibration data filter 168 can determine similar sets of information and combine these similar sets to generate a merged set of information obtained.
[0043] Parameter data can also be filtered based on a machine state that is determined by machine state logic 172. Machine states can be indicative of a particular condition of a
Petition 870170078527, of 10/16/2017, p. 103/168 / 56 machine during an operation. For example, but not by limitation, machine states can include any of the following; an idle state, an unloaded idle state, a field transport state, a road transport state, a harvest state, a discharge state while harvesting, and a header state, among others. Some of the parameter data that is obtained by sensors 122 may not be relevant if the data is obtained during a certain machine state. For example, when an operator performs a cable loop, which is a loop at the end of a row pass to position the machine for a next pass in the adjacent row, the crop yield sensor (such as a mass flow sensor of grain) can continue to obtain data during the lap. However, data obtained during the lap may not include an indication of a crop being harvested as machine 100 may temporarily leave the area that can be harvested from the field. In addition, or alternatively, parameter data can be filtered based on the identified delay correction, such as a delay correction that is applied due to a change in machine speed that is inconsistent with the rate at which the sensor information is captured. Any delay correction that is performed can be identified as a delay period that occurs while capturing the sensor information. Machine state logic 172, appropriately, can identify a set of spatial information that was obtained during a correction period. In this way, machine state logic 172 can determine irrelevant parameter data based in part on an identified machine state, and remove said irrelevant data.
[0044] It is also contemplated that a variety of other filter logic 174 can be applied to filter the relevant parameter data according to calibration data filter 168. For example, another filter logic 174 can determine data points that are determined to be
Petition 870170078527, of 10/16/2017, p. 104/168 / 56 within statistical limits within a set.
[0045] In addition to filtering the obtained parameter data, preprocessing logic 142 can prepare the obtained parameter data in a variety of other modes. It is shown illustratively in FIG. 1B that preprocessing logic 142 includes parameter scaling logic 176. In one example, parameter scaling logic 176 is configured to scale the parameter data obtained based on a parameter correction factor. To scale the parameter data, logic 176 determines a statistical shift in a set of parameter data obtained. For example, logic 176 determines a statistically significant standard deviation in a set of parameter data obtained. This can be a statistically significant standard deviation (for example, not due to sampling error alone, and instead a characteristic of the whole set) between selected crop yields (for example, mass flow, density) from a variety of locations within a sampling region. In addition, or alternatively, determining a statistical shift may include determining a standard deviation from the mean, an upper limit of the sensed parameter data, etc. Based on the degree of statistical shift, parameter scaling logic 176 can determine a parameter correction factor and scale the data appropriately.
[0046] In the example of crop yield sensing as an agronomic parameter, parameter 176 scheduling logic recalculates a yield from a detected mass flow, machine speed, and collector width (for example, a component of controllable subsystems 112) to remove an upper yield limit. With the removal of an upper yield limit, field values can be scaled by parameter 176 scaling logic based on a determined yield correction factor. Once
Petition 870170078527, of 10/16/2017, p. 105/168 / 56 that the yield correction factor is determined and the field values are staggered, logic 176 then you can calculate a new upper yield limit and truncate the yield values determined above the new upper yield limit. In this way, scheduling logic 176 may include a mechanism for determining a more accurate operational parameter by scheduling the estimated parameters with respect to each other.
[0047] In one example, since the parameter data obtained is prepared by preprocessing logic 142, the prepared data is provided for the polarization correction logic 144 to reduce a determined polarization between the prepared data. It is shown in FIG. 1B The polarization correction logic 144 includes rectification logic 178, a multi-machine factor logic 180, artifact removal logic 182, and data verification logic 184.
[0048] When multiple machines are harvesting in the same field, there may be a polarization of the sensing system that occurs from machine to machine. In addition, when there is a single machine harvesting in a field, there may be a polarization of the sensing system between the sensors on that machine. Conventional systems can exhibit a polarization of the sensing system, both internally (single machine) and externally (multiple machines) that reflects a 10 to 50% difference between sets of detected operational parameters. It is desirable to have a system that is responsible for these determined displacements and provides accurate operational parameter outputs from each machine that is in operation.
[0049] In one example, polarization correction logic 144 provides a post-calibration algorithm that statistically calculates polarization from machine to machine, or from sensor to sensor on an individual machine, to reduce polarization and output accurate parameter data . O
Petition 870170078527, of 10/16/2017, p. 106/168 / 56 operating parameter monitoring system 118 can obtain multiple sets of parameter data. In an operation where a single machine is used, each data set is indicative of, for example, a parameter data set that is obtained in a specific spatial region of the field. For example, a first set corresponds with data obtained during a first harvest pass (for example, harvesting a first set of rows), while a second set corresponds with data obtained during a second harvest pass (for example, harvesting a second set rows). Where multiple machines are used, each data set that is obtained can be obtained by a different agricultural machine. For example, a first set may correspond with data obtained by agricultural machine 100, while a second set corresponds with data obtained by agricultural machine 162, and a third set corresponds with data obtained by agricultural machine 164, etc. Each of the individual sets, regardless of whether one or more machines are used, can include parameter data from a localized region of the field. The sets can be compared to identify a polarization between the sensing systems or individual sensors on a single machine, and therefore eliminate the polarization that occurs when measuring these local regions.
[0050] In one example, the polarization correction logic 144 uses the scaled data sets, as scaled by the parameter 176 scaling logic. In this way, the data sets have already been pre-processed to remove any statistical shift identified within of the sets. The polarization correction logic 144 is then configured to analyze the sets with respect to each other, and thus determine a polarization between the sets.
[0051] A variety of algorithms can be applied to scaled parameter data with polarization correction logic 144, and more
Petition 870170078527, of 10/16/2017, p. 107/168 / 56 specifically with rectification logic 178. For example, rectification logic 178 can apply a generalized additive model to rectify parameter data according to latitude and longitude determined from geospatial system 120. Alternatively, but not by limitation, rectification logic 178 may include a localized regression model that is performed to reduce a sensing system bias. In one example, the rectification logic 178 adjusts the yield value for each combined so that the average yield equals the original global heavy average yield. It is also noted that the rectification logic 178 can be configured to perform a localized rectification. For example, yield parameter data can be obtained for 1% of a total region in a field. Rectification logic 178 will recognize that only a specific region of the field has been harvested and execute a rectification algorithm on the indicative data for the 1% region. With the execution of the rectification, a localized rectification metric can be applied to the data obtained from other regions located within the field. In this way, a result of performing the rectification on only a portion of the field can be used to rectify the rest of the field data.
[0052] Multi-machine factor logic 180 is configured to determine a weighted offset value between several machines that are operating and obtaining operational parameters. For example, it can be determined by the factor logic of multiple machines 180 that between each machine operating in a field, there is a sensing system polarization of approximately 3% from machine to machine. In this way, the multi-machine factor logic 180 will determine a throughput range across the machines and a shift from one machine to another. The field interval and the offset can be used to generate a multi-machine factor that is applied with the rectification logic 178. [0053] It is also noted that even when sensors (via
Petition 870170078527, of 10/16/2017, p. 108/168 / 56 a single machine or between multiple machines) have a relatively low polarization (for example, less than +/- 2%), this does not guarantee that accurate parameter data will be determined by the polarization correction logic 144. For example, there may be transient characteristics within the data. It may be beneficial to identify and remove these transient characteristics to provide more accurate parameter output. For example, but not by limitation, when two combines (for example, machines 100 and 164) are harvesting in a single field, each combination can change a forward speed depending on a machine state. Combines may need to slow down to make a cable loop, move over rough terrain, pass over a slope or a particularly dense portion of the crop in the field, etc. When the front speed of a combination changes while obtaining parameter data, there is usually a delay correction that is performed. For example, there may be a delay of approximately 10 seconds between when geospatial data is obtained and when parameter data is obtained. In this way, as the speed is changed, the delay correction can be inconsistent until a consistent speed is achieved. It is clear that it is contemplated here that the delay correction can be identified and applied to a variety of channels in addition to a sensed change in speed. Regardless of the sensed channel, the need to correct the delay can manifest itself as a need to assign the sensed data (for example, mass flow) to a corresponding geolocation. In conventional systems, these and other delay corrections can be shown as inaccurate data parameter outputs when observing a field map. Specifically, on some maps, these inconsistent delays can be viewed as spots or other visual inaccuracies on a field map. The artifact removal logic 182 is configured to identify and remove such artifacts that are indicative of outliers in the parameter data
Petition 870170078527, of 10/16/2017, p. 109/168 / 56 operational detected.
[0054] Polarization correction logic 144 illustratively also includes data verification component 184. In one example, data verification component 184 is configured to incorporate data that is provided by direct observation to further reduce the calibration bias. An example of a data source that can be provided with a verification component 184 includes an indication of a terrestrial truth. The terrestrial truth in general can refer to an actual observed value of any of the parameters obtained by the operational parameter monitoring system 118.
