• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    A device 225 may receive equipment information, associated with a first device 205, including information associated with identified abnormalities as a function of operating information collected during operation of the first equipment 205, and messages generated during operation of the device. first device 205. The device 225 may receive maintenance information, associated with the first device 205, which identifies one or more component failures associated with one or more pieces of equipment. The device 225 may identify associations between the one or more coin failures and the first equipment information. The device 225 may receive equipment information, associated with a second equipment 205, including information associated with identified abnormalities based on the operating information collected during operation of the second equipment 205, and messages generated during the operation of the second equipment 205. 205. The device 225 may generate and provide a prediction, associated with a future failure of a piece of equipment of the second equipment 205, based on the second equipment information and associations.
    公开号:FR3053813A1
    申请号:FR1756442
    申请日:2017-07-07
    公开日:2018-01-12
    发明作者:Johan Arnold SMIT；Paul BUTTERLEY
    申请人:GE Aviation Systems Ltd；
    IPC主号:
    专利说明:

    (57) A device 225 can receive cPequipment information, associated with a first equipment 205, including information associated with anomalies identified as a function of operating information collected during the operation of the first equipment 205, and messages generated during operation. of the first piece of equipment 205. The device 225 can receive maintenance information, associated with the first piece of equipment 205, which identifies one or more failures of parts associated with one or more pieces of equipment. The device 225 can identify associations between the one or more parts failures and the first equipment information. The device 225 can receive equipment information, associated with a second equipment 205, including information associated with anomalies identified as a function of the operating information collected during the operation of the second equipment 205, and messages generated during the operation of the second equipment 205. The device 225 can generate and provide a prediction, associated with a future failure of a piece of equipment of the second equipment 205, as a function of the information of second equipment and of the associations.
    Dispositr ofmaintenance Deviceuser215_____ y
    Network
    -4Ώ. Environmental provisions
    Environment of nuaqe informatiaue 250
    Ç j Platform p r onostiC225
    IT resource - Miomatiq resource p 1 Λ Ppsso Ir-n nf (rr cil> 1e222 - Resource1 ilomaiq p 22
    VMS .JiLl HYPs


    Prediction rules for predicting part failure
    One or more types of data can be collected in association with an aircraft and / or an operation of the aircraft, such as fast access recorder (QAR) data, engine control unit (EMU) data, post-flight report (PFR) data, maintenance, repair, and overhaul (MRO) data (for example, weather data, route data, airport data), or the like.
    According to some possible implementations, a method can include receiving, by one or more devices, first equipment information associated with a first equipment, in which the first equipment information can include information associated with first anomalies identified as a function first operating information collected during the operation of the first equipment, and wherein the first equipment information may include information associated with first messages, associated with the operation of the first equipment, which are generated during the operation of the first equipment; receive, by the one or more devices, first maintenance information, associated with the first equipment, which identifies one or more failures of parts associated with one or more pieces of equipment; identify, by the one or more devices, associations between the one or more parts failures and the first equipment information; to receive, by the one or more devices, second equipment information associated with a second equipment, in which the second equipment information can include information associated with second anomalies identified as a function of second operating information collected during operation of the second equipment, and wherein the second equipment information may include information associated with second messages, associated with the operation of the second equipment, which are generated during the operation of the second equipment; generate, by the one or more devices and based on information from second equipment and associations, a prediction associated with a future failure of a piece of equipment of the second equipment; and providing, by the one or more devices, information associated with the prediction.
    In some possible implementations, a device may include one or more processors for: receiving first equipment information associated with one or more first pieces of equipment, wherein the first equipment information may include information associated with identified anomalies according to the operating information collected during the operation of the one or more first pieces of equipment, and in which the first piece of information can include information associated with messages, associated with the operation of the one or more first pieces of equipment, which are generated during the operation of one or more first pieces of equipment; receive maintenance information, associated with one or more first pieces of equipment, which identifies one or more failures of parts of one or more pieces of equipment of the one or more first pieces of equipment; identify associations between the one or more parts failures and the first equipment information; and storing information, regarding associations between the one or more part failures and the first equipment information, to allow a prediction to be made regarding a future failure of a piece of equipment of a second element of the 'equipment.
    According to certain possible implementations, a computer-readable medium which is not transient can store instructions which, when executed by one or more processors, cause the one or more processors: to receive information from the first equipment associated with the first equipment, the first equipment information may include information associated with first anomalies identified based on first operating information collected during operation of the first equipment, and wherein the first equipment information may include information associated with first messages, associated with the operation of the first equipment, which are generated during the operation of the first equipment; access associations identified based on information associated with one or more equipment part faults and second equipment information, in which one or more equipment part faults can be associated with the second equipment and can be identified based on maintenance information associated with the second equipment, wherein the second equipment information may include information associated with second anomalies identified based on second operating information collected during operation of the second equipment, and wherein the information second equipment may include information associated with second messages, associated with the operation of the second equipment, which are generated during the operation of the second equipment; generate, based on information from the first equipment and associations, a prediction associated with a future failure of a piece of equipment from the first equipment; and provide information associated with the prediction.
    - Figs. IA and IB are schematic diagrams of an overview of an example of implementation described here;
    -Fig. 2 is a diagram of an example of an environment in which systems and / or methods, described here, can be implemented;
    -Fig. 3 is a diagram of examples of components of one or more devices in FIG. 2;
    -Fig. 4 is a flow diagram of an exemplary process for generating a prognosis rule for predicting a future part failure associated with an aircraft; and
    -Fig. 5 is a flow diagram of an exemplary process for generating a prediction, associated with a future part failure associated with an aircraft, according to a prognosis rule.
    The following detailed description of the implementation examples refers to the accompanying drawings. The same reference numbers in different drawings can identify identical or similar elements.
    An aircraft is a complex device that can experience a large number of failures and / or faults associated with a large number of parts and / or systems (Here, collectively referred to as parts of an aircraft, and individually as a part of an aircraft). A considerable amount of information can be collected in association with the aircraft and / or the operation of the aircraft, such as information associated with the operation of the aircraft during one or more flights, during landing, during takeoff, during ground maneuvers (here designated as operating information), information associated with failures, maintenance, repair, servicing or the like of parts, associated with the aircraft (here designated as maintenance information), and / or information associated with an environment in which the aircraft flies, operates, is based, or the like (here designated as information on the environment). However, due to the large amount of information available and the number of different parts of an aircraft, identifying one or more of these types of information that is useful in predicting future part failure can be difficult, costly, and costly. time, and / or resources.
    Implementations described here can provide a prognostic platform for generating one or more prognostic rules used to predict a future part failure associated with an aircraft. In some implementations, the prediction platform may generate the prognosis rule based on the analysis of operating information, maintenance information, and / or environmental information associated with multiples (for example, hundreds, thousands) operations of multiple aircraft. In some implementations, the prognostic platform may use the prognostic rule to predict a future part failure associated with an aircraft.
    Notably, while the techniques described here are described in association with the generation of prognosis rules and predictions of part failures in the aeronautical context, these techniques can also be implemented in other contexts. For example, these techniques can be implemented to generate prognosis rules and predictions of part failures associated with a type of equipment (for example, including one or more systems, devices, machines, or other) other than an aircraft, such as another type of transportation equipment (for example, a train, automobile, boat), industrial equipment, manufacturing equipment, mining equipment, oil and gas equipment, d electrical equipment (for example, associated with the generation of electricity, the transmission and / or distribution of electricity), a device, a motor, a turbine, or others.
    In these cases, the forecasting platform can identify one or more prognosis rules as a function of the operating information associated with one or more items of equipment, maintenance information associated with one or more items of equipment, and / or environmental information associated with one or more items of equipment. The prognostic platform can then use the one or more prognostic rules to predict a future part failure associated with an item of equipment.
