• 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:
    The invention relates to a method (100; 200) for detecting defect (s) of a pantograph of a railway vehicle, said method (100) comprising the following steps: capturing (104) at least one image of said pantograph; - Analysis (106) of said image by a previously trained neural network for the detection of defect (s) of pantographs from defect images (s) previously captured. It also relates to a detection device implementing such a method, and a system and a railway equipped with such a detection device.
    公开号:FR3047451A1
    申请号:FR1651029
    申请日:2016-02-09
    公开日:2017-08-11
    发明作者:Alain Riveiro；Michel Paindavoine；Xavier Bruneau
    申请人:Globalsensing Tech；SNCF Reseau；
    IPC主号:
    专利说明:

    "Method, device and system for detecting defect (s) of a pantograph of a vehicle moving on a railway line"
    The present invention relates to a method for detecting defect (s) of a pantograph of a railway vehicle moving on a railway track. It also relates to a device and a system implementing such a method, and a railway equipped with such a device or such a system.
    The field of the invention is the field of devices for monitoring the state of deterioration of a pantograph.
    State of the art
    Currently, the detection of defects of a pantograph of a rail vehicle can be done by visual inspection, which is long, poor ergonomics and inefficient. In addition, such an inspection is only possible when the vehicle is stationary.
    There are also detection systems using cameras arranged to capture images of the pantograph. These sensors are in permanent communication with a remote central server and transmit the captured images to this server. This central server executes software that analyzes the received images from data describing the pantograph and stored in a database. An operator, specifically trained, then checks the results provided by the server and assesses the presence or absence of a fault.
    However, these detection systems are not reactive. With these systems, the detection time of a defect of the pantograph can take one, or even more, minute (s). However, a train traveling at 230 km / h travels about 4km per minute. Therefore, a defect in the pantograph can cause the destruction of 4km catenary, only during the detection time of the fault!
    In addition, the current detection systems do not work when the communication between the camera and the remote server is cut off.
    Finally, the current detection systems are dependent on the appreciation of a dedicated operator specifically trained for this task. This further decreases the reaction time and is costly in terms of training and personnel.
    An object of the present invention is to overcome these disadvantages.
    Another object of the invention is to provide a method, device and system for detecting defect (s) of a more reactive pantograph.
    It is also another object of the invention to provide a method, device and system for detecting defect (s) of a pantograph less expensive in terms of training and manpower.
    Yet another object of the invention is to provide a method, device and system for detecting defect (s) of a more efficient pantograph.
    DISCLOSURE OF THE INVENTION The invention makes it possible to achieve at least one of these objects by a defect detection method (s) of a pantograph of a railway vehicle moving on a railway track, said method comprising at least one of at least one iteration of a detection phase comprising the following steps: - capture of at least one image of said pantograph at at least one site, said capture, lying along said railway, during the passage of said vehicle; - Providing at least one captured image to a previously trained neural network for detecting defect (s) of pantographs from defect images (s) previously captured; and - analysis of said image by said neural network, said analysis providing data, called defect, relating to the presence or absence of a defect in said pantograph.
    Thus, the method according to the invention proposes to perform a detection of a defect of the pantograph with a neuron network previously and specifically trained. Consequently, the method according to the invention does not require the intervention of a specially trained operator for this task, or even no intervention on the part of any operator, when detecting a defect of a pantograph. Therefore, the detection of a defect can be performed faster and more reactively.
    In addition, the method of the invention does not require training of an operator, it is less expensive in terms of training and manpower.
    In addition, the neural network used, being previously trained, allows a more effective detection of defects of a pantograph.
    The method according to the invention may further comprise a step of detecting the presence of a railway vehicle during the passage of a rail vehicle at the capture site, the detection phase of a fault being triggered following said step presence detection.
    Such a presence detection step can be carried out by a railway vehicle detection means, such as one or more accelerometers arranged at the level of the railway for example.
    Alternatively, such detection can be performed by a trained neural network to recognize a railway vehicle from images provided by a camera for example.
    In a particularly preferred version of the method according to the invention, the neural network can be stored in situ at the capture site. In this case, the analysis step may advantageously be performed in situ on said capture site.