[0055] An example of terrestrial truth for yield parameter data includes an actual measured weight of a sample of a harvested load. For example, when harvesting a crop, the combined can place the harvested grain on a cart with one or more measuring scales (for example, sensors 122). In another example, agricultural machine 100 can be operated on a scale. The scales can obtain an indication of the check logic and measured weight 184 will use the indication in determining a calibration setting with logic 178. Two particular scenarios will now be briefly discussed. In one scenario, each combination gets an accurate weight to determine the amount of grain that was harvested by that combine. The data verification logic 184 then calculates a sum of the weights across all machines. Logic 184 can then compare the sum with the estimated mass flow as provided by the yield monitoring logic 124 from each machine. In a second scenario, a single combination is used, so the single machine can obtain an accurate final weight measurement when the entire field is harvested, or multiple accurate weight measurements that correspond to specific regions of the field. The measurements will be reconciled by the data verification component 184 and provided for the rectification logic 178 for
Petition 870170078527, of 10/16/2017, p. 110/168 / 56 reduce the calibration bias. It is noted that a variety of parameters in addition to the crop yield can be used with data verification component 184.
[0056] Before describing these scenarios, it will be noted that FIG. 1B illustratively shows that bias correction logic 144 can provide bias reduction information determined for calibration system 132. For example, bias correction logic 144 provides a bias correction factor for sensor interface 136, which uses the correction factor to adjust sensor signals generated by sensors 122. FIG. 1B also shows that calibration system 132 can provide an indication of the bias correction factor for operating parameter monitoring system 118. System 118 can then use the correction factor with any of the monitoring logic discussed here to reduce data inaccuracies during operational monitoring. In addition, it is noted that the determined calibration correction factor can be applied to the previously obtained operational parameter data, which can be stored in data store 114. This allows the agricultural machine 100 to adjust before yield, humidity, depth of planting, and other parameter data to reflect the newly accurate calibration balance.
[0057] FIG. 2 illustrates an example of a method 200 illustrating the operation of the calibration correction system with multiple agricultural machines. More specifically, method 200 may include a method of reducing a sensing system bias through a first agricultural machine and a second agricultural machine.
[0058] As noted above in a similar way, there may be several agricultural machines working the same operations or similar operations in a field at the same time or at different times. The calibration of the sensors on each machine can occur initially at
Petition 870170078527, of 10/16/2017, p. 111/168 / 56 time of manufacture. In addition, an operator 166 can perform manual calibrations with the manual calibration component 134. Thus, when the agricultural machine 100 performs an operation and operational parameter data is obtained with the monitoring system 118, data is unique for each machine that is operating, and currently there is no way to reconcile this data across machines to provide a consistent output that is representative of accurate parameter monitoring. [0059] A calibration correction system, according to the modalities described here, can operate substantially in real time. It is noted that the term "real time" used here generally refers to operations that occur concurrently or with respect to one another without a large deviation between the time when these operations are performed. Processing time does not negate the system's ability to operate in real time. In this way, multiple machines can operate in the same field at the same time so the sensor information and calibration correction is carried out by the systems substantially in real time.
[0060] In block 202, it is shown illustratively that the multiple machines collect or collect operational parameter data. Each machine can collect a variety of data that is included, but not limited to, machine identification, geospatial data, and parameter data. Multiple machines that collect machine identification information in general are indicated in block 216. Each agricultural machine 100 can include a machine identifier stored in data storage 114 and provided to remote systems 116 via communication system 108 and over the network 158. In addition, as an operation is being performed, the geospatial system 120 can obtain information such as, but not limited to, latitude and longitude at a variety of time points that are indicative of when the operation occurs. The collection of geospatial data with multiple machines is generally
Petition 870170078527, of 10/16/2017, p. 112/168 / 56 indicated in block 218. Depending on the operation being performed (such as a harvest operation, planting operation, tillage operation, or nutrient monitoring operation, among others) each machine will collect parameter data which is indicative of the operation. The collection of parameter data in general is indicated in block 220 in FIG. 2. It is also noted that the collection of parameter data, according to block 202, can specifically include access to a collection of agronomic data previously collected from data storage 114 or other storage structure. The calibration correction system 138 can access a data collection that includes a first data set that is sensed by a first agricultural machine and a second data set detected by the second agricultural machine.
[0061] In block 204, it is shown illustratively that the method includes aggregating the operational parameter data from multiple machines. The data aggregator 114 can aggregate the data obtained from the operational parameter monitoring system 118 and / or data storage 114 in preparation for performing data pre-processing. Aggregating parameter data from multiple machines can include aggregating individual data points for one or more sets, where the sets are defined by the machine obtaining the data, the location where the data was obtained, the time the data was obtained , or other criteria. For example, the first data set is sensed by the first agricultural machine during a harvesting operation that is performed against a first portion of a harvesting environment, and the second data set is sensed by the second agricultural machine with respect to a second portion of the harvest environment.
[0062] In block 206, the method includes performing data pre-processing. Performing data pre-processing may include executing any of the features discussed in relation to the prePetition logic 870170078527, of 10/16/2017, pg. 113/168 / 56 processing 142 in FIG. 1B. For example, preprocessing logic 142 can determine a correction factor among the aggregate data set based on, for example, a statistical deviation. Additionally, performing pre-processing may include filtering the data obtained, as indicated in block 224. Filtering the data obtained may include executing path redundancy logic 170, machine state logic 172, or other filter logic 174, as provided by the calibration data filter 168. In general, filtering the data obtained provides a mechanism for removing outliers and irrelevant data sources that will not be beneficial in generating an accurate parameter output.
[0063] Performing data pre-processing can also include staggering the data obtained, which is generally indicated by block 226. In one example, staggering the data obtained includes staggering each of the first and second sets, individually, with based on a determined correction factor corresponding to each of the sets. For example, a first offset is determined for the data in the first set and a second offset is determined for the data in the second set, and the parameter correction factor is partially based on the first and second offsets. In addition, the first displacement can be indicative of a first average deviation in the first set, where the first average deviation is greater than a minimum deviation limit that is used to perform the scheduling. Similarly, the second displacement can be indicative of a second average deviation in the second set, where the second average deviation is greater than a minimum deviation limit that is used to perform the scaling.
[0064] In block 208 of method 200, it is shown illustratively that the method includes determining that there is a polarization between the sensing systems of the multiple machines. In one example, determining whether a bias exists includes analyzing a deviation between the average parameter output
Petition 870170078527, of 10/16/2017, p. 114/168 / 56 between each machine. For example, calibration correction system 138 determines that there is significant polarization between an average deviation of the first staggered set and an average deviation of the second staggered set. If the polarization is above a limit, the calibration correction system 138 can determine that there is significant polarization between the machines and that a calibration correction should be used.
[0065] Block 210 of method 200 includes performing a polarization correction to rectify the operating parameter data. In one example, polarization correction logic 144 performs one or more rectification functions, one of which may include generalized additive rectification, as indicated in block 228. Performing generalized additive rectification with rectification logic 178 may include adjusting the operational parameter values obtained (for example, in the first and second staggered sets) so that the average parameter value is equal to the original global weighted average parameter value. In addition, performing a polarization correction may include applying a multi-machine factor with multi-machine factor logic 180, which is generally indicated in block 232. Multi-machine factor 230 can include a weighted offset that is determined by logic multiple machine factor 180, which in general indicates a shift from the global average between each agricultural machine. Additionally, performing a bias correction may include removing artifacts, as indicated in block 232. For example, artifact removal logic 182 removes transient characteristics in the obtained operational parameter data such as, but not limited to, inconsistencies that result from the change speed delay corrections, disparate data points, among others. Performing a bias correction also illustratively includes verifying the data correction, as indicated in block 234. Verifying the data correction may include using the data verification component 184 to compare the estimated data correction for
Petition 870170078527, of 10/16/2017, p. 115/168 / 56 a real known value of the operating parameter. For example, the terrestrial truth can be determined for the crop yield and this terrestrial truth can be used to determine an additional correction offset between a real crop mass that is harvested and the estimated crop mass.
[0066] In block 212, method 200 illustratively includes applying a bias correction to all relevant machines collecting the operating parameter data. For example, applying polarization correction may include providing a calibration offset adjustment with polarization correction logic 144 for calibration system 132. In this way, sensors 122 themselves can be calibrated or blocked 212 may include system calibration 132 instructing sensor interface 136 to adjust the sensor signals provided by sensors 122 so any future operational parameter data that is obtained is consistent across all machines, with respect to each other.
[0067] In block 214, method 200 includes issuing the corrected operational parameter data. Corrected parameter data can be output in a variety of ways. In one example, issuing the corrected parameter data may include providing a corrected field map with the field map generator 130, as indicated in block 236. A corrected field map in general will provide a smooth view of the emitted parameter (for example, harvest yield) based on the location where the operation was carried out. This can provide a real-time view for operator 166 that indicates how the machine is operating during operation. Corrected field maps in general will be discussed in further detail below with respect to FIGS. 5A and 5B. In addition, or alternatively, outputting the corrected parameter data can include outputting an infographic, as indicated by block 238. The data visualization system 148 can also generate other data views 156 which can include
Petition 870170078527, of 10/16/2017, p. 116/168 / 56 charts, graphs, maps, and a variety of infographic material.