    Figs. IA and IB are a schematic diagram of an overview of an exemplary implementation 100 described here. For the purposes of implementation example 100, it is assumed that each aircraft in a set of aircraft (for example, aircraft 1 to aircraft Nl) includes one or more aircraft devices capable of receiving (for example, detect, collect, determine) operating information associated with the operation of the aircraft series.
    As shown in FIG. IA, and by the reference number 105, an aircraft device 1, associated with the aircraft 1, can receive operating information associated with the aircraft 1 during the operation of the aircraft 1. Similarly, as shown by the reference number 110, an aircraft device Nl, associated with the aircraft Nl, can receive operating information associated with the aircraft Nl during the operation of the aircraft N1. As shown by the reference numerals 115 and 120, the devices from aircraft 1 to aircraft Nl can provide operating information the aircraft of aircraft 1 and of aircraft Nl, respectively, to a prognosis platform.
    As shown by the reference number 125, the forecast platform can also receive maintenance information associated with aircraft 1 up to aircraft N-1. As shown by the reference number 130, the forecasting platform can also receive information on the environment associated with the aircraft 1 up to the aircraft Nl and / or the operation of the aircraft 1 up to the aircraft Nl.
    As shown by the reference number 135, the forecasting platform can generate one or more prognosis rules based on information which identifies one or more parts failures and operating information, maintenance information, and / or information on the environment. A prognosis rule may include a rule associated with predicting a future part failure of an aircraft part.
    As shown in FIG. IB, and by the reference number 140, the aircraft device N, associated with the aircraft N (for example, an aircraft not included in the aircraft 1 up to the aircraft Nl), can receive information from operation associated with the aircraft N during the operation of the aircraft N. As shown by the reference number 145, the aircraft device N can provide information on the operation of the aircraft N to the forecasting platform.
    As shown by the reference number 150, the forecasting platform can also receive, from the maintenance device, maintenance information associated with the aircraft N. As shown by the reference number 155, the forecasting platform can also receive, from the environmental device, information on the environment associated with the aircraft N and / or with the operation of the aircraft N. Notably, while an example of implementation 100 is described in the context of generating a prediction for a future part failure of aircraft N, in some implementations, a prediction for a future part failure can be generated for any of aircraft 1 to aircraft Nl using the prognosis rules .
    As shown by reference number 160, the prognostic platform can access the information associated with one or more prognostic rules, generated and stored by the prognostic platform as described above in relation to FIG. IA. As shown by reference number 165, the forecasting platform can generate a prediction for a future part failure, associated with the aircraft N, according to one or more prognosis rules and operating information associated with the aircraft N, maintenance information associated with aircraft N, and / or environmental information associated with aircraft N.
    As shown by reference number 170, the forecasting platform can provide information associated with the prediction of future part failure to a user device, such as a user device associated with an owner and / or a user of the aircraft N (for example, in such a way that a preventive or curative action can be carried out).
    In this way, a forecast platform can generate one or more prognosis rules and can generate a prediction associated with a future aircraft part failure using the one or more prognosis rules. This can allow future part failure to be avoided and / or repaired before it occurs, thereby improving the reliability, safety, usability, or the like of the aircraft.
    In addition, human and IT resources of the user device, and / or network resources consumed by the user device can be saved since the forecasting platform can allow the owner and / or user of the aircraft to '' quickly and easily identify a potential future part failure, thus requiring less working hours and / or less IT resources and / or less network consumption by the user device.
    As indicated above, Figs. IA and IB are provided simply as an example. Other examples are possible and may differ from what has been described with reference to Figs. IA and IB.
    Fig. 2 is a diagram of an example of an environment 200 in which systems and / or methods, described here, can be implemented. As shown in FIG. 2, the environment 200 may include one or more aircraft 205-1 to 205-N (N> 1) (below collectively and individually referred to as aircraft 205), and each aircraft 205 may include one or more aircraft devices correspondents 210-1 to 210-N (below designated collectively by aircraft device 210 and individually by aircraft device 210). As further shown, the environment 200 may include a maintenance device 215, an environmental device 220, a platform3053813 formeο prognosis form 225 hosted in a cloud computing environment 230, a user device 235, and a network 240. Devices Environment 200 can be interconnected via wired connections, wireless connections, or a combination of wired and wireless connections.
    Aircraft 205 includes a vehicle that can fly. For example, aircraft 205 may include an aircraft, such as a jet, propeller plane, helicopter, glider, drone (UAV), spacecraft, satellite, or the like. In some implementations, aircraft 205 may include one or more aircraft devices 210.
    The aircraft device 210 includes one or more devices capable of detecting, collecting, receiving, determining, processing, storing, and / or providing operating information associated with the operation of aircraft 205. For example, the aircraft device 210 may include a device capable of detecting, collecting, measuring, receiving, or otherwise determining operating information associated with aircraft 205, such as an acoustic sensor, a vibration sensor, a temperature sensor, a pressure sensor, a sensor and / or navigation instrument, speed sensor, current sensor, voltage detector, flow meter, position sensor, accelerometer, strain gauge, torque sensor, viscometer, or others . In certain implementations, the aircraft device 210 may include any type of device which can be installed on and / or in the aircraft 205 and which can determine operating information associated with the aircraft 205 and / or one or more multiple systems of aircraft 205.
    In some implementations, the aircraft device 210 may be able to provide the operating information. For example, the aircraft device 210 may include a communication device which allows the aircraft device 210 to communicate with another aircraft device 210, maintenance device 215, environmental device 220, forecast platform 225, user device 235, or others, via a wired and / or wireless connection (for example, via Wi-Fi connection, Bluetooth connection, cellular network connection, Ethernet connection, etc.).
    The maintenance device 215 includes a device capable of receiving, determining, processing, storing, and / or providing maintenance information associated with the aircraft 205. For example, the maintenance device 215 may include a server or a group of servers. In some implementations, the maintenance device 215 may be able to send information to and / or receive information from another device in the environment 200, such as the forecasting platform 225.
    The environmental device 220 includes a device capable of receiving, determining, processing, storing, and / or providing information on the environment associated with the aircraft 205 and / or with the operation of the aircraft 205. For example, the environmental device 220 can include a server or group of servers. In some implementations, the environmental device 220 may be able to send information to and / or receive information from another device in the environment 200, such as the forecasting platform 225.
    The forecast platform 225 includes one or more devices capable of creating, identifying, generating, storing and / or using one or more forecast rules associated with a prediction of part failure associated with the aircraft 205. For example, the forecast platform 225 can include a server or group of servers. In certain implementations, the forecasting platform 225 may be able to receive operating information, maintenance information, and / or information on the environment associated with the aircraft 205 and / or with the operation of the aircraft 205, and generating, as a function of the one or more prognosis rules, a prediction of part failure associated with the aircraft 205. In addition, or as a variant, the prognosis platform 225 may be able to provide information associated with the prediction of part failure to another device, such as a user device 235 (for example, such that a preventive or curative action can be taken).
    In some implementations, as shown, the prediction platform 225 may be in a cloud computing environment 230. Notably, while the implementations described here describe the prediction platform 225 as being in a computing cloud environment 230, in some implementations, the prediction platform 225 may not be in a cloud (i.e., may be implemented outside of a cloud environment) or may be in part in a cloud computing environment.
    The cloud computing environment 230 can include an environment that hosts a prediction platform 225. The cloud computing environment 230 can provide IT services, software, data access, storage, etc. which do not require the end user (for example, the user device 235) to know a physical location and the configuration of the system (s) and / or device (s) which host (s) the platform -prognosis form 225. As shown, the cloud computing environment 230 can include a group of computing resources 232 (collectively designated as computing resources 232 and individually as “computing resource 232”).
    Computer resource 232 includes one or more personal computers, computer workstations, server devices, or another type of computer and / or communication device. In some implementations, the computer resource 232 can host a forecasting platform 225. The cloud resources can include computer instances running in the computer resource 232, storage devices placed in the computer resource 232, data transfer devices provided by computer resource 232, etc. In some implementations, the computer resource 232 can communicate with other computer resources 232 via wired connections, wireless connections, or a combination of wired and wireless connections.