    In this version, the detection of a defect of a pantograph is performed directly at the capture site. Thus, the method according to the invention does not require communication with a central site to detect a fault, unlike systems of the state of the art. In other words, the detection of a defect of a pantograph can be performed at any time, even when there is no connection with a central site.
    Advantageously, the detection phase may comprise a transmission of the image of the pantograph, picked up by a first capture site, at a second capture site. The second capture site can then perform an analysis step to verify the result of the analysis step performed on said first capture site.
    Such a version makes it possible to improve the results of detection of a defect of a pantograph since the second capture site verifies the result of the analysis step performed on the first capture site.
    According to another non-limiting version, the detection phase may comprise a transmission of the image of the pantograph, picked up at a first capture site, at a second capture site, the analysis step being performed on said second capture site.
    Such a version makes it possible to reduce the cost of implementing the method according to the invention since, in this version, it is not necessary to equip each detection site with computing means executing the neural network.
    At least two capture sites can be connected through a wireless communication network, such as the cellular network, or through a dedicated wireless connection.
    Alternatively, at least two capture sites can be connected through a wired connection.
    Advantageously, the method according to the invention can be implemented on several capture sites, distributed along the railway, the neural network used being common to at least two, in particular all, of said capture sites.
    Thus, the method according to the invention makes it possible to obtain repetitive results that do not depend on the capture site, the detection level of each capture site being substantially identical.
    According to an advantageous characteristic, when the neural network signals the presence of a defect, the method according to the invention may comprise a step of classifying said defect in one of several predetermined classes.
    Indeed, each fault data, provided by the neural network which signals the presence of a defect, can be previously assigned to a class according to the level of severity of the defect. Thus, when the neural network provides a data signaling a fault, the detected fault can be classified according to the fault data that represents it.
    The method according to the invention may further comprise a learning phase, carrying out a training of the neural network from previously collected pantograph defect images, said learning phase being performed prior to the first iteration of the phase of training. detection.
    Advantageously, the learning phase can be performed at a central site. The neural network can then be loaded into a computer or a processor fitted to each capture site, before or after installation on the capture site.
    In a particularly advantageous version, the method according to the invention may comprise at least one iteration of an update phase of the neural network, performing an update of the neural network from new defects detected.
    Thus, the neural network is constantly learning, and is completed as and when over time. Thus, it allows for a more effective, more accurate and more complete detection of defects of a pantograph.
    To do this, new known defect images, or images of new detected defects can be used to make such an update.
    The images used to carry out the update may comprise images captured at at least one capture site, or images acquired by an operator, for example during laboratory tests.
    The updating phase can be performed at each fault detection or at a predetermined frequency.
    Thus, the neural network is strengthened, adapts and improves at a predetermined frequency, or whenever a fault is detected.
    Preferably, the update phase can be performed on a central site remote from each capture site, the updated neural network being transmitted to each capture site after updating.
    Thus, the detection of a fault on a first capture site causes an update of the neural network so that a second capture site, located hundreds of kilometers from the first capture site and using the same neural network , can benefit even if said defect has not been found / detected at said second capture site. This feature allows all capture sites to benefit from the individual "experience" of each capture site.
    In this case, each capture site is in communication with the central site, preferably through a wireless communication network such as the cellular network.
    The detection phase may further comprise a step of analyzing at least one parameter relating to said vehicle, from at least one image of said vehicle, selected from the following: a number of said vehicle, a composition of said vehicle , or - a condition of the said vehicle or a car of the said vehicle.
    The method according to the invention may comprise a signaling, in particular automated signaling, of a defect found: - to the driver of the vehicle, - to a beacon found in said vehicle, - to an operator, etc.
    The fault signaling is advantageously performed through a wireless communication network or through a wireless connection. The signaling step may comprise a transmission of a data item informing the detected fault.
    Alternatively, or in addition, the signaling step may comprise a transmission of a control data to the vehicle, modifying the operation of the vehicle, such as for example: a slowing control data, in particular braking, of the vehicle, - a data of lowering of the pantograph so that it is no longer in contact with the catenary, - etc.