[0068] Additionally, calibration correction system 138 can be configured to output corrected metrics, as indicated in block 240. Corrected metrics are indicative of the parameter data obtained as adjusted by polarization correction logic 144. For example, in example of a combined spoon, corrected metrics 240 include an average yield compared to a percentage deviation for each of the machines, plus a corrected yield compared to a deviation by an average of all machines. In addition, issuing corrected operating parameter data may include issuing a calibration correction summary, as indicated in block 242. In one example, the calibration correction summary includes a visual output that compares the original parameter outputs to the outputs of corrected parameter and the weighted offset that will be applied for future and / or historical parameter data. Metrics can also include an adjusted mass flow (kilograms per second) and an adjusted productivity (for example, crop yield in tons per hour), an average combined yield and a percentage deviation from an overall average, along with a range that includes a maximum percentage standard deviation calculated with respect to a minimum percentage standard deviation, among others. These are examples only.
[0069] FIG. 3 is a flow diagram illustrating an example of operating calibration correction system 138 with a single agricultural machine. In one example, method 300 includes a method of reducing a sensing system bias in an agricultural machine.
[0070] As discussed above in a similar manner with respect to method 200, a calibration correction system and the associated systems described here can operate substantially in real time with respect to a single machine. For a single remote machine to be able to perform the method of reducing polarization of the sensing system as a
Petition 870170078527, of 10/16/2017, p. 117/168 / 56 direct board. Second, but not by limitation, a single machine can use a calibration correction system where this machine is processing historical spatial information in combination with information from the single machine.
[0071] In block 302, it is shown illustratively that method 300 includes collecting or accessing a collection of operational parameter data. The collection of operational parameter data may include accessing geospatial data, as indicated in block 318, historical operational data, as indicated in block 320, and / or the current parameter data, as indicated in block 322.
[0072] With data collection or evaluation, method 300 proceeds to aggregate the data that is associated with this single machine. In general this is indicated in block 304. As discussed in a similar manner above with respect to FIG. 2, data aggregator 140 can aggregate parameter data from operating parameter monitoring system 118 and / or data storage 114. When a single machine is operating, aggregating data may include aggregating the data into one or more sets. For example, each set can include data obtained during a specific operating time window, from a specific region in a field, etc. In one example, a first set includes agronomic data that is sensed during a first agricultural machine pass in an operating environment, and a second set includes agronomic data that is sensed during a second agricultural machine pass in an operating environment. The first set can refer to the data obtained during a current operating session, while the second set can refer to the data obtained during an operating session that was performed at some previous time. These are just examples.
[0073] Data pre-processing can be performed on the data of
Petition 870170078527, of 10/16/2017, p. 118/168 / 56 parameters obtained (and aggregates), as indicated in block 306. It is noted that performing data pre-processing can include any of the pre-processing features discussed with respect to FIG. 2 (method 200, block 206) and preprocessing logic 142 of FIG. 1. As shown in FIG. 3, performing pre-processing includes determining a correction factor, as indicated in block 324, filtering the data obtained, as indicated in block 326, and scaling the data obtained, as indicated in block 328. It is also noted that scaling the data obtained in accordance with block 328 may include the use of parameter scheduling logic 178 to analyze a localized region of data for a specific field, and apply the appropriate pre-processing to the rest of the field data. In one example, data scaling includes adjusting each of the first and second sets individually, based on a determined correction factor corresponding to each of the sets. The parameter correction factor can be determined by a statistical deviation between the data contained within each of the sets.
[0074] In block 308, method 300 includes determining a polarization between the first and the second sets, as well as between current and historical operational parameter data that are obtained with the single machine. Determining a polarization can include the calibration correction system 138 to determine if there is a polarization between an average deviation of the first staggered set and an average deviation of the second staggered set. Of course, a polarization can also be determined in a variety of other ways.
[0075] In block 310, the method includes performing a polarization correction to rectify the first and second staggered sets from the machine, as well as the current and historical operational sets. The polarization correction that is performed with respect to FIG. 2 and multiple machines that are working in one operation can also be applied
Petition 870170078527, of 10/16/2017, p. 119/168 / 56 for method 300 for a single machine. In this way, block 310 illustratively includes performing generalized additive rectification with rectification logic 178. In addition, or alternatively, rectification logic 178 can perform local regression rectification, as indicated in block 332. Using local regression rectification in general it may not include using a combined factor since regression requires only information from a single machine. An example of a rectification regression that can be applied, using rectification logic 178, for information obtained with a single machine, includes a Gaussian process regression. In addition, or alternatively, the rectification logic 178 may include a generalized linear model that can be applied to either single machine or multiple machine cases. It is clear that it is noted that a variety of different geospatial rectification operations for various data sources with specific source correction that can be applied. Performing the grinding operation may include generating a calibration correction factor, and applying this calibration factor to the first and second adjusted (for example, scaled) data sets obtained by the single machine.
[0076] Performing the bias correction can also include removing artifacts, as indicated in block 334, using artifact removal logic 182 to identify outliers of data and transient characteristics in the parameter data. In addition, verification of a data correction is indicated in block 336, which may include the use of data verification component 184 to compare a terrestrial truth (such as an actual yield as determined by a measurement with an accurate scale) for the scaled parameter data sets.
[0077] In block 314, a polarization correction is applied to all relevant historical parameter data for the machine. Applying the bias correction to historical data can rectify all data from
Petition 870170078527, of 10/16/2017, p. 120/168 / 56 parameters obtained by a single machine for a specific operation. This generates operational parameters that are accurate for the entire period of operation.
[0078] In block 316, the corrected operational parameter data are issued that can include any of: issue a corrected field map and infographic, as indicated in blocks 338 and 340, respectively; corrected metrics, as indicated in block 342; and / or a summary of calibration correction, as indicated in block 344; or any of the other outputs discussed with respect to FIG. 2 (method 200, block 214) and data visualization system 148.
[0079] Before describing the operational control findings that are provided by the calibration correction system 138, an example of an agricultural machine 100 will first be described. FIG. 4 is a partial schematic illustration of partial image of machine 100, in an example where machine 100 is a combined 400. It can be seen in FIG. 4 that the combined 400 illustratively includes an operator compartment 458, and a set of front end equipment that includes a collector 402, and a cutter in general indicated at 404. The combined 400 may also include a feeder 406, an accelerator feeder 408 and a thresher in general indicated at 410. The thresher 410 illustratively includes a threshing rotor 412 and a concave set 414. In addition, the combined 400 may include a separator 416 which includes a separator rotor. Combine 400 may include a cleaning subsystem (or cleaning shoe) 418 which, itself, may include a cleaning fan 420, screen 422, and sieve 424. The material handling system in combined 400 may also include the whisk discharge 426, tailings elevator 428, clean grain elevator 430 as well as discharge auger 434 and nozzle 436. Combine 400 may additionally include a waste subsystem 438 which may include cutter 440 and spreader 442. The combined
Petition 870170078527, of 10/16/2017, p. 121/168 / 56
400 may also have a propulsion subsystem that includes an engine that drives 444 ground hitch wheels or rails, etc. It will be noted that the combined 400 may also have more than one of any of the subsystems mentioned above.
[0080] In operation, and by way of illustration only, the combined
400 illustratively moves across a field and in a general direction indicated by the arrow 446. When it moves, the collector 402 engages the harvest that is harvested and collects the harvest for the cutter 404. Once the harvest is cut, the crop is moved by a conveyor in the feeder 406 to the feed accelerator 408 which accelerates the crop to the thresher 410. The crop is threshed by rotor 412 turning the crop against the hollow 414. The threshed crop is moved by a rotor and separator 416 separate where part of the waste is moved by the beater 426 to the waste subsystem 438. It can be cut by the waste cutter 440 and spread in the field by the spreader 442. In other implementations the waste simply dropped into a window in instead of being cut and spread. [0081] The grain falls into the cleaning shoe (or cleaning subsystem) 418. The screen 422 separates part of the larger material from the grain and the sieve 424 separates part of the finer material from the clean grain. Clean grain falls to a auger in the clean grain elevator 430, which moves the clean grain up and deposits it into the clean grain tank 432. The residue can be moved from the cleaning shoe 418 by air flow generated by the cleaning fan 420. This waste can be moved backwards in combined 400 to the waste handling subsystem 438.
[0082] FIG. 4 also illustratively shows that, in one example, the combined 400 may include a ground speed sensor 446, one or more separator loss sensors 448, a clean grain camera 450, and one or more shoe loss sensors from cleaning 452. The ground speed sensor 446 illustratively detects the travel speed of the
Petition 870170078527, of 10/16/2017, p. 122/168 / 56 combined 400 on the ground when the combined moves in a general direction indicated by the arrow 446. Sensing the ground speed can be done by sensing the rotation speed of the wheels, drive shaft, axle , or other components. The travel speed can also be determined by a positioning system, such as geospatial system 120, generally represented by geospatial sensor 460 in FIG.
4.
[0083] Cleaning shoe loss sensors 452 illustratively provide an output signal indicative of the amount of grain lost by the right and left sides of cleaning shoe 418. In one example, sensors 452 are shock sensors that count grain shocks per unit of time (or per unit of distance traveled) to provide an indication of the loss of cleaning shoe grain. The shock sensors for the right and left sides of the cleaning shoe can provide individual signals, or a combined or aggregate signal. It will be noted that the 452 sensors may also comprise only a single sensor, instead of separate sensors for each shoe.
[0084] The separator loss sensors 448 provide a signal indicating grain loss in the left and right separators. The sensors associated with the left and right separators can provide separate grain loss signals or a combined or aggregate signal. As can also be done using a wide variety of different types of sensors, it will be appreciated that the separator loss sensors 448 can also comprise only a single sensor, instead of separate left and right sensors.