    As further shown in FIG. 2, the computer resource 232 can include a group of cloud resources, such as one or more applications (“APPs”) 232-1, one or more virtual machines (“VMs”) 232-2, virtualized storage (“VSs”) ) 232-3, one or more hypervisors (“HYPs”) 232-4, or others.
    The 232-1 application can include one or more software applications that can be delivered to or accessible by the user device 235. The 232-1 application can eliminate a need to install and run the software applications on the user device 235. For example, the application 232-1 can include software associated with a forecasting platform 225 and / or any other software that can be provided via the cloud computing environment 230. In certain implementations, an application
    232-1 can send / receive information to / from one or more other 232-1 applications, via a virtual machine 2322.
    The virtual machine 232-2 can include a software implementation of a machine (for example, a computer) that runs programs like a physical machine. The virtual machine 232-2 can be either a system virtual machine or a process virtual machine, depending on the use and the degree of correspondence to any real machine by the virtual machine 232-2. A system virtual machine can provide a complete system platform that supports the running of a complete operating system ("OS"). A process virtual machine can execute a program alone, and can support a process alone. In some implementations, the virtual machine 232-2 can run on behalf of a user (for example, a user device 235), and can manage the infrastructure of the cloud computing environment 230, such as managing data, synchronization, or long-term data transfers.
    Virtualized storage 232-3 can include one or more storage systems and / or one or more devices that use virtualization techniques in computer resource storage systems or devices 232. In some implementations, in the context of 'a storage system, types of virtualization can include block virtualization and file virtualization. Block virtualization can refer to the abstraction (or separation) of logical storage from physical storage in such a way that it is possible to access the storage system regardless of physical storage or heterogeneous structure. Separation can allow administrators of the storage system to have flexibility in how administrators manage storage for end users. File virtualization can eliminate dependencies between data accessed at a file level and a location where files are physically stored. This can help optimize storage usage, server consolidation, and / or the performance of non-disruptive file migrations.
    The 232-4 hypervisor can provide hardware virtualization techniques that allow multiple operating systems (for example, guest operating systems) to run concurrently on a host computer, such as a computer resource 232. L 232-4 hypervisor can present a virtual operating platform to guest operating systems, and can manage the execution of guest operating systems. Multiple examples of a variety of operating systems can share virtualized hardware resources.
    User device 235 includes a device capable of receiving, storing, processing, and / or providing information associated with a prediction of part failure associated with aircraft 205. For example, user device 235 may include a communication and computer device , like a mobile phone (for example, a Smartphone, a radiotelephone, etc.), a laptop, a tablet, a manual computer, a desktop computer, a server, a group of servers, a communication device that can be worn (for example, a connected watch, a pair of connected glasses, etc.), or a similar type of device.
    Network 240 may include one or more wired and / or wireless networks. For example, network 240 may include a cellular network (for example, long-term evolution network (LTE), a 3G network, a code division multiple access network (CDMA), etc.), a mobile network public land line (PLMN), local area network (LAN), wide area network (WAN), metropolitan area network (MAN), telephone network (e.g. public switched telephone network (PSTN)), private network, network ad hoc, an intranet, the Internet, a fiber optic network, or the like, and / or a combination of these or other types of networks.
    The number and arrangement of devices and networks shown in FIG. 2 are provided as an example. In practice, this may be additional devices and / or networks, fewer devices and / or networks, different devices and / or networks, or devices and / or networks arranged differently from those shown in FIG. 2. In addition, two or more devices shown in FIG. 2 can be implemented in a single device, or a single device shown in FIG. 2 can be implemented as multiple distributed devices. In addition, or alternatively, a series of devices (for example, one or more devices) from environment 200 can perform one or more functions described as being performed by another series of devices from environment 200.
    Fig. 3 is a diagram of examples of components of a device 300. The device 300 may correspond to the aircraft device 210, to the maintenance device 215, to the environmental device 220, to the forecast platform 225, and / or to the user device 235. In certain implementations, the aircraft device 210, the maintenance device 215, the environmental device 220, the forecasting platform 225, and / or the user device 235 may include one or more devices 300 and / or one or more components of the device 300. As shown in FIG. 3, the device 300 may include a bus 310, a processor 320, a memory 330, a storage component 340, an input component 350, an output component 360, and a communication interface 370.
    The bus 310 includes a component that allows communication between the components of the device 300. The processor 320 is implemented in hardware, in business hardware, or in a combination of hardware and software. Processor 320 includes a processor (e.g., a central processing unit (CPU), a graphics processor (GPU), and / or an accelerated processing unit (APU)), a microprocessor, a microcontroller, and / or any component processing (for example, a user programmable pre-broadcast network (FPGA) and / or a specific application integrated circuit (ASIC)) which interprets and / or executes instructions. In some implementations, processor 320 includes one or more processors that can be programmed to perform a function. The memory 330 includes a random access memory (RAM), a read only memory (ROM), and / or another type of the dynamic or static storage device (for example, a flash memory, a magnetic memory, and / or an optical memory) which stores information and / or instructions for use by processor 320.
    The storage component 340 stores information and / or software relating to the operation and use of the device 300. For example, the storage component 340 may include a hard disk (e.g., a magnetic disk, an optical disk, a magneto-optical disc, and / or an SSD disc), a compact disc (CD), a versatile digital disc (DVD), a floppy disk, a cartridge, a magnetic tape, and / or any other type of non-transient computer readable medium , jointly associated with a corresponding reader.
    The input component 350 includes a component that allows the device 300 to receive information, such as via user input (for example, a touch screen display, a keyboard, a mouse, a button, a switch, and / or a microphone). Additionally, or alternatively, the input component 350 may include a sensor for detecting information (for example, a global positioning system (GPS) component, an accelerometer, a gyroscope, and / or an actuator). The output component 360 includes a component that provides output information from the device 300 (for example, a display, a speaker, and / or one or more light emitting diodes (LEDs)).
    The communication interface 370 includes a component of the transceiver type (for example, a transceiver and / or a separate receiver and transmitter) which allows the device 300 to communicate with other devices, such as via a wired connection , a wireless connection, or a combination of wired and wireless connections. The communication interface 370 can allow the device 300 to receive information from another device and / or provide information to another device. For example, the communication interface 370 can include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wifi interface, a cellular network interface, or the like.
    The device 300 can carry out one or more of the processes described here. The device 300 can carry out these processes in response to the processor 320 executing the software instructions stored by a non-transient computer readable medium, such as the memory 330 and / or the storage component 340. A computer readable medium is defined here as a memory device. non-transient memory. A memory device includes memory space in a single physical storage device or a memory space distributed among multiple physical storage devices.
    Software instructions can be read from memory 330 and / or storage component 340 from another computer-readable medium or from another device via the communication interface 370. When executed, the software instructions stored in the memory 330 and / or the storage component 340 can cause the processor 320 to carry out one or more processes described here. In addition, or alternatively, wired circuitry can be used in place of or in combination with software instructions to perform one or more of the processes described here. Thus, the implementations described here are not limited to any specific combination of hardware and software.
    The number and arrangement of the components shown in FIG. 3 are provided as an example. In practice, the device 300 may include additional components, fewer components, different components, or components arranged differently from those shown in FIG. 3. In addition, or as a variant, a series of components (for example, one or more components) of the device 300 can perform one or more functions described as being performed by another series of components of the device 300.
    Fig. 4 is a flow diagram of an example process 400 for generating a prognosis rule for predicting a future part failure associated with an aircraft. In some implementations, one or more process blocks of FIG. 4 can be carried out by the forecasting platform 225. In certain implementations, one or more process blocks of FIG. 4 can be implemented by another device or a group of devices separate from or including the prognosis platform 225, like another environment device 200.