    The order data can be executed automatically in the vehicle, or after validation of a driver of the vehicle.
    According to another aspect of the invention, there is provided a defect detection device (s) of a pantograph of a railway vehicle moving on a railway track, intended to be arranged on a capture site located at said railway, said device comprising: - a camera for capturing at least one image of said pantograph during the passage of said vehicle by said capturing site; at least one processor executing a previously trained neural network for the detection of defect (s) of pantographs from previously captured defect images, to analyze at least one captured image and to provide a datum, called a defect datum, relating to the presence or absence of a defect in said pantograph.
    More generally, the device according to the invention is equipped with means for implementing any combination of the functions / steps implemented at the capture site, and described above.
    In particular, the device according to the invention may comprise a wireless communication means with a central site, respectively with another capture site and / or with the railway vehicle, for transmitting and / or receiving data to / from said site central, respectively said capture site and / or said railway vehicle.
    The system according to the invention may comprise at least one means of autonomous energy production, of the solar or wind type for supplying said system.
    The system may further include a battery powered by the power generating means.
    In addition, the system according to the invention can be arranged to be powered by a low voltage signal, for example 24V, or by a high voltage signal, for example 220V. To do this, the system according to the invention may comprise a voltage converter for converting the high voltage signal into a low voltage signal.
    Preferably, the camera may be an infrared camera. The camera can alternatively be a CCD or CMOS camera.
    The camera can be equipped with lighting. In particular the camera can be provided with an infrared flash.
    The system according to the invention may further comprise, for at least one capture site, at least one means for detecting the presence of a railway vehicle during the passage of a railway vehicle at the capture site. In this case, the camera can be triggered / activated when the presence detection means signals the presence of a railway vehicle.
    Such a presence detection means may for example comprise one or more accelerometers, in particular arranged at the level of the railway.
    Alternatively, the presence detection means may comprise a trained neural network for recognizing a railway vehicle from signals measured at the capture site, for example acceleration signals measured by one or more accelerometers, or captured images. by a dedicated camera or by the camera used to capture images of the pantograph.
    According to yet another aspect of the invention, there is provided a defect detection system (s) of a pantograph of a railway vehicle moving on a railway track, comprising at least two devices according to the invention, arranged on as many capture sites distributed along a railway line.
    The capturing devices can be arranged on poles already present along the railway.
    At least two detection devices can communicate with each other wirelessly.
    At least one, in particular each, detection device can communicate, wirelessly, with a central site.
    According to yet another aspect of the invention, there is provided a railway track equipped with: at least one device according to the invention; or - a system according to the invention.
    The wireless communication network used between the detection devices, and / or between the central site and at least one detection device may be the GPRS network, 3G, 4G, 5G, etc. More generally, the wireless communication network may be the cellular network.
    DESCRIPTION OF THE FIGURES AND EMBODIMENTS Other advantages and characteristics will appear on examining the detailed description of nonlimiting exemplary embodiments, and the appended drawings in which: FIG. 1 is a schematic representation of a first example non-limiting embodiment of a method according to the invention; FIG. 2 is a schematic representation of a second nonlimiting exemplary embodiment of a method according to the invention; FIG. 3 is a schematic representation of an exemplary embodiment of a detection device according to the invention; FIGURE 4 is a schematic representation of the device of FIGURE 3 on a capture site; and FIG. 5 is a schematic representation of an exemplary embodiment of a detection system according to the invention.
    It is understood that the embodiments which will be described later are in no way limiting. In particular, it will be possible to imagine variants of the invention comprising only a selection of characteristics described, subsequently isolated from the other characteristics described, if this selection of characteristics is sufficient to confer a technical advantage or to differentiate the invention with respect to of the prior art. This selection comprises at least one feature preferably functional without structural details, or with only a part of the structural details, if this part is only sufficient to confer a technical advantage or to differentiate the invention from the state of the prior art .
    In the figures, the elements common to several figures retain the same reference.
    FIGURE 1 is a schematic representation of a first non-limiting exemplary embodiment of the method according to the invention.