[0085] It will also be noted that the sensors described with respect to the combined 400 (in addition to the sensors already described with respect to the machine 100) can also include other sensors. For example, they can include a humidity sensor that is configured to sense the humidity level
Petition 870170078527, of 10/16/2017, p. 123/168 / 56 of the material that is passing through the combined 400, and / or sensing the moisture level of the soil in which the combined 400 passes over during operation. The combined 400 can also include a machine status sensor 462 that is configured to sense whether the combined 400 is configured to drop the waste, drop a window, or perform another machine operation. They can also include cleaning shoe fan speed sensors that can be configured close to fan 420 to sense fan speed. They can include machine adjustment sensors that are configured to sense the various configurable settings on the combined 400. They can also include a machine orientation sensor that can be any of a wide variety of different types of sensors that detect the orientation of the combined 400. For example, the detected orientation can identify the orientation of combined 400, the position of parts of combined 400 with respect to other parts, or the position of parts with respect to the ground, etc. Another example of a machine orientation sensor includes a sensor that detects the height of a collector 402 above the ground. In addition, crop property sensors can sense a variety of different crop properties such as crop type, crop moisture, and other crop properties. Other crop properties may include different grain constituents such as, but not limited to, oil, starch and protein properties. More particularly, crop property sensors can detect crop characteristics while they are being processed by machine 400, for example, when the crop is being passed through a 430 grain elevator. A particular example of a crop property sensor includes a mass flow rate sensor 464 that detects the mass flow rate of a crop through elevator 430, or provides other output signals indicative of similar variables.
[0086] In this way, the size and number of sensors used with the
Petition 870170078527, of 10/16/2017, p. 124/168 / 56 systems described here may vary. In addition, or alternatively, inferred measurements can be obtained from the virtual sensors. In one example, virtual sensors include combinations and a series of communication combinations between related inputs, commands, and real sensors that together provide these inferred measurements.
[0087] FIG. 5A shows a pictorial view of a field graph representing a measured agronomic parameter such as crop yield. The field chart 500 in general represents an original set of parameter data obtained with an agricultural machine, where these data are not pre-processed or corrected according to the calibration correction system 138. For example, the field 500 represents the crop yield with respect to a location in the field as determined by a mass flow sensor. More specifically, but not by limitation, the operational parameter monitoring system 118 can use a mass flow sensor 122 and the geospatial system 120 according to yield monitoring logic 124 to obtain a relational set of data that is provided by the field map generator 150 in the form generally shown by the field map graph 500. It can be seen that the field map graph 500 represents data with a high degree of variance between the crop yield detected across the field. Specifically, there are individual rows that vary quite significantly when compared to a neighboring row. For example, each row can correspond with the collector width, and sensor information from sensors across the collector can vary. However, it is also noted that variances in the original parameter data can manifest on the map for specific plant rows or even a single plant, where information for these plants is sensed both individually and as a set of plants. This map probably reflects data inaccuracies as the crop yield is unlikely to vary
Petition 870170078527, of 10/16/2017, p. 125/168 / 56 that much between neighboring ranks. In one example, areas of high density detected (high yield yield detected) are usually colored red, while areas of medium density detected are usually yellow, and areas of low density detected are usually colored blue.
[0088] To further illustrate, in general it can be seen portions close to 502 and 504 in which a high yield of crop was originally detected with the monitoring system 118. On the contrary, in general it is shown in portions 506 and 508 that a yield of relatively low yield was detected by the 118 system. An average yield yield detected in general was detected in the area represented by reference numeral 503. Such a high degree of variability as presented on a map can be confusing when the map is observed by the operator 166. In addition, a group of transient characteristics is generally indicated by the grouping of spots within the circle referred to as the numeral 501. Graph 500 provides little information about the performance of the crop as well as the performance of the machine in harvesting the crop.
[0089] FIG. 5B shows a pictorial view of a smoothed field plot 510 representing an adjusted and corrected agronomic parameter such as crop yield. In one example, the calibration correction system 138 used pre-processing logic 142, and polarization collection logic 144 to prepare crop yield data and perform a grinding operation on that data. It can be seen that graph 510 in general indicates a lesser degree of variance between the various portions of the field and the adjusted yield of harvest values, when compared to the raw data indications of graph 500. In one example, the correction logic polarization 144 uses rectification logic 178 to remove a calibration bias determined between both separate cases of a single machine and individual cases of a plurality of machines
Petition 870170078527, of 10/16/2017, p. 126/168 / 56 that operates in the same field. For example, it can be seen in Graph 510 that the transient characteristics have been removed (for example, represented by 501 in Graph 500), and that areas of smoothed high density are generally represented by reference numerals 512 and 514. On the other hand, smoothed low density areas are generally represented by reference numerals 516 and 518. An example of a smoothed medium density area is generally represented by reference numeral 520. In this way, smoothed high density (for example, high yield of crop ) is represented by regions that are colored red, while smoothed average density is represented by regions that are colored yellow, and smoothed low density is represented by regions that are colored blue.
[0090] The field chart 510 provides an accurate field map, as generated by the field map generator 150, which allows an operator 166 to collect discoveries regarding the operation of the agricultural machine 100 and the performance of the particular crop that is harvested . Of course, it is noted that map 510 can also be representative of any of the other agronomic or operational parameters discussed earlier here.
[0091] FIG. 6 is a pictorial view of another example in which the agricultural machine 100 is shown as a tillage machine 600 (or disk). The tillage machine 600 illustratively includes a variety of tillage implements 602 which generally includes rotating discs that form trenches on a surface of the ground as the machine 600 moves in a general direction indicated by the arrow 610. It is noted that the tillage machine 600 is a representative view of a tillage machine and the calibration correction mechanisms discussed here can also be implemented in a variety of other tillage machines. The tillage machine 600 also illustratively includes guide wheels 604 and a
Petition 870170078527, of 10/16/2017, p. 127/168 / 56 mechanism for connection to an energized mobile machine, the mechanism generally represented in reference numeral 606. The tillage machine 600 can also include a variety of operational parameter sensors. For example, a tillage machine 600 includes tillage depth sensors 608 that can be arranged in a variety of locations on the machine, but which are particularly illustratively arranged on or near disks 602. Tillage depth sensors 608 can detect a depth of disk 602 within a soil surface, and provide the sensed data for another monitoring logic 130 of the operating parameter monitoring system 118. As discussed above with respect to agricultural machine 100, the detected parameter data can be used calibration correction system 138 to determine a polarization correction factor between individual sensors 608 on machine 600, and / or the calibration polarization between machine 600 and a variety of other sensors arranged on other tillage machines that perform a similar operation or the same operation.
[0092] Other soil conditions can also be monitored by machine 600 or any other agricultural machine described here. These other soil conditions may include, but are not limited to, soil moisture, soil temperature, organic matter composition, soil nutrient levels, volumetric soil density, and planter downward pressure with respect to a soil surface, among others.
[0093] FIG. 7 is a pictorial view of an example where agricultural machine 100 is shown as a planter 700. Planter 700 illustratively includes a support structure 702 that houses a plurality of row planting units 706. Planter 700 can also include a interface for connection to a mobile powered machine, the interface in general being represented by 704. As is discussed
Petition 870170078527, of 10/16/2017, p. 128/168 / 56 similarly with respect to agricultural machine 100 and tillage machine 600, planting machine 700 can include a variety of sensors arranged in a variety of locations on the machine and configured to sense parameters such as, but not limited to, the planting depth. In a particular example, machine orientation sensors 708 can detect the height of a planting depth sensor in relation to the ground. These machine orientation sensors can include planting depth sensors that provide planting depth data according to planting depth monitoring logic 128 and operating parameter monitoring system 118. The planting depth data obtained can be used by the calibration correction system 138 to determine a displacement both between individual sensors on the planter 700, and / or between sensors and a given calibration of machine 700 and a variety of other similar planting machines.
[0094] Other examples of agricultural machines (or any of the machines described above), according to modalities described here, may include sprayers or applicators to apply, for example, fertilizers, pesticides, or other nutrient formulas. Monitoring of operational parameters can be performed to obtain information regarding the rate at which said formulas are applied. In this way, the calibration correction system and methods described here can be used appropriately in determining an appropriate calibration and reducing calibration bias for chemical application operations, and specifically for operations that include measuring the rate at which a formula is applied during operation. In this way, the agronomic data that can be monitored and adjusted with modalities of a calibration correction system discussed here includes data associated with grain moisture, grain loss, grain quality, residue yield, residue quality,
Petition 870170078527, of 10/16/2017, p. 129/168 / 56 non-threshing properties, chemical application rate, soil moisture, soil temperature, organic matter composition, soil nutrient levels, volumetric soil density, and planter downward pressure with respect to a soil surface , among others.
[0095] This discussion mentioned processors and / or servers. In one example, processors and servers include computer processors with associated memory and timing circuits, not shown separately. They are functional parts of the systems or devices to which they belong and are activated by, and facilitate the functionality of other components or items in these systems.