    As shown in FIG. 4, the process 400 can include receiving operating information associated with the operation of an aircraft (block 410). For example, the prognostic platform 225 can receive operating information associated with the operation of aircraft 205. In some implementations, the prognostic platform 225 can receive operating information when another device provides the operating information. operation, as when the aircraft device 210 provides the operating information.
    Operational information may include information associated with the operation of aircraft 205 (for example, during flight, during landing, during takeoff, during ground maneuvers). For example, the operating information may include one or more types of data, associated with one or more parts and / or systems (here collectively designated by parts and individually by a part) of the aircraft 205, which are detected collected, measured, received, or otherwise determined during operation by, for example, one or more aircraft devices 210 of aircraft 205.
    As a particular example, the operating information may include quick access recorder (QAR) data collected by one or more aircraft devices 210 of aircraft 205. In some implementations, the QAR data may include raw data, corresponding to multiple (for example, hundreds, thousands) parameters associated with parts of aircraft 205, which are collected and / or received by one or more aircraft devices 210. As another example, operating information may include engine control unit (EMU) data collected by one or more aircraft devices 210 of aircraft 205. In some implementations, EMU data may include corresponding data parameters associated with an engine of the aircraft 205.
    In some implementations, the forecasting platform 225 can identify an anomaly based on the operating information. An anomaly can include an event, indicated by one or more pieces of information included in the operating information, which is atypical, abnormal, unexpected, significant, or others. For example, an anomaly may include an occurrence of a value of a parameter satisfying a threshold value (for example, being less than or equal to the threshold value, greater than or equal to the threshold value) during operation of the aircraft 205. As another example, an anomaly may include an occurrence of a value of a parameter changing by a threshold amount (for example, a sudden or gradual increase or decrease) during operation. As yet another example, an anomaly can include an occurrence of a difference between a value of a first parameter and a value of a second parameter satisfying a threshold value during the operation of aircraft 205. As also a another example, an anomaly may include an occurrence of a value of a parameter being in a range of values (for example, at a time, for a particular amount of time, during a particular time window) during operation of the aircraft 205. As yet another example, an anomaly may include an occurrence of a trend, pattern, or the like, associated with a parameter, detected by the prognostic platform 225 (for example, using an algorithm of trend detection, a pattern detection algorithm). In some implementations, the anomaly can be associated with one or more parameters. In certain implementations, the anomaly can be associated with a single operation of the aircraft 205. In addition, or as a variant, the anomaly can be associated with multiple operations of the aircraft 205.
    In addition, or alternatively, the forecasting platform 225 can associate time information with the anomaly. For example, the forecasting platform 225 can identify, as a function of the operating information, a moment (for example, a time of day, a date) at which the anomaly occurred, and can associate the temporal information with the 'anomaly. As another example, the prognosis platform 225 can identify moments associated with multiple pieces of operational information that contribute to the anomaly (for example, timestamps associated with pieces of operational information according to which the anomaly has been identified), and can associate the time information with the anomaly.
    In some implementations, the forecast platform 225 can identify the anomaly based on one or more pieces of operating information. For example, the forecasting platform 225 can determine information associated with the identification of one or more anomalies (i.e., a series of anomaly rules, a series of anomaly detection algorithms, which define a series of anomalies), and can identify one or more anomalies based on operating information and information associated with the identification of one or more anomalies.
    In certain implementations, the forecast platform 225 can generate an anomaly score corresponding to the anomaly. The anomaly score can identify the severity of the anomaly (for example, high, medium, low, a numeric value from zero to one). In certain implementations, the forecasting platform 225 can determine the severity of the anomaly based on operating information corresponding to the anomaly and information associated with the identification of the anomaly.
    In addition, or alternatively, the prognosis platform 225 may determine the abnormality score in another way, as according to a series of abnormality score rules associated with the generation of the score, an anomaly score algorithm.
    In addition, or alternatively, the operating information can include information associated with a message which is generated during the operation of aircraft 205 and relates to the operation of aircraft 205 (here referred to as message information). The message may include an alarm, notification, indication, or the like, generated during the operation of aircraft 205. For example, the message may be generated by a software module, associated with one or more parts of the aircraft 205, to cause a message to be provided during operation (for example, by turning on an alarm light, by displaying a message on a display screen). As a particular example, the message information may include post-flight report (PFR) data, collected by one or more aircraft devices 210 of aircraft 205, associated with messages generated during operation. In some implementations, the message information may correspond to one or more pieces of QAR data and / or EMU data. In addition, or alternatively, the message information may correspond to one or more other pieces of information (i.e., information which is not included in the QAR data or the EMU data).
    In addition, or alternatively, the operating information may include another type of information associated with the aircraft 205 and / or the operation of the aircraft 205, such as an aircraft identifier (for example, an aircraft number aircraft identification, a numeric suffix), a function identifier (for example, a flight identification number, a flight itinerary and / or flight route information), information that identifies an owner and / or a user of aircraft 205, or the like.
    In certain implementations, the forecasting platform 225 can receive the operating information from one or more aircraft devices 210 of the aircraft 205. For example, the forecasting platform 225 can receive (for example, automatically, based on user input) operating information from the one or more aircraft devices 210 when aircraft 205 lands at a destination associated with operation, such as when the one or more aircraft devices 210 connect to network 240 (for example, a Wi-Fi network) associated with the destination. In addition, or alternatively, the forecasting platform 225 can receive the operating information during operation (for example, in real time or in near real time) via a network 240 (for example, a network of satellites).
    In some implementations, the prognostic platform 225 can receive operating information associated with multiple aircraft 205 and / or multiple operations from multiple aircraft 205. This can allow the prognostic platform 225 to generate a better prognosis rule, associated with the prediction of a future failure of an aircraft part, than those which can be generated using operating information coming from a single aircraft. In certain implementations, the forecasting platform 225 can store information associated with the operation information, such as the operation identifier and / or the aircraft identifier corresponding to the operation of the aircraft 205 and to the aircraft 205, respectively.
    As further shown in FIG. 4, process 400 may include receiving maintenance information associated with the aircraft that identifies a part failure associated with the aircraft (block 420). For example, the forecasting platform 225 can receive maintenance information, associated with aircraft 205, which identifies a failure, defect, error, or the like, associated with a part and / or a system of the aircraft 205 (here referred to as a part failure). In some implementations, the forecasting platform 225 can receive maintenance information when another device provides maintenance information, such as when maintenance device 215 provides maintenance information.
    Maintenance information may include information associated with maintenance, repair, servicing, or the like, of aircraft 205. For example, maintenance information may include maintenance, repair, and overhaul data ( MRO) associated with aircraft 205 and / or one or more parts of aircraft 205. In some implementations, maintenance information may include information associated with part failure, such as information that identifies the part (for example, a part identification number, a part name, a serial number, a part manufacturer, a part brand), information that identifies the part failure (for example, a type of failure part failure identifier), a date associated with the part failure (for example, a date when the part failure was identified, a date it occurred repaired part failure), a way in which the part failure has been remedied (for example, repair, replacement, reconfiguration), or the like.
    In addition, or alternatively, the maintenance information may include other information associated with the maintenance and / or repair of the aircraft 205. For example, the maintenance information may include information associated with routine maintenance , preventive maintenance, and / or an inspection performed on aircraft 205.
    In addition, or alternatively, the maintenance information can include another type of information associated with the aircraft 205, such as the aircraft identifier, an operation identifier associated with the part failure, an associated operation identifier. maintenance or inspection of aircraft 205, or the like. In certain implementations, the forecasting platform 225 can receive the maintenance information from the maintenance device 215.