    The method 100 of FIGURE 1 comprises a step 102 of detecting the passage of a railway vehicle, such as a train. Such detection can be performed by a standard presence detection means.
    During a step 104, one or more images of the pantograph of the train are captured (s), for example by a camera.
    In a step 106, the image (s) captured in step 104 is (are) provided to a processor executing a previously trained neural network with a multitude of pantograph defect images. The neural network analyzes the image (s) provided. The analysis determines a fault data signaling no fault, the process is stopped until a next iteration.
    During a step 108, the image (s) captured in step 104 is (are) stored in a database in association with the determined fault data for this (these) image (s). ) during step 106, in view, for example, of their subsequent use for an update of the neural network.
    When in step 106, the neural network provides fault data signaling a fault, then an optional step 110 performs a fault classification in a fault category. For example, the identified defect can be classified in the category: - "minor defect" signaling the detection of a non-critical defect requiring no intervention; - "major defect" signaling a major gravity defect requiring intervention when the train has completed its journey; or - "critical fault" signaling a critical fault requiring urgent intervention.
    When the fault detected is a minor fault, then no intervention is performed.
    When the detected fault is an average fault, then a step 112 signals the fault to a maintenance center or the train driver, or to a central site, so that the defect can be corrected at the end of the journey of the train.
    When the detected fault is a major fault, then a step 114 sends a control signal to the train, in order to modify the behavior of the train. A control signal can trigger: - a stop or a slowing down of the train, or - a lowering of the pantograph so that it is no longer in contact with the catenary.
    At the level of the train, the command can be triggered automatically, possibly after confirmation of the train driver, during a step 116.
    A new iteration of the method 100 can then be performed during another passage of a rail vehicle.
    FIG. 2 is a schematic representation of a second non-limiting exemplary embodiment of the method according to the invention.
    The method 200 of FIGURE 2 includes all the steps of the method 100 of FIGURE 1. Unlike the method 100 of FIGURE 1, in the method 200, the analyzing step 106 is performed at a site remote from the site capturing images.
    Thus, the method 200 comprises, after the step 104 of capturing the images, a step 202 of sending the captured images to the remote site. Steps 106 and 108 are performed at the remote site.
    When the analysis indicates a fault, the capture site receives the fault data in a step 204, performed after step 108. Then steps 110 to 116 are performed.
    The remote site performing the analysis step 106 in place of the capture site, can be a central site common to several capture sites, or another capture site, to which the capture site is connected by a wireless connection. .
    FIGURE 3 is a schematic representation of a non-limiting embodiment of a detection device according to the invention.
    The detection device 300, shown in FIG. 3, is intended to be positioned at a capture site located along a railway line. The device 300 may, for example, be arranged on a pole located at the periphery of the railway.
    The device 300 comprises a camera 302, intended to capture one or more images of a pantograph of a railway vehicle, such as a train, during the passage of the railway vehicle at the capture site. The camera 302 can be programmed to go into standby when no railway vehicle passes at the capture site.
    To detect the passage of a railway vehicle, the device 300 may comprise a presence detection means, such as a neuron system driven to detect the presence of a railway vehicle, or such as an accelerometer 304 detecting the vibrations caused by the passage of a railway vehicle. This presence detection means 304 may be used to activate the camera, which is in standby mode, just before the passage of a railway vehicle at the capture site.
    A processor 306 is arranged in the device 300 to execute a previously trained neural network 308 for the detection of pantograph defect (s). This processor 306 is programmed to receive the images picked up by the camera 302, and to supply them at the input of the neural network 308, so that the latter provides a fault data item, indicating the presence or absence of a pantograph defect of the railway vehicle. .
    The processor 306 is programmed to store the images captured by the camera 302, in a database 310, in association with the default data provided by the neural network 308 for these images.
    The device 300 further comprises a communication module 312, coupled with an antenna 314, for communicating wirelessly with: a central site for transmitting to said central site the images captured by the camera 302, and possibly the data of defect provided by the neural network 308 for said images, and / or receiving from said central site an updated neural network; and / or - another detection device arranged on another capture site for: transmitting to said other detection device the images captured by the camera 302, and receiving a fault data determined by said other detection device; - the railway vehicle to signal the presence of a fault and / or issue a control signal to change the operation of the vehicle and / or the pantograph position of said vehicle.