[0096] Still, a number of user interface views have been discussed. They can take a wide variety of different forms and can have a wide variety of different user-operable input mechanisms arranged therein. For example, the input mechanisms that can be used by the user can be text boxes, check boxes, icons, links, scroll menus, search boxes, etc. They can also be performed in a wide variety of different ways. For example, they can be operated using a point and click device (such as a bali traek or mouse). They can be operated using hardware buttons, switches, a joystick or keyboard, thumb switches or thumb pads, etc. They can also be operated using a virtual keyboard or other virtual actuators. In addition, where the screen on which they are displayed is a touchscreen, they can be actuated using touch gestures. Also, where the device that displays them has speech recognition components, they can be operated using speech commands. [0097] A number of data stores have also been discussed. It will be noted that each of them can be broken up into multiple data stores. All stores can be local to the systems that access them, all can be remote, or even
Petition 870170078527, of 10/16/2017, p. 130/168 / 56 can be local while others are remote. All of these configurations are covered here.
[0098] Still, the figures show a number of blocks with written functionality for each block. It will be noted that fewer blocks can be used such that the functionality is performed by fewer components. In addition, more blocks can be used with the functionality distributed among more components.
[0099] FIG. 8 is a block diagram of agricultural machine 100, shown in FIG. 1, except that it communicates with elements in a remote server architecture 101. In one example, remote server architecture 101 can provide computing, software, data access, and storage services that do not require end user knowledge of physical location or configuration of the system that distributes the services. In many ways, remote servers can distribute services over a wide area network, such as the internet, using appropriate protocols. For example, remote servers can distribute applications over a wide area network and they can be accessed through a network browser or any other computing component. Software or components shown in FIG. 1 as well as the corresponding data, can be stored on the servers in a remote location. The computing resources in a remote server environment can be consolidated into a remote data center location or they can be dispersed. Remote server infrastructure can deliver services across divided data centers, even though they appear as a single access point for the user. Thus, the components and functions described here can be provided from a remote server at a remote location using a remote server architecture. Alternatively, they can be provided from a conventional server, or they can be installed on client devices
Petition 870170078527, of 10/16/2017, p. 131/168 / 56 directly, or in other ways.
[00100] In the example shown in FIG. 8, some items are similar to those shown in FIG. 1 and they are similarly numbered. FIG. 8 specifically shows that data visualization system 148, remote systems 160 and data storage 114 can be located at a remote server location 103. Therefore, the combine 100 accesses these systems via remote server location 103.
[00101] FIG. 8 also represents another example of a remote server architecture. FIG. 8 shows that it is also contemplated that some elements of FIG. 1 are arranged at remote server location 103 while others are not. For example, data storage 114 or agricultural machines 162, 164 can be arranged in a location separate from location 103, and accessed via the remote server at location 103. Regardless of where they are located, they can be accessed directly by combine 100, through a network (both a wide area network and a local area network), they can be hosted at a remote site by a service, or they can be provided as a service, or accessed by a connection service that resides in a remote location. In addition, data can be stored substantially in any location and intermittently accessed by, or directed to, intended parties. For example, physical carriers can be used instead of, or in addition to, electromagnetic wave carriers. In such a modality, where cell coverage is poor or non-existent, another mobile machine (such as a fuel truck) may have an automated information collection system. As the combination or machine approaches the fuel truck for refueling, the system automatically collects information from the combine using any type of ad-hoc wireless connection. The information collected can then
Petition 870170078527, of 10/16/2017, p. 132/168 / 56 be directed to the main network when the fuel truck reaches a location where there is cellular coverage (or other wireless coverage). For example, the fuel truck may enter a covered location when traveling to fuel other machines or when at a primary fuel storage location. All of these architectures are covered here. Additionally, information can be stored on the combine until the combine enters a covered location. The harvester itself can then send the information to the main network.
[00102] It will also be noted that the elements of FIG. 1, or portions thereof, may be arranged in a wide variety of different devices. Parts of these devices include servers, desktop computers, laptop computers, tablet computers, or other mobile devices, such as palm top computers, cell phones, smart phones, multimedia players, personal digital assistants, etc.
[00103] FIG. 9 is a simplified block diagram of an illustrative example of a portable device or mobile computing device that can be used as a customer or user portable device 16, in which the present system (or parts thereof) can be distributed. For example, a mobile device can be distributed in machine operator compartment 100 for use in generating, processing or displaying the data. Figures 10 to 12 are examples of mobile or portable devices.
[00104] FIG. 9 provides a general block diagram of the components of a client device 16 that can rotate some components shown in FIG. 1, which interact with the same, or both. In device 16, a communications link 13 is provided that allows the portable device to communicate with other computing devices and
Petition 870170078527, of 10/16/2017, p. 133/168 / 56 under some modalities provides a channel to receive information automatically, such as by scanning. Examples of communications link 13 include allowing communication through one or more communication protocols, such as wireless services used to provide cellular access to a network, as well as protocols that provide local wireless connections to networks.
[00105] Under other modalities, applications can be received on a removable Secure Digital (SD) card that is connected with an interface
15. Interface 15 and communication links 13 communicate with a processor 17 (which can also incorporate processor 102 from FIG. 1) along a bus 19 which is also connected with memory 21 and input / output (I / O) 23, as well as clock 25 and location system 27.
[00106] I / O 23 components, in one mode, are provided to facilitate entry and exit operations. I / O components 23 for various modes of device 16 may include input components such as buttons, touch sensors, optical sensors, microphones, touch screens, proximity sensors, accelerometers, orientation sensors and output components such as a display device, a speaker, and or a printer port. Other I / O 23 components can also be used.
[00107] The clock 25 illustratively comprises a real time clock component that emits a time and hour. Illustratively, it can also provide timing functions for processor 17.
[00108] Location system 27 illustratively includes a component that emits a current geographical location of device 16. This may include, for example, a global positioning system (GPS) receiver, a LORAN system, an estimated navigation system , a cell triangulation system, or other positioning system.
Petition 870170078527, of 10/16/2017, p. 134/168 / 56
It can also include, for example, mapping software or navigation software that generates desired maps, navigation routes and other geographic functions.
[00109] Memory 21 stores operating system 29, network settings 31, applications 33, application configuration settings 35, data storage 37, communication triggers 39, and communication configuration settings 41. Memory 21 can include all types of volatile and non-volatile computer readable memory devices. It can also include computer storage media (described below). Memory 21 stores computer-readable instructions which, when executed by processor 17, cause the processor to perform computer-implemented steps or functions according to the instructions. Processor 17 can be activated by other components to also facilitate its functionality.
[00110] FIG. 10 shows an example in which device 16 is a tablet 1000 computer. In FIG. 10, computer 1000 is shown with user interface display screen 1002. Screen 1002 can be a touch screen or a pen enabled interface that receives input from a pen or stylus. You can also use a virtual keyboard on the screen. Of course, it must be attached with a keyboard or other user input device using a suitable attachment mechanism, such as a USB port or wireless connection, for example. Computer 1000 can also receive voice inputs illustratively.
[00111] FIG. 11 provides an additional example of devices 16 that can be used, although others can also be used. In FIG. 11, a feature phone, smart phone or mobile phone 45 is provided as the device 16. The phone 45 includes a set of keypads 47 for dialing phone numbers, a display 49 capable of displaying images including application images, icons, pages network, photos, and video,
Petition 870170078527, of 10/16/2017, p. 135/168 / 56 and control buttons 51 to select items shown on the display. The phone includes an antenna 53 for receiving cell phone signals. In some embodiments, the phone 45 also includes a slot for a Digital Secure (SD) card 55 that accepts an SD card 57.
[00112] FIG. 12 is similar to FIG. 11, except that the phone is a smart phone 71. The smart phone 71 has a touch sensitive display 73 that displays icons or tiles or other user input mechanisms 75. The mechanisms 75 can be used by a user to run applications, make calls, perform data transfer operations, etc. in general, smart phone 71 is built on a mobile operating system and offers more advanced computing power and connectivity than a functionality phone. Note that other forms of devices 16 are possible.
[00113] FIG. 13 is an example of a computing environment in which elements of FIG. 1, or parts thereof, (for example) may be distributed. With reference to FIG. 13, an example system for implementing part of the modalities includes a general purpose computing device in the form of a computer 810. Computer components 810 may include, but are not limited to, a processing unit 820 (which may comprise the processor 102), a system memory 830, and a system bus 821 that couples various system components including the system memory with the processing unit 820. The system bus 821 can be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. Memory and programs described with reference to FIG. 1 can be distributed in the corresponding portions of FIG. 13.
[00114] The 810 computer typically includes a variety of media
Petition 870170078527, of 10/16/2017, p. 136/168 / 56 computer readable. Computer readable media can be any available media that can be accessed by the 810 computer and includes both volatile and non-volatile media, removable and non-removable media. By way of example, and not limitation, computer-readable media may comprise computer storage media and communication media. Computer storage media is different from, and does not include, a modulated data signal or carrier wave. It includes hardware storage media including both removable and non-removable, volatile and non-volatile media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile discs (DVD) or other optical disc storage, magnetic tapes, magnetic tape , magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by the 810 computer. The media can incorporate computer-readable instructions, data structures, modules program or other data in a transport mechanism and includes any means of information distribution. The term "modulated data signal" means a signal that has one or more of its characteristics defined or altered in such a way as to encode the information in the signal.
[00115] System memory 830 includes computer storage media in the form of volatile and / or non-volatile memory such as read-only memory (ROM) 831 and random access memory (RAM) 832. An input / output system basic 833 (BIOS), containing the basic routines that help transfer information between elements inside the 810 computer,