    In some implementations, the prognosis platform 225 may receive maintenance information associated with multiple aircraft 205. This may allow the prognosis platform 225 to generate a better prognosis rule, associated with the prediction of '' future failure of an aircraft part, than those that can be generated using maintenance information for a single aircraft. In some implementations, the forecasting platform 225 may store information associated with maintenance information, such as the aircraft identifier corresponding to aircraft 205 (for example, such that the forecasting platform 225 can determine maintenance information, associated with aircraft 205, later).
    As further shown in FIG. 4, process 400 may include receiving environmental information associated with the aircraft and / or the operation of the aircraft (block 430). For example, the forecasting platform 225 can receive information on the environment associated with the aircraft 205 and / or the operation of the aircraft 205. In certain implementations, the forecasting platform 225 can receive environmental information when another device provides environmental information, such as when the environmental device 220 provides environmental information.
    Environmental information may include information associated with an environment in which aircraft 205 flies, operates, is based, or the like. For example, environmental information may include weather data associated with the operation of aircraft 205 (for example, information that identifies one or more weather conditions associated with operation). As another example, the environmental information may include route data and / or flight route data associated with the operation. As yet another example, the environmental information may include information associated with a place of departure or arrival associated with the operation, such as information which identifies the place of departure or the place of arrival, the meteorological data of departure or arrival, departure or arrival climatic information (for example, the general climatic conditions of the place of departure or arrival, such as dusty, windy, hot, cold, icy, rainy), or others.
    In addition, or alternatively, the environmental information can include another type of information associated with the aircraft 205, such as the aircraft identifier corresponding to the environmental information, the operation identifier corresponding to the information on the environment, or others. In some implementations, the forecasting platform 225 can receive environmental information from the environmental device 220.
    In some implementations, the prognosis platform 225 can receive environmental information associated with multiple aircraft 205 and / or multiple operations of multiple aircraft 205. This can allow the prognosis platform 225 to generate a prognosis rule, associated with the prediction of a future failure of an aircraft part, than those which can be generated using environmental information associated with a single aircraft and / or a single operation.
    In certain implementations, the forecasting platform 225 can store information associated with information on the environment, such as the aircraft identifier corresponding to aircraft 205, the operation identifier corresponding to operation, or others (for example example, such that the forecast platform 225 can determine environmental information, associated with aircraft 205 and / or operation, later).
    As further shown in FIG. 4, process 400 may include generating a prognosis rule, associated with predicting a future part failure, based on operating information, maintenance information, and / or environmental information (block 440 ). For example, the prediction platform 225 can generate a prognosis rule, associated with the prediction of a future part failure, based on operating information, maintenance information, and environmental information (sometimes collectively designated as aircraft information). In some implementations, the prognostic platform 225 may generate (for example, automatically) the prognostic rule after the prognostic platform 225 has received operating information, maintenance information, and / or environmental information.
    The prognosis rule may include a rule associated with the prediction of a future part failure of an aircraft part 205. For example, the prognosis rule may include information that identifies any combination of one or more elements operating information, one or more elements of environmental information, one or more other elements of maintenance information, and / or one or more parts failures, the presence of which indicates that a part failure may occur.
    In certain implementations, the forecasting platform 225 can generate the forecasting rule as a function of the identification of an association between one or more elements of the operating information, one or more elements of the maintenance information, and / or one or more elements of the environmental information and a part failure identified in the maintenance information. In some implementations, the forecasting platform 225 can identify the association using an association detection algorithm which performs an association detection technique, such as a basket basket analysis technique (“ market basket ”), an association rules technique, a collaborative filtering technique, or others.
    For example, suppose that the forecasting platform 225 stores or has access to an association detection algorithm designed to implement a basket basket analysis technique associated with the operations of multiple aircraft 205, and that the prediction platform 225 receives operating information, maintenance information, and environmental information associated with multiple aircraft 205 and multiple operations of multiple aircraft 205, as described above. Here, the association detection algorithm can cause the forecasting platform 225 to create a “basket” (for example, an entry in a database), corresponding to an operation of a particular aircraft 205, by function of an operation identifier and / or an aircraft identifier associated with the operation and with the particular aircraft 205.
    Then, the forecasting platform 225 can add one or more elements of the operating information, associated with the operation, to the basket, such as information which identifies one or more anomalies identified as a function of the operating information collected during operation, information associated with one or more messages generated during operation, or others. In some implementations, the 225 prediction platform can add one or more elements of environmental information, associated with operation, to the basket. The prognostic platform 225 can repeat these steps for each operation of the particular aircraft 205 for which the prognostic platform 225 has received operating information and environmental information.
    Continuing with this example, the prognostic platform 225 can then identify a part failure associated with the particular aircraft 205. Here, depending on the information associated with the part failure, the forecasting platform 225 can add an indication of the part failure to one or more baskets corresponding to one or more operations of the particular aircraft 205. For example, the forecasting platform 225 can add an indication that the part failure has occurred in a next number of operations (for example, 100 flights) of the aircraft 205 specific to baskets corresponding to the number of operations preceding part failure (for example, 100 flights immediately preceding the identification and / or repair of the part failure). As another example, the forecasting platform 225 can add an indication that the part failure has occurred within the next number of hours of operation (for example, 500 hours) of the aircraft 205 specific to baskets corresponding to the number of hours of operation before the part failure (for example, baskets corresponding to operations that cover 500 hours of operation immediately preceding the identification and / or repair of the part failure).
    In addition, or alternatively, the forecasting platform 225 can add one or more other elements of the maintenance information, associated with the particular aircraft 205, to baskets associated with the particular aircraft 205, such as information associated with routine maintenance, preventive maintenance, inspections, damaged or degraded parts, information associated with another part failure, or others.
    In some implementations, the prognostic platform 225 may repeat these steps for multiple aircraft 205 for which the prognostic platform 225 has received operational information, environmental information, and maintenance information . In this way, the forecasting platform 225 can store or have access to multiple baskets corresponding to multiple operations of multiple aircraft 205, where each basket can include operational information, maintenance information, and / or information on the environment associated with an operation and a corresponding aircraft 205.
    Then, the prediction platform 225 can analyze the baskets in order and identify associations, patterns, trends, or others, associated with one or more coin failures.
    In some implementations, the prognosis platform 225 can generate the prognosis rule based on multiple elements of the operating information, environmental information, and / or maintenance information. In some implementations, the 225 forecast platform can generate multiple forecast rules based on basket analysis. In some implementations, the prediction platform 225 can determine a measure associated with the prognosis rule, such as a confidence measure, an increase measure, a support measure, or others.
    In some implementations, the prognosis platform 225 can filter one or more prognosis rules generated by the prognosis platform 225 by, for example, comparing one or more measures, associated with each prognosis rule, with a or several measurement thresholds. In this example, if the one or more measures do not meet the one or more measurement thresholds, then the forecasting platform 225 can filter the prognosis rule (for example, so that the prognosis rule may not be used to predict future part failure). Conversely, if the one or more measurements satisfy the one or more measurement thresholds, then the forecasting platform 225 may not filter the prognosis rule (for example, in such a way that the prognosis rule can be used to predict future part failure).
    As further shown in FIG. 4, process 400 may include storing information associated with the prognosis rule (block 450). For example, the prognosis platform 225 can store information associated with the prognosis rule. In some implementations, the prognostic platform 225 can store the information associated with the prognostic rule in such a way that the prognostic platform 225 can access the information associated with the prognostic rule later (for example, for use them for predicting future part failure).
    Although FIG. 4 shows an example of process blocks 400, in some implementations, process 400 may include additional blocks, fewer blocks, different blocks, or blocks arranged differently from those shown in FIG. 4. In addition, or as a variant, two or more of the process blocks 400 can be produced in parallel.
    Fig. 5 is a flow diagram of an example process 500 for generating a prediction for a future part failure, associated with an aircraft, according to a prognosis rule. In some implementations, one or more process blocks of FIG. 5 can be performed by the prognosis platform 225. In certain implementations, one or more process blocks of FIG. 5 can be produced by another device or a group of devices separate from or including the forecasting platform 225, like another device from the environment 200.