    FIGURE 4 is a schematic representation of the device 300 of FIGURE 3 at a capture site.
    The capture site 400 comprises a detection device, such as, for example, the detection device 300, positioned on a post 402 lying on the edge of a railway 404 to detect the defects of the pantographs 406 of a powered railway vehicle 408. by a catenary 410.
    FIGURE 5 is a schematic representation of an exemplary non-limiting embodiment of a system according to the invention.
    The system 500 comprises several capture sites 400i-400n, each equipped with at least one detection device, respectively 300i-300n. The 400i-400n capture sites are for example distributed along a railway network.
    The system 500 further comprises a central site 502, in wireless communication with each detection device 300i-300n through a wireless communication network 504, such as for example the cellular network.
    The central site 502 comprises a processor 504 and a database 506 storing a multitude of pantograph images in association with defect data (s) determined for these images. These images, as well as the associated defect data, can be obtained during preliminary observations of pantograph defects or in the laboratory.
    The processor 504 is programmed to drive a neural network, for example the neural network 308, from the images stored in the database 504 and the associated fault data (s). Such training is performed prior to the first use of the detection devices 300. The trained neural network 308 is then transmitted to each detection device 300 of each capture site 400, through the communication network 504. Each detection device 300 each capture site 400 therefore uses the same neural network 308.
    In addition, the central site 502 receives from each detection device 300 in use, pantograph images and the defect data associated with these images. These images and the associated defect data are stored in the database 506. At regular frequency, or at the request of an operator or of the detection devices 300, the processor 502 carries out a setting. updating the neural network 308 by a new training of said neural network 308 with the new received images and the new defect data (s) associated with them. After updating, the updated neural network 308 is retransmitted to each detection device 300 through the communication network 504.
    Thus, when a fault is detected on a first capture site, then, a second capture site, located hundreds of kilometers from said first capture site, benefits from learning based on said detection even though the defect in question has never been detected on said second capture site. Therefore, all 400 capture sites benefit from the "individual" experience of each capture site.
    Of course, the invention is not limited to the examples detailed above.
    权利要求:
    Claims (16)
    [1" id="c-fr-0001]
    A method (100; 200) for detecting defect (s) of a pantograph (406) of a railway vehicle (408) moving on a railway track (404), said method (100) comprising at least one iteration a detection phase comprising the following steps: - capture (104) of at least one image of said pantograph (406) at at least one site (400), said capture, located along said path rail (404), when passing said vehicle (408); analysis (106) of said image by a neuron network (308) previously trained for the detection of defect (s) of pantographs from defect images (s) previously captured, said analysis (106) providing data, said defect, relating to the presence or absence of a defect in said pantograph (406).
    [2" id="c-fr-0002]
    2. Method (100) according to the preceding claim, characterized in that the neural network (308) is stored in situ at the capture site (400), the step (106) of analysis being performed in situ on said capture site (400).
    [3" id="c-fr-0003]
    3. Method (200) according to the preceding claim, characterized in that the detection phase comprises a transmission (202) of the image of the pantograph (406), captured by a first capture site (400), at a second site capturing device (400), said second capture site (400) performing an analysis step for verifying the result of the analysis step (106) performed on said first capture site (400).
    [4" id="c-fr-0004]
    4. Method (200) according to claim 1, characterized in that the detection phase comprises a transmission (202) of the image of the pantograph (406), picked up by a first capture site (400), at a second site capture (400), the analysis step (106) being performed on said second capture site (400).
    [5" id="c-fr-0005]
    5. Method (100; 200) according to any one of the preceding claims, characterized in that it is implemented on several capture sites (400i-400n), distributed along the railway track (404), the neural network (308) used being common to at least two, in particular all, of said capture sites (400i-400n).