Petition 870170078527, of 10/16/2017, p. 137/168 / 56 as during startup, it is typically stored in ROM 831. RAM 832 typically contains data and / or program modules that are immediately accessible to and / or are currently being operated by the 820 processing unit. example, and not of limitation, FIG. 13 illustrates operating system 834, application programs 835, other program modules 836, and program data 837.
[00116] The 810 computer may also include other removable / non-removable volatile / non-volatile computer storage media. By way of example only, FIG. 13 illustrates a hard disk drive 841 that reads from or writes to non-removable non-volatile magnetic media, a magnetic disk drive 851, a non-volatile magnetic disk 852, an optical disk drive 855, and a non-volatile optical disk 856. Hard disk drive 841 is typically connected to the system bus 821 through a non-removable memory interface such as interface 840, and magnetic disk drive 851 and optical disk drive 855 are typically connected to the system bus 821 by a non-removable memory interface, such as the 850 interface.
[00117] Alternatively, or in addition, the functionality described here can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field Programmable Portal Arrangements (FPGAs), Application Specific Integrated Circuits (eg ASICs), Application Specific Standard Products (eg , ASSPs), System Systems on a Chip (SOCs), Complex Programmable Logic Devices (CPLDs), etc.
[00118] The drives and their associated computer storage media discussed above and illustrated in FIG. 13 provide storage of computer-readable instructions, data structures, program modules and other data for computer 810. In FIG. 13, for example,
Petition 870170078527, of 10/16/2017, p. 138/168 / 56 hard disk drive 841 is illustrated as storage operating system 844, application programs 845, other program modules 846, and program data 847. Note that these components can be both the same and different from the system operating conditions 834, application programs 835, other program modules 836, and program data 837.
[00119] A user can enter commands and information for computer 810 through input devices such as a keyboard 862, a microphone 863, and a pointing device 861, such as a mouse, traekball or touch panel. Other input devices (not shown) may include a joystick, game pad, satellite dish, scanner or the like. These and other input devices are usually connected to the processing unit 820 via an 860 user input interface that is coupled to the system bus, but can be connected by other interface and bus structures. A visual display 891 or other type of display device is also connected to the 821 system bus via an interface, such as an 890 video interface. In addition to the monitor, computers can also include other peripheral output devices such as speakers 897 and printer 896, which can be connected via an 895 output peripheral interface.
[00120] The 810 computer is operated in a networked environment using logical connections (such as the local area network - LAN, or wide area network WAN) to one or more remote computers, such as a remote 880 computer.
[00121] When used in a LAN network environment, computer 810 is connected to LAN 871 via a network interface or 870 adapter. When used in a WAN network environment, computer 810 typically includes an 872 modem or other means to
Petition 870170078527, of 10/16/2017, p. 139/168 / 56 to establish communications over WAN 873, such as the Internet. In a network environment, program modules can be stored on a remote memory storage device. FIG. 13 illustrates, for example, that remote application programs 885 may reside on remote computer 880.
[00122] It should also be noted that the different examples described here can be combined in different ways. That is, parts of one or more examples can be combined with parts of one or more other examples. All of this is covered here.
[00123] Example 1 is a method of reducing a sensing system bias through a first agricultural machine and a second agricultural machine, comprising:
access a collection of agronomic data indicative of an estimated crop yield, the collection including at least a first set of data detected by the first agricultural machine and a second set of data detected by the second agricultural machine;
scale the first and second data sets based on a yield correction factor;
determine a polarization between the first staggered data set and the second staggered data set;
perform a rectification operation, according to rectification logic, in the first and second staggered data sets, in which to perform the rectification operation includes:
generate a calibration correction factor based on the determined polarization;
reduce the polarization between the first staggered data set and the second staggered data set to obtain a corrected crop yield data set; and issue the calibration correction factor for the first and the
Petition 870170078527, of 10/16/2017, p. 140/168 / 56 second agricultural machine for use in sensing the first data set on the first agricultural machine and the second data set on the second agricultural machine; and generate a field map view indicative of the corrected set of crop yield data.
[00124] Example 2 is the method of any or all of the previous examples, in which to scale the first and second data sets comprises:
determining a first offset in the first data set and a second offset in the second data set; and generate the yield correction factor based on the first and second determined displacements.
[00125] Example 3 is the method of any or all of the previous examples, where staggering further comprises:
apply the yield correction factor for the first set to generate the first scaled data set; and apply the yield correction factor for the second set to generate the second scaled data set.
[00126] Example 4 is the method of any one or all of the previous examples, in which determining the first and second displacements comprises, respectively:
identify a first average deviation in the first set, where the first average deviation is greater than a minimum deviation limit that is necessary to perform the escalation; and identifying a second average deviation in the second set, where the second average deviation is greater than a minimum deviation limit that is required to perform the escalation.
[00127] Example 5 is the method of any or all of the previous examples, in which the first data set is sensed by
Petition 870170078527, of 10/16/2017, p. 141/168 / 56 first agricultural machine during a harvesting operation that is performed with respect to a first portion of a harvesting environment, and in which the second data set is sensed by the second agricultural machine during a harvesting operation that is performed with respect to a second portion of a harvest environment.
[00128] Example 6 is the method of any one or all of the previous examples, in which performing the grinding operation, according to the grinding logic, comprises performing an additive grinding function with respect to data yield of estimated harvest.
[00129] Example 7 is the method of any or all of the previous examples, in which performing the grinding operation additionally comprises:
identify at least one transient characteristic in the corrected set of crop yield data; and reduce the transient characteristic using artifact removal logic.
[00130] Example 8 is the method of any or all of the previous examples, where the at least one transient characteristic is indicative of a delayed speed correction.
[00131] Example 9 is the method of any or all of the previous examples, in which performing the grinding operation additionally comprises:
get an indication of terrestrial truth.
[00132] Example 10 is the method of any or all of the previous examples, in which the terrestrial truth indication identifies a measurement of actual crop yield.
[00133] Example 11 is a method of correcting a polarization of the sensing system in an agricultural machine, comprising:
access a collection of agronomic data detected by the
Petition 870170078527, of 10/16/2017, p. 142/168 / 56 agricultural machine, the collection including at least a first set and a second set;
adjust the first and second sets based on a parameter correction factor;
determine a polarization of the sensing system between the first and second adjusted sets;
perform a grinding operation on the first and second adjusted sets, the grinding operation including:
generate a calibration correction factor; and apply the calibration correction factor for the first and second sets adjusted to reduce the polarization of the sensing system; and to generate a visual data representation of the first and second sets adjusted with the reduction of the polarization of the sensing system.
[00134] Example 12 is the method of any or all of the previous examples, in which the first set includes agronomic data that is sensed during a first pass of the agricultural machine in an operating environment, and in which the second set includes agronomic data that is sensed during a second pass of the agricultural machine in the operating environment.
[00135] Example 13 is the method of any or all of the previous examples, in which performing the rectification operation comprises performing at least one of:
an additive rectification operation; or a localized regression rectification operation.
[00136] Example 14 is the method of any or all of the previous examples, in which agronomic data is indicative of at least one of:
Petition 870170078527, of 10/16/2017, p. 143/168 / 56 a yield parameter; a planting depth parameter; a soil moisture parameter; a crop parameter; or a geospatial parameter.
[00137] Example 15 is the method of any or all of the previous examples, in which adjusting the first and second sets based on a parameter correction factor comprises:
identify a displacement within each of the first and second sets;
generate a parameter correction factor based on the identified offset; and apply the parameter correction factor for the first and second sets.
[00138] Example 16 is the method of any or all of the previous examples, wherein the visual data representation comprises a corrected field map view.
[00139] Example 17 is the method of any or all of the previous examples, further comprising:
perform pre-processing logic that includes:
filter the first and second data sets based on a filter criterion, where the filter criterion is indicative of an agricultural machine's machine state.
[00140] Example 18 is an agricultural machine comprising:
a yield monitoring system that includes a mass flow sensor and a geospatial sensor, in which the field monitoring system is configured to obtain a collection of yield density information;
a calibration correction system configured for
Petition 870170078527, of 10/16/2017, p. 144/168 / 56 determine a calibration shift factor, in which the calibration correction system includes:
pre-processing logic that schedules the collection of information yield density; and polarization correction logic that performs a rectification operation, based on the calibration displacement factor, in the staggered collection of the yield density information to remove a polarization from the sensing system; and a data visualization system that generates a field map view of the information yield density collection with the sensing system polarization removed.
[00141] Example 19 is the agricultural machine of any one or all of the previous examples, further comprising:
a calibration system configured to provide the calibration shift factor for the monitoring system field; and in which the monitoring system field uses the calibration displacement factor to obtain the information yield density collection.
[00142] Example 20 is the agricultural machine of any or all of the previous examples, in which the polarization correction logic comprises the data verification component, and in which the data verification component is configured to:
obtain an indication of a terrestrial truth measurement; and use terrestrial truth measurement to perform the rectification operation with the polarization correction logic.
[00143] Although the matter has been described in the specific language for structural features and / or methodological acts, it should be understood that the matter defined in the attached claims is not necessarily limited to the specific features or acts described above. Instead,
Petition 870170078527, of 10/16/2017, p. 145/168 / 56 the specific functionalities and acts described above are disclosed as exemplary ways of implementing the claims.
Petition 870170078527, of 10/16/2017, p. 146/168