    As shown in FIG. 5, process 500 may include receiving operating information and / or environmental information associated with the operation of an aircraft, and / or maintenance information associated with the aircraft (block 510). For example, the forecasting platform 225 can receive operating information and / or environmental information associated with the operation of aircraft 205, and / or maintenance information associated with aircraft 205.
    In some implementations, the prognosis platform 225 can receive operating information, environmental information, and / or maintenance information as described above with reference to Fig. 4. In some implementations, operating information, environmental information, and maintenance information may include information similar to operating information, environmental information, and maintenance information described above in referring to FIG. 4.
    As further shown in FIG. 5, process 500 can include accessing information associated with a prognosis rule to predict a future part failure associated with the aircraft (block 520). For example, the prognosis platform 225 can access information associated with a prognosis rule to predict a future part failure associated with the aircraft 205.
    In certain implementations, the forecasting platform 225 can access the information associated with the prognostic rule as a function of the storage of the information associated with the prognostic rule, as described above with reference to FIG. 4. In some implementations, the prediction platform 225 can access information associated with multiple prognosis rules (for example, such that the prognosis platform 225 can make multiple predictions corresponding to multiple parts failures).
    As further shown in FIG. 5, process 500 may include generating a prediction, associated with a future part failure, based on the prognosis rule and operating information, environmental information, and / or maintenance information (block 530 ). For example, the forecast platform 225 can generate a prediction, associated with a future part failure of a part of the aircraft 205, as a function of the forecast rule and operating information, information on the environment, and / or maintenance information.
    In some implementations, the prediction platform 225 can generate the prediction based on the comparison of the operating information, environmental information, and / or maintenance information with the information associated with the forecast rule. For example, the information associated with the prognosis rule can identify one or more particular elements of the operating information, environmental information, and / or maintenance information which are associated with a particular part failure. Here, the prediction platform 225 can determine whether the operating information, the environmental information, and / or the maintenance information includes the one or more particular elements of the information. If the operating information, the environmental information, and / or the maintenance information includes the one or more particular elements of the information, then the forecasting platform 225 can generate a prediction that a future part failure, corresponding to the prognosis rule, will take place. Conversely, if the operating information, the environmental information, and / or the maintenance information does not include each of one or more particular elements, then the forecasting platform 225 can generate a prediction that a future part failure will not occur.
    As another example, the forecasting platform 225 can generate the prediction as a function of the proximity of the correspondence of the elements corresponding to operating information, maintenance information, and / or information on the environment with the elements identified by the prognosis rule as being associated with part failure. Here, the forecasting platform 225 can generate a prediction which indicates a probability that the part, associated with the forecasting rule, will have a failure, depending on the proximity of the operating information, maintenance information, and / or information on the environment with the elements identified by the prognosis rule. In some implementations, the 225 prediction platform can filter the prediction based on a threshold.
    In addition, or alternatively, the pieces of information identified by the prognosis rule may include a range of values and / or a threshold value. Here, the forecasting platform 225 can generate a prediction based on where the corresponding elements of operating information, maintenance information, and / or environmental information fall within the range of values, if the elements correspondents meet the threshold, or others. In such a case, information associated with each piece of information can be combined to form the prediction.
    In some implementations, the forecasting platform 225 can determine additional information associated with the prediction, such as a confidence measure associated with the prediction, a support measure associated with the prediction, an increase measure associated with the prediction. prediction, a window of time during which a future coin failure may occur (for example, in a case where the forecasting platform 225 predicts a future coin failure), or the like.
    In some implementations, the prognosis platform 225 can update the information associated with the prognosis rule based on operating information, environmental information, and / or maintenance information. For example, the forecasting platform 225 can update and / or create one or more baskets based on operating information, environmental information, and / or maintenance information. Here, the forecasting platform 225 can update information associated with one or more existing forecasting rules and / or create one or more new forecasting rules, depending on the baskets updated and / or created, the as described above with reference to FIG. 4.
    As further shown in FIG. 5, process 500 may include providing information associated with the prediction (block 540). For example, the prediction platform 225 can provide information associated with the prediction. In some implementations, the prediction platform 225 can provide the information associated with the prediction in order to inform an owner and / or a user of the aircraft 205 of a future predicted part failure (for example, in order allow a curative and / or preventive action to be carried out).
    In addition, or alternatively, the forecasting platform 225 can provide the information associated with the prediction in order to cause an action to be performed automatically, such as the creation and / or assignment of a work order, the scheduling an inspection and / or repair of the part, in order to cause aircraft 205 to be automatically put out of service, in order to automatically cause a software module, associated with the part, to be updated , in order to cause an order for a new part to be placed, or the like, thereby reducing a security risk and / or allowing a period during which the aircraft 205 is out of service to be reduced.
    As another example, the prediction platform 225 can provide the information associated with the prediction in order to automatically create a stopwatch to count down to the occurrence of predicted part failure and / or automatically send one or more reminders of the impending part failure. It can also decrease a safety risk by reducing the chance that aircraft 205 will operate with an impending part failure.
    As yet another example, the forecasting platform 225 can provide the information associated with the prediction so that an active step is automatically started on the aircraft 205 when the part failure is imminent (for example, maintenance personnel must push a button or enter a command to prevent the aircraft from stopping when, for example, maintenance personnel have inspected the part and certified aircraft 205 for flight). As another example, the prediction platform 225 can provide the information associated with the prediction in order to automatically schedule more frequent inspections when a predicted date of the part failure approaches. As yet another example, the prediction platform 225 can provide the information associated with the prediction in order to automatically trigger an inspection of another room.
    As yet another example, the prediction platform 225 can provide the information associated with prediction to a device associated with a designer and / or manufacturer of the part associated with the future part failure.
    Although FIG. 5 shows an example of process blocks 500, in some implementations, process 500 may include additional blocks, fewer blocks, different blocks, or blocks arranged differently from those shown in FIG. 5. In addition, or as a variant, two or more of the blocks of the process 500 can be produced in parallel.
    The implementations described here can provide a prognostic platform that can generate one or more prognosis rules and predict future part failure based on the one or more prognosis rules.
    The foregoing description provides illustration and description, but is not intended to be exhaustive or to limit the implementations to the precise form described. Modifications and variations are possible in light of the above description or can be acquired through the practice of implementations.
    As used herein, the term component is intended to be interpreted broadly as hardware, business hardware, and / or a combination of hardware and software.
    Some implementations are described here in conjunction with thresholds. As used here, satisfying a threshold can refer to a value being greater than the threshold, greater than the threshold, higher than the threshold, greater than or equal to the threshold, less than the threshold, less than the threshold, more lower than the threshold, less than or equal to the threshold, equal to the threshold, etc.
    It will be apparent that systems and / or methods, described herein, can be implemented in different forms of hardware, business hardware, or a combination of hardware and software. The specialized control equipment or actual software code used to implement these systems and / or processes does not limit these implementations. Thus, the operation and behavior of systems and / or processes have been described here without reference to a specific software code - it will be understood that software and hardware can be designed to implement systems and / or processes in function of this description.
    Even if particular combinations of features are listed in the claims and / or described in the description, these combinations are not intended to limit the description of the possible implementations. In fact, many of these features can be combined in ways not specifically listed in the claims and / or described in the description. Although each dependent claim listed below may depend directly on a single claim, the description of possible implementations includes each dependent claim in combination with any other claim in the set of claims.
    No element, act, or instruction used here may be interpreted as critical or essential unless it is explicitly described as such. Also, as used here, the item "one" is intended to include one or more elements, and may be used interchangeably with "one or more." Furthermore, as used here, the term “series” is intended to include one or more elements (for example, linked elements, unrelated elements, a combination of linked elements, and unrelated elements, etc.), and can be used interchangeably with “one or more.” When only one element is signified, the term “one” or similar language is used. Also, as used here, the terms "a", "have", "having" or the like are meant to be open terms. In addition, the phrase “on the basis of” is intended to mean “on the basis, at least in part, of” unless otherwise specified.