    [6" id="c-fr-0006]
    6. Method (100; 200) according to any one of the preceding claims, characterized in that, when the neural network signals the presence of a fault, said method (100; 200) further comprises a step (110) of classifying said defect in one of several predetermined classes.
    [7" id="c-fr-0007]
    7. Method (100; 200) according to any one of the preceding claims, characterized in that it comprises a learning phase, performing a training of the neural network from previously collected pantograph defect images, said phase of learning being performed prior to the first iteration of the detection phase.
    [8" id="c-fr-0008]
    8. Method (100; 200) according to any one of the preceding claims, characterized in that it comprises at least one iteration of an update phase of the neural network, performing an update of the neural network (308). ) from new defects detected.
    [9" id="c-fr-0009]
    9. Method (100; 200) according to the preceding claim, characterized in that the update phase is performed at each fault detection or at a predetermined frequency.
    [10" id="c-fr-0010]
    10. Method (100; 200) according to any one of claims 8 or 9, characterized in that the update phase is performed on a central site (502) remote from each capture site (400i-400n), the updated neural network being transmitted to each capture site (400i-400n) after updating.
    [11" id="c-fr-0011]
    11. Method according to any one of the preceding claims, characterized in that the detection phase further comprises a step of analyzing at least one parameter relating to said vehicle from at least one image of said vehicle, chosen from the following: a number of said vehicle, a composition of said vehicle, or a state of said vehicle or a car of said vehicle.
    [12" id="c-fr-0012]
    12. Device (300) for detecting defect (s) of a pantograph (406) of a railway vehicle (408) moving on a railway track (404), intended to be arranged on a capture site (400) located at said track (404), said device (300) comprising: - a camera (302) for capturing at least one image of said pantograph (406) when passing said vehicle (408) through said pick-up site ( 400); at least one processor (306) executing a previously trained neural network for the detection of defect (s) of pantographs from defect images (s) previously captured, for analyzing at least one captured image and providing a given data , called defect, relating to the presence or absence of a defect in said pantograph (406).
    [13" id="c-fr-0013]
    13. System (500) for detecting defect (s) of a pantograph (406) of a railway vehicle (408) moving on a railway track (404), comprising at least two detection devices (300i-300n) according to the preceding claim, arranged on as many capture sites (400i-400n) distributed along a railway track (404).
    [14" id="c-fr-0014]
    14. System (500) according to the preceding claim, characterized in that at least two detection devices (300i-300n) communicate with each other wirelessly.
    [15" id="c-fr-0015]
    15. System (500) according to any one of claims 13 or 14, characterized in that at least one detection device (300i-300n) communicates, wirelessly, with a central site (502).
    [16" id="c-fr-0016]
    16. Track (404) equipped with: - at least one device (300) according to claim 12; or - a system (500) according to any one of claims 13-15.
    类似技术:
    公开号 | 公开日 | 专利标题
    EP3205528A1|2017-08-16|Method, device and system for detecting fault| in a pantograph of a moving vehicle on a railway
    CN106652551B|2021-03-09|Parking space detection method and equipment
    US7536457B2|2009-05-19|System and method for wireless delivery of event data
    WO2014199040A1|2014-12-18|Method and system for identifying damage caused to a vehicle
    CN1292391C|2006-12-27|System for realizing full-range over speed monitoring of vehicles running on expressway and its operating method
    JP2010535658A5|2011-05-06|
    KR101691559B1|2016-12-30|Remote monitoring system and method for charging infrastructure of electrical vehicles
    KR102167291B1|2020-10-20|System and method for providing road status information
    CN109827613B|2020-08-28|System for detecting settlement and damage of well lid by utilizing sensing data generated by rolling of vehicle
    EP3531102A1|2019-08-28|Device for inspecting subframes of a railway vehicle and corresponding inspection method
    EP3213213A1|2017-09-06|Diagnostic aid method, device and system
    CN104773155A|2015-07-15|Initial failure diagnosis method for automobile braking system
    EP2238579B1|2019-06-19|Surveillance system comprising a large number of cameras
    CN107256618B|2020-04-07|Alarm system and method for monitoring plant inclination state
    WO2013045839A1|2013-04-04|Method and system for detecting incidents on a vehicle offered for hire, and automated hiring system implementing such a method and system
    FR2903519A1|2008-01-11|Motor vehicle classification system for tariffication and collection of toll fee, has video camera for discriminating vehicles from images captured upstream of passage channel and transmitting output data of vehicles to computer
    FR3057380B1|2019-07-26|METHOD AND SYSTEM FOR DETECTING REDUCED RAIL-WHEEL ADHERENCE, AND VEHICLE EQUIPPED WITH SUCH A SYSTEM
    FR3024116A1|2016-01-29|CABLE TRANSPORT EQUIPMENT
    FR2675610A1|1992-10-23|METHOD AND INSTALLATION FOR EVALUATING A TRAFFIC FLOW OF ROAD VEHICLES.