权利要求:
Claims (20)
[1]
1. Method to reduce a polarization of the sensing system through a first agricultural machine and a second agricultural machine, characterized by the fact that it comprises:
access a collection of agronomic data indicative of an estimated crop yield, the collection including at least a first set of data sensed by the first agricultural machine and a second set of data sensed by the second agricultural machine;
scale the first and second data sets based on a yield correction factor;
determine a polarization between the first set of scaled data and the second set of scaled data;
perform a rectification operation, according to rectification logic, in the first and second set of scaled data, in which to perform the rectification operation includes:
generate a calibration correction factor based on the determined polarization;
reduce the polarization between the first set of scaled data and the second set of scaled data to obtain a corrected set of crop yield data; and issuing the calibration correction factor for the first and second agricultural machines for use when sensing the first data set on the first agricultural machine and the second data set on the second agricultural machine; and generate a field map view indicative of the corrected set of crop yield data.
[2]
2. Method according to claim 1, characterized by the fact that staggering the first and second data sets comprises:
Petition 870170078527, of 10/16/2017, p. 147/168 determining a first offset in the first data set and a second offset in the second data set; and generate the yield correction factor based on the first and second determined displacements.
[3]
3. Method according to claim 2, characterized by the fact that staggered additionally comprises:
apply the yield correction factor to the first set to generate the first set of scaled data; and apply the yield correction factor to the second set to generate the second set of scaled data.
[4]
4. Method according to claim 2, characterized by the fact that determining the first and second displacements comprises, respectively:
identify a first average deviation in the first set, where the first average deviation is greater than a minimum deviation limit that is required to perform the escalation; and identifying a second average deviation in the second set, where the second average deviation is greater than a minimum deviation limit that is necessary to perform the scheduling.
[5]
5. Method according to claim 1, characterized by the fact that the first data set is sensed by the first agricultural machine during a harvesting operation that is performed in relation to a first portion of a harvesting environment, and in which the second data set is sensed by the second agricultural machine during a harvesting operation that is performed in relation to a second portion of a harvesting environment.
[6]
6. Method according to claim 1, characterized by the fact that performing the grinding operation, according to the grinding logic, comprises performing an additive grinding function with
Petition 870170078527, of 10/16/2017, p. 148/168 with respect to estimated crop yield data.
[7]
7. Method according to claim 1, characterized by the fact that performing the grinding operation additionally comprises:
identify at least one transient characteristic in the corrected set of crop yield data; and reduce the transient characteristic using artifact removal logic.
[8]
Method according to claim 7, characterized in that the at least one transient characteristic is indicative of a delayed speed correction.
[9]
9. Method according to claim 1, characterized by the fact that performing the grinding operation additionally comprises:
get an indication of terrestrial truth.
[10]
10. Method according to claim 9, characterized by the fact that the indication of terrestrial truth identifies a measurement of real crop yield.
[11]
11. Method to correct a polarization of the sensing system in an agricultural machine, characterized by the fact that it comprises:
access a collection of agronomic data sensed by the agricultural machine, the collection including at least a first set and a second set;
adjust the first and second sets based on a parameter correction factor;
determine a polarization of the sensing system between the first and second adjusted sets;
perform a rectification operation on the first and second
Petition 870170078527, of 10/16/2017, p. 149/168 sets adjusted, the grinding operation including:
generate a calibration correction factor; and apply the calibration correction factor to the first and second sets adjusted to reduce the polarization of the sensing system; and generating a visual data representation of the first and second sets adjusted by reducing the polarization of the sensing system.
[12]
12. Method according to claim 11, characterized in that the first set includes agronomic data that is sensed during a first pass of the agricultural machine in an operating environment, and in which the second set includes agronomic data that is sensed during a second pass of the agricultural machine in the operating environment.
[13]
13. Method according to claim 11, characterized by the fact that performing the grinding operation comprises performing at least one of:
an additive grinding operation; or a localized regression rectification operation.
[14]
14. Method according to claim 11, characterized by the fact that agronomic data are indicative of at least one of:
a performance parameter; a planting depth parameter; a soil moisture parameter; a crop parameter; or a geospatial parameter.
[15]
15. Method according to claim 11, characterized by the fact that adjusting the first and second sets based on a parameter correction factor comprises:
Petition 870170078527, of 10/16/2017, p. 150/168 identify an offset in each of the first and second sets;
generate a parameter correction factor based on the identified offset; and apply the parameter correction factor to the first and second sets.
[16]
16. Method according to claim 11, characterized in that the visual data representation comprises a corrected field map view.
[17]
17. Method according to claim 11, characterized by the fact that it additionally comprises:
perform pre-processing logic that includes:
filter the first and second data sets based on a filter criterion, where the filter criterion is indicative of an agricultural machine's machine state.
[18]
18. Agricultural machinery, characterized by the fact that it comprises:
a performance monitoring system that includes a mass flow sensor and a geospatial sensor, where the performance monitoring system is configured to obtain a collection of yield density information;
a calibration correction system configured to determine a calibration shift factor, where the calibration correction system includes:
pre-processing logic that scales the collection of yield density information; and polarization correction logic that performs an operation of
Petition 870170078527, of 10/16/2017, p. 151/168 rectification, based on the calibration displacement factor, in the staggered collection of yield density information to remove a sensing system bias; and a data visualization system that generates a field map view of the yield density information collection with the sensing system polarization removed.
[19]
19. Agricultural machine according to claim 18, characterized by the fact that it additionally comprises:
a calibration system configured to provide the calibration shift factor for the yield monitoring system; and where the yield monitoring system uses the calibration displacement factor to obtain the yield density information collection.
[20]
20. Agricultural machine according to claim 18, characterized by the fact that the polarization correction logic comprises a data verification component, and in which the data verification component is configured to:
obtain an indication of a terrestrial truth measurement; and use terrestrial truth measurement when performing the rectification operation with the polarization correction logic.
Petition 870170078527, of 10/16/2017, p. 152/168
1/15
MACHINE MACHINE
LU
O
LU
The <
LL
A.D
LU
O
O
DC * <
Z>
ω z>
© I ©
<
_l o
O
A.D
The <
<
z>
LU
Q <
OI ©
Õ '<
The <
o hÍ ω o ω o <
A.D
O <O Ξ DC LU Iω§ ω ο <
CC o
O
Q O <O Ξ <LU CC ω o ω ω Qj <> Ξ- <LU _l I- Ο ω £ ω ι— οο ζ Ζ) ο ω ο
MONITORING LOGICHUMIDITY126 OTHER MONITORING LOGIC130 MONITORING LOGICINCOME124 MONITORING LOGIC FOR 'PLANTING DEPTH 128
ϋ
I — I
LLI SOI α <ό
Ο ^- ο
LLI ο
° ο ω, <Ο ο <<S 00 ω <ω ο
OLLJ Z <N | CC LLIO-S -h | LLJ <α ωSaw<LLJthe oThe DC _l CL 5 o- ^ 1-i E9fSZ) LUThe Q DC § ω <O OI o 2 2 LU DC ^Q 0 LU <Q lu n. Q, g 3luOOQ ‘<<ZÍ Oh!S LU CC o oc <o DC _jo o o _i ü o.
Petition 870170078527, of 10/16/2017, p. 153/168
2/15