    权利要求:
    Claims (20)
    [1" id="c-fr-0001]
    1. Process, comprising:
    receiving, by one or more devices (225), first equipment information (205) associated with a first equipment (205), the first equipment information (205) including information associated with first anomalies identified as a function of first operating information collected during the operation of the first equipment (205), and the first equipment information including information associated with first messages, associated with the operation of the first equipment (205), which are generated during the operation of the first equipment (205 );
    receiving, by the one or more devices (225), first maintenance information, associated with the first equipment (205), which identifies one or more failures of parts associated with one or more pieces of equipment;
    identify, by the one or more devices (225), associations between the one or more parts failures and the first equipment information (205);
    receiving, by the one or more devices (225), second equipment information associated with the second equipment (205), the second equipment information (205) including information associated with second anomalies identified as a function of second operating information collected during operation of the second equipment (205), and second equipment information (205) including information associated with second messages, associated with operation of the second equipment (205), which is generated during operation of the second equipment (205 );
    generate, by the one or more devices and based on information from the second equipment (205) and associations, a prediction associated with a future failure of a part of the second equipment (205); and providing, by the one or more devices (225), information associated with the prediction.
    [2" id="c-fr-0002]
    2. Method according to claim 1, in which identifying the associations between the one or more parts failures and the first equipment information (205) comprises:
    analyze the first equipment information (205) and the first maintenance information using at least one of:
    a technique for analyzing the housewife's basket, a technique for association rules, or a technique for collaborative filtering; and to identify the associations based on an analysis result of the first equipment information and the first maintenance information.
    [3" id="c-fr-0003]
    3. Method according to claim 1 or 2, further comprising:
    obtaining the first operating information, collected during the operation of the first equipment (205), from a device on board the first equipment (205), the first operating information including data from a quick access recorder ( QAR) collected during the operation of the first equipment (205); and identify the first anomalies based on QAR data.
    [4" id="c-fr-0004]
    4. Method according to any one of the preceding claims, further comprising:
    obtaining the first operating information, collected during the operation of the first equipment (205), from a device on board the first equipment (205), the first operating information including motor control unit data (EMU) collected during the operation of the first equipment (205); and identify early anomalies based on EMU data.
    [5" id="c-fr-0005]
    5. Method according to any one of the preceding claims, in which receiving the first equipment information (205) comprises:
    obtain the information associated with the first messages, associated with the operation of the first equipment (205), from a device on board the first equipment (205), the first messages being included in post-flight report data (PFR) ) collected during the operation of the first equipment (205).
    [6" id="c-fr-0006]
    6. Method according to any one of the preceding claims, in which the first maintenance information is associated with maintenance, repair and overhaul data (MRO) collected during the maintenance or inspection of the first equipment (205). .
    [7" id="c-fr-0007]
    7. Method according to any one of the preceding claims, further comprising:
    to receive information on the environment associated with the first equipment (205) or with an operation of the first equipment (205); and wherein identifying the associations between the one or more part failures and the first equipment information (205) includes:
    to identify the associations still based on environmental information associated with the first equipment (205) or with the operation of the first equipment (205).
    [8" id="c-fr-0008]
    8. Device, comprising:
    one or more processors (320) for:
    receiving first equipment information (205) associated with one or more first pieces of equipment, the first equipment information (205) including information associated with anomalies identified based on operating information collected during the operation of the one or more first pieces of equipment, and first piece of equipment information (205) including information associated with messages, associated with the operation of the one or more first pieces of equipment, which are generated during the operation of the one or more first pieces of equipment equipment ;
    receive maintenance information, associated with one or more first pieces of equipment, which identifies one or more failures of parts of one or more pieces of equipment of the one or more first pieces of equipment;
    identifying associations between the one or more part failures and the first equipment information (205); and storing information, regarding associations between the one or more part failures and the first equipment information (205), to enable a prediction to be made regarding a future failure of a piece of equipment from a second piece of equipment.
    [9" id="c-fr-0009]
    9. Device according to claim 8, in which the one or more processors (320), when identifying the associations between the one or more parts failures and the first equipment information (205), are intended for:
    identify associations based on an association detection algorithm that performs at least one of a household basket analysis technique, an association rule technique, or a collaborative filtering technique.
    [10" id="c-fr-0010]
    10. Device according to claim 8 or 9, in which the one or more processors (320) are further intended for:
    obtain the operating information, collected during the operation of the one or more first pieces of equipment, from one or more devices on board the one or more first pieces of equipment, the operating information including data from the recorder quick access (QAR) data collected during the operation of one or more first pieces of equipment, or operating information including engine control unit (EMU) data collected during the operation of one or more first pieces of equipment equipment ; and identify anomalies based on QAR data or EMU data.
    [11" id="c-fr-0011]
    11. Device according to any one of claims 8 to 10, in which the one or more processors (320), when receiving the information of the first equipment (205), are intended for:
    obtain the information associated with the messages, associated with the operation of the one or more first pieces of equipment, from one or more devices on board the one or more first pieces of equipment, the messages being included in post-flight report data ( PFR) collected during the operation of one or more first pieces of equipment.
    [12" id="c-fr-0012]
    12. Device according to any one of claims 8 to
    11, wherein the maintenance information is associated with maintenance, repair, and overhaul (MRO) data collected during the maintenance or inspection of one or more first pieces of equipment.
    [13" id="c-fr-0013]
    13. Device according to any one of claims 8 to
    12, in which the one or more processors (320) are further intended for:
    receive environmental information associated with one or more first pieces of equipment or with the operation of one or more first pieces of equipment; and in which the one or more processors (320), when identifying the associations between the one or more parts failures and the first equipment information (205), are intended for:
    identify associations in addition based on environmental information associated with one or more first pieces of equipment or with the operation of one or more first pieces of equipment.
    [14" id="c-fr-0014]
    14. Device according to any one of claims 8 to
    13, in which the maintenance information, associated with one or more first pieces of equipment, further includes information associated with preventive maintenance, routine maintenance, or an inspection of the one or more first pieces of equipment, and in which the one or more processors, when identifying associations between the one or more parts failures and the first equipment information (205), are intended to:
    identify associations based on information associated with preventive maintenance, routine maintenance, or inspection of one or more first pieces of equipment.
    [15" id="c-fr-0015]
    15. Non-transient computer readable medium storing instructions, the instructions comprising:
    one or more instructions which, when executed by one or more processors, cause the one or more processors (320):
    receive first equipment information (205) associated with the first equipment (205), the first equipment information (205) including information associated with first anomalies identified based on first operating information collected during operation of the first equipment (205 ), and the first equipment information (205) including information associated with first messages, associated with the operation of the first equipment (205), which is generated during the operation of the first equipment (205);
    access associations identified based on information associated with one or more equipment part failures and second equipment information (205), the one or more equipment part failures being associated with the second equipment (205) and being identified as a function of the maintenance information associated with the second equipment (205), the second equipment information (205) including information associated with second anomalies identified as a function of second operating information collected during the operation of the second equipment (205), and the second equipment information (205) including information associated with second messages, associated with the operation of the second equipment (205), which is generated during the operation of the second equipment (205);
    generate, based on first equipment information (205) and associations, a prediction associated with a future failure of a piece of equipment of the first equipment (205); and provide information associated with the prediction.
    [16" id="c-fr-0016]
    16. computer-readable non-transient medium according to claim 15, in which the one or more instructions, when they are executed by the one or more processors (320), furthermore make the one or more processors (320):
    obtain the first operating information, collected during the operation of the first equipment (205), from a device on board the first equipment (205), the first operating information including data from fast access recorder (QAR) collected during the operation of the first equipment (205); and determine the information associated with the first anomalies based on the QAR data.