    FR3042766B1|2019-10-18|METHOD AND DEVICE FOR DETERMINING A SAFE ACTION TO REDUCE THE RISK OF COLLISION OF A VEHICLE WITH AN OBJECT
    FR2980617A1|2013-03-29|DEVICE AND METHOD FOR VERIFYING TRAFFIC DATA
    CN107492160A|2017-12-19|A kind of vehicle-mounted protective survey device
    KR100479905B1|2005-03-31|Car identification apparatus and car identification system using the same
    CN210442657U|2020-05-01|Intelligent transportation monitoring system for wind generating set and components
    FR3065526B1|2019-07-19|SYSTEM FOR DETECTING A STATE OR DYSFUNCTION BY VIBRATION ANALYSIS
    同族专利:
    公开号 | 公开日
    FR3047451B1|2019-03-22|
    EP3205528A1|2017-08-16|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    WO2001014928A2|1999-08-20|2001-03-01|Digital Now, Inc.|Print inspection system|
    WO2009018612A1|2007-08-06|2009-02-12|Qr Limited|Pantograph damage and wear monitoring system|
    WO2012038485A1|2010-09-22|2012-03-29|Henesis S.R.L.|Pantograph monitoring system and method|
    WO2012175773A1|2011-06-20|2012-12-27|Universidad De Vigo|System and method for measuring the thickness of collector shoes of a pantograph|CN109934172A|2019-03-14|2019-06-25|中南大学|High-speed train pantograph exempts from GPS line failure vision-based detection localization method for the national games|
    DE102018114005A1|2018-06-12|2019-12-12|Carl Zeiss Jena Gmbh|Material testing of optical specimens|
    CN109614873A|2018-11-15|2019-04-12|中兴飞流信息科技有限公司|Train safety sign detection method, server and storage medium neural network based|
    WO2021043388A1|2019-09-03|2021-03-11|Schweizerische Bundesbahnen Sbb|Device and method for detecting wear and/or damage on a pantograph|
    CN111238393A|2020-01-20|2020-06-05|成都铁安科技有限责任公司|Pantograph carbon slide plate detecting system and its control method|
    法律状态:
    2017-02-28| PLFP| Fee payment|Year of fee payment: 2 |
    2017-08-11| PLSC| Search report ready|Effective date: 20170811 |
    2018-02-26| PLFP| Fee payment|Year of fee payment: 3 |
    2020-02-28| PLFP| Fee payment|Year of fee payment: 5 |
    2021-02-26| PLFP| Fee payment|Year of fee payment: 6 |
    优先权:
    申请号 | 申请日 | 专利标题
    FR1651029A|FR3047451B1|2016-02-09|2016-02-09|METHOD, DEVICE AND SYSTEM FOR DETECTING THE DEFECTOF A PANTOGRAPH OF A VEHICLE MOVING ON A RAILWAY|
    FR1651029|2016-02-09|FR1651029A| FR3047451B1|2016-02-09|2016-02-09|METHOD, DEVICE AND SYSTEM FOR DETECTING THE DEFECTOF A PANTOGRAPH OF A VEHICLE MOVING ON A RAILWAY|
    EP17154816.7A| EP3205528A1|2016-02-09|2017-02-06|Method, device and system for detecting fault in a pantograph of a moving vehicle on a railway|
    [返回顶部]