类似技术:

---

公开号 | 公开日 | 专利标题

---

BR102017022222A2|2018-05-29|METHODS FOR REDUCING AND CORRECTING SENSING SYSTEM POLARIZATION, AND, AGRICULTURAL MACHINE

---

US10408645B2|2019-09-10|Correcting bias in parameter monitoring

---

US10028435B2|2018-07-24|Sensor calibration using field information

---

US9972058B2|2018-05-15|Method for correcting the time delay in measuring agricultural yield

---

BR112017026437B1|2022-01-18|COMPUTER SYSTEM AND COMPUTER DEPLOYED METHOD FOR MONITORING ONE OR MORE FIELDS OPERATIONS

---

BR102016018669A2|2017-03-21|crop route generator system, crop machine, and computer-implemented method for generating a crop route for a crop machine

---

US10209235B2|2019-02-19|Sensing and surfacing of crop loss data

---

EP3709238A1|2020-09-16|Computer-generated accurate yield map data using expert filters and spatial outlier detection

---

BR102020002765A2|2020-10-20|METHOD TO CONTROL A WORK MACHINE, WORK MACHINE, AND, IMAGE SELECTION SYSTEM

---

AU2015238898A1|2015-10-29|System and method for forest management using stand development performance as measured by leaf area index

---

US9894836B2|2018-02-20|Machine operation enhancement

---

BR102020001022A2|2020-10-20|METHOD TO CONTROL A MACHINE, COMPUTER SYSTEM, AND WORKING MACHINE

---

JP6589978B2|2019-10-16|Plant health diagnosis apparatus, method and program

---

Anderson et al.2019|Prediction of maize grain yield before maturity using improved temporal height estimates of unmanned aerial systems

---

EP3662730A1|2020-06-10|Machine control through active groundterrain mapping

---

US9807932B2|2017-11-07|Probabilistic control of an agricultural machine

---

AU2016294498A1|2018-02-08|Modular systems and methods for determining crop yields with high resolution geo-referenced sensors

---

US20200323129A1|2020-10-15|Augmented crop loss sensing

---

EP3732941A1|2020-11-04|Residue monitoring and residue-based control

---

BR102015009517A2|2016-04-12|sugar cane harvester, method of harvesting a crop in a field, and, computer readable storage medium

---

US10278329B2|2019-05-07|Grain management system and combine

---

US10768156B1|2020-09-08|Yield analysis through agronomic analytics

---

BR102020009247A2|2020-11-17|method for controlling a mobile working machine, and mobile and agricultural working machines

---

US20210051849A1|2021-02-25|Enhancement of combine harvester yield data through augmentation with spatial grain cart data

同族专利:

---

公开号 | 公开日

---

US20180122020A1|2018-05-03|

---

EP3316208A1|2018-05-02|

---

US10832351B2|2020-11-10|

引用文献:

---

公开号 | 申请日 | 公开日 | 申请人 | 专利标题

---

---

US5995895A|1997-07-15|1999-11-30|Case Corporation|Control of vehicular systems in response to anticipated conditions predicted using predetermined geo-referenced maps|

---

US7313478B1|2006-06-08|2007-12-25|Deere & Company|Method for determining field readiness using soil moisture modeling|

---

US20080306804A1|2007-06-06|2008-12-11|Opdycke Thomas C|Systems for scheduling marketing campaigns in public places in order to enable measurement and optimization of audience response|

---

WO2015048499A1|2013-09-27|2015-04-02|John Earl Acheson|Yield monitor calibration method and system|

---

GB201405788D0|2014-03-31|2014-05-14|Imp Innovations Ltd|A computer implemented method of deriving performance from a local model|

---

US10109024B2|2014-09-05|2018-10-23|The Climate Corporation|Collecting data to generate an agricultural prescription|

---

RU2670905C9|2015-04-21|2018-12-12|Фармерс Эдж Инк.|Methods of yield data calibration|US11140807B2|2017-09-07|2021-10-12|Deere & Company|System for optimizing agricultural machine settings|

---

US10687466B2|2018-01-29|2020-06-23|Cnh Industrial America Llc|Predictive header height control system|

---

CN108681724A|2018-05-25|2018-10-19|深圳春沐源控股有限公司|Farming operations monitoring method and device|

---

US10736266B2|2018-05-31|2020-08-11|Deere & Company|Control of settings on a combine harvester with bias removal|

---

US11178818B2|2018-10-26|2021-11-23|Deere & Company|Harvesting machine control system with fill level processing based on yield data|

---

US11240961B2|2018-10-26|2022-02-08|Deere & Company|Controlling a harvesting machine based on a geo-spatial representation indicating where the harvesting machine is likely to reach capacity|

---

CN109614763B|2019-01-30|2019-09-06|北京师范大学|A kind of area crops yield estimation method correcting crop modeling based on multi-source information substep|

---

WO2020180424A1|2019-03-04|2020-09-10|Iocurrents, Inc.|Data compression and communication using machine learning|

---

US11234366B2|2019-04-10|2022-02-01|Deere & Company|Image selection for machine control|

---

US11079725B2|2019-04-10|2021-08-03|Deere & Company|Machine control using real-time model|

---

US20210289703A1|2020-03-17|2021-09-23|Cnh Industrial America Llc|System and method for controlling harvester implement position of an agricultural harvester|

---

US20210321567A1|2020-04-21|2021-10-21|Deere & Company|Agricultural harvesting machine control using machine learning for variable delays|

法律状态:
2018-05-29| B03A| Publication of an application: publication of a patent application or of a certificate of addition of invention|

优先权:

---

申请号 | 申请日 | 专利标题

---

US15/340704|2016-11-01|

---

US15/340,704|US10832351B2|2016-11-01|2016-11-01|Correcting bias in agricultural parameter monitoring|

---