    [17" id="c-fr-0017]
    17. A computer-readable non-transitory medium according to claims 15 or 16, in which the one or more instructions, when they are executed by the one or more processors (320), also make the one or more processors (320):
    obtain the first operating information, collected during the operation of the first equipment (205), from a device on board the first equipment (205), the first operating information including engine control unit (EMU) data ) collected during the operation of the first equipment (205); and determine the information associated with the first anomalies based on EMU data.
    [18" id="c-fr-0018]
    18. non-transient computer readable medium according to any one of claims 15 to 17, in which the one or more instructions, which cause the one or more processors (320) to receive the information from the first equipment (205), make the one or more processors (320):
    obtain the information associated with the first messages, associated with the operation of the first equipment (205), from a device on board the first equipment (205), the first messages being included in collected post-flight report (PFR) data during the operation of the first equipment (205).
    [19" id="c-fr-0019]
    19. computer-readable non-transient medium according to any one of claims 15 to 18, in which the first equipment information (205) further includes first maintenance information associated with the first equipment (205), the first maintenance information, associated with the first equipment (205), being associated with maintenance, repair, and overhaul (MRO) data collected during the maintenance or inspection of the first equipment (205).
    [20" id="c-fr-0020]
    20. Non-transient computer readable medium according to
    5 of any of claims 15 to 19, wherein the first equipment information (205) further includes environmental information associated with the first equipment (205) or with an operation of the first equipment (205), the information on the environment including data
    10 meteorological, climatic data, or route data associated with the first equipment (205) or with the operation of the first equipment (205).
    1/6
    类似技术:
    公开号 | 公开日 | 专利标题
    FR3053813A1|2018-01-12|PROGNOSTIC RULES FOR PREDICTING A PIECE FAILURE
    AU2016213726B2|2017-08-03|Core network analytics system
    EP3388986A1|2018-10-17|End-to-end project management platform with artificial intelligence integration
    US9710322B2|2017-07-18|Component dependency mapping service
    CA2722687C|2015-11-24|Method and apparatus for obtaining vehicle data
    US20160039291A1|2016-02-11|Vehicle Battery Data Analysis Service
    EP3425512B1|2020-02-12|Software analytics platform
    US10372843B2|2019-08-06|Virtual aircraft network
    US10693740B2|2020-06-23|Data transformation of performance statistics and ticket information for network devices for use in machine learning models
    US20200117494A1|2020-04-16|Minimizing impact of migrating virtual services
    US20190156680A1|2019-05-23|Stop purpose classification for vehicle fleets
    WO2019209618A1|2019-10-31|Computer system and method for creating a supervised failure model
    US10346585B2|2019-07-09|Method of predicting heat exchanger blockage via ram air fan surge margin
    US10810069B2|2020-10-20|Data processing for component failure determination
    US10642713B1|2020-05-05|Object-based monitoring and remediation system
    US10762725B2|2020-09-01|Automatic classification of inactive vehicle tracking unit
    US10053228B2|2018-08-21|Aircraft status report matching
    CA3080707A1|2019-05-09|Computer system and method for performing a virtual load test
    US11049114B2|2021-06-29|Device, medium, and method for tailored interface generation based on internet of things data, vendor data, and/or user preferences data
    US20190354914A1|2019-11-21|Coordinating Execution of Predictive Models between Multiple Data Analytics Platforms to Predict Problems at an Asset
    FR3047822A1|2017-08-18|REAL-TIME REAL-TIME DIAGNOSTICS OF FAILURE IN AN AIRCRAFT
    US20200043250A1|2020-02-06|Configuring telematics devices
    US11204861B2|2021-12-21|Systems and methods for fault injection and ensuring failsafe FMS SaaS platforms
    US10552246B1|2020-02-04|Computer system and method for handling non-communicative assets
    JP2019532868A|2019-11-14|Method and system for monitoring helicopter health
    同族专利:
    公开号 | 公开日
    GB2552302B|2020-06-24|
    GB201611992D0|2016-08-24|
    US20180011481A1|2018-01-11|
    GB2552302A|2018-01-24|
    US10452062B2|2019-10-22|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    US20090228409A1|2008-03-10|2009-09-10|Eklund Neil H|Method, Apparatus And Computer Program Product For Predicting A Fault Utilizing Multi-Resolution Classifier Fusion|
    US20100049379A1|2008-08-20|2010-02-25|Airbus Operations|Method and device for assisting in the diagnostic and in the dispatch decision of an aircraft|
    EP2266880A1|2009-06-09|2010-12-29|Honeywell International Inc.|Method of automated fault analysis and diagnostic testing of an aircraft|
    US20080040152A1|2006-08-10|2008-02-14|The Boeing Company|Systems and Methods for Health Management of Single or Multi-Platform Systems|
    FR3009396B1|2013-07-31|2017-03-17|Airbus Operations Sas|METHOD AND COMPUTER PROGRAM FOR AIDING THE MAINTENANCE OF AIRCRAFT EQUIPMENT|
    FR3011105B1|2013-09-20|2017-01-27|Airbus Operations Sas|METHOD FOR IDENTIFYING FAILURE EQUIPMENT IN AN AIRCRAFT|
    US9881428B2|2014-07-30|2018-01-30|Verizon Patent And Licensing Inc.|Analysis of vehicle data to predict component failure|
    US9550583B2|2015-03-03|2017-01-24|Honeywell International Inc.|Aircraft LRU data collection and reliability prediction|US20180211336A1|2017-01-23|2018-07-26|United Technologies Corporation|Classification of Gas Turbine Engine Components and Decision for Use|
    US10643187B2|2017-06-09|2020-05-05|Kidde Technologies, Inc.|Reporting and prioritizing faults for aircraft downtime reduction|
    US20190057560A1|2017-08-16|2019-02-21|The Boeing Company|Method and system for predicting wing anti-ice failure|
    CN108845080B|2018-06-15|2021-04-09|幻飞智控科技（上海）有限公司|Unmanned aerial vehicle for environment monitoring and monitoring method thereof|
    CN109376872A|2018-09-07|2019-02-22|上海电力学院|A kind of offshore wind farm unit maintenance system|
    CN109460831A|2018-09-18|2019-03-12|中国铁道科学研究院集团有限公司电子计算技术研究所|A kind of overhaul of the equipments operational method, device and system|
    US10977877B2|2019-04-17|2021-04-13|Raytheon Technologies Corporation|Engine gateway with engine data storage|
    EP3726325A1|2019-04-17|2020-10-21|United Technologies Corporation|Gas turbine engine with dynamic data recording|
    US11208916B2|2019-04-17|2021-12-28|Raytheon Technologies Corporation|Self-healing remote dynamic data recording|
    CN111210668B|2019-12-30|2022-02-15|四川函钛科技有限公司|Landing stage flight trajectory offset correction method based on time sequence QAR parameter|
    CN111709537A|2020-05-22|2020-09-25|北京市地铁运营有限公司运营二分公司|Terminal, platform and system for reporting and repairing train fault|
    CN112298602A|2020-10-28|2021-02-02|广州极飞科技有限公司|Unmanned aerial vehicle fault detection method, device, equipment and storage medium|
    法律状态:
    2018-06-20| PLFP| Fee payment|Year of fee payment: 2 |
    2019-06-21| PLFP| Fee payment|Year of fee payment: 3 |
    2020-02-28| PLSC| Search report ready|Effective date: 20200228 |
    2020-06-23| PLFP| Fee payment|Year of fee payment: 4 |
    2021-06-23| PLFP| Fee payment|Year of fee payment: 5 |
    优先权:
    申请号 | 申请日 | 专利标题
    GB1611992.7A|GB2552302B|2016-07-11|2016-07-11|Prognostic rules for predicting a part failure|
    GB1611992.7|2016-07-11|
    [返回顶部]