CN112991318A - Motor train unit pantograph fault detection method and device and storage medium - Google Patents
Motor train unit pantograph fault detection method and device and storage medium Download PDFInfo
- Publication number
- CN112991318A CN112991318A CN202110348306.6A CN202110348306A CN112991318A CN 112991318 A CN112991318 A CN 112991318A CN 202110348306 A CN202110348306 A CN 202110348306A CN 112991318 A CN112991318 A CN 112991318A
- Authority
- CN
- China
- Prior art keywords
- pantograph
- detection result
- monitoring image
- fault
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 152
- 238000012544 monitoring process Methods 0.000 claims abstract description 171
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 46
- 230000009545 invasion Effects 0.000 claims abstract description 37
- 230000033001 locomotion Effects 0.000 claims abstract description 19
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 51
- 229910052799 carbon Inorganic materials 0.000 claims description 51
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 238000005299 abrasion Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010586 diagram Methods 0.000 claims description 10
- 230000004044 response Effects 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000000926 separation method Methods 0.000 claims description 4
- 241000271559 Dromaiidae Species 0.000 claims description 3
- 238000012549 training Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 8
- 230000005856 abnormality Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L5/00—Current collectors for power supply lines of electrically-propelled vehicles
- B60L5/18—Current collectors for power supply lines of electrically-propelled vehicles using bow-type collectors in contact with trolley wire
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L5/00—Current collectors for power supply lines of electrically-propelled vehicles
- B60L5/18—Current collectors for power supply lines of electrically-propelled vehicles using bow-type collectors in contact with trolley wire
- B60L5/20—Details of contact bow
- B60L5/205—Details of contact bow with carbon contact members
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Current-Collector Devices For Electrically Propelled Vehicles (AREA)
Abstract
The application discloses a method, a device and a storage medium for detecting faults of a pantograph of a motor train unit, wherein the method comprises the steps of firstly constructing a fault detection algorithm model through a historical monitoring image of the pantograph, and because the historical monitoring image comprises a monitoring image corresponding to the situation that the pantograph has foreign matters, when the monitoring image of the pantograph is obtained, the foreign matters can be detected from the monitoring image, a foreign matter intrusion detection result is obtained, then whether a target intrusion item takes the pantograph as a terminal point or not is judged according to a motion path of the target intrusion item in the foreign matter intrusion detection result, and if so, the target intrusion item is a real foreign matter intrusion item. By applying the technical scheme, the foreign matter invasion of the pantograph can be detected, the comprehensiveness of pantograph fault detection is ensured, and the driving safety is improved. In addition, the historical monitoring image adopted in the training of the fault detection algorithm model is a real image in actual monitoring, so that the accuracy of the pantograph fault detection result is ensured.
Description
Technical Field
The application relates to the technical field of video and image processing, in particular to a method and a device for detecting a pantograph fault of a motor train unit and a storage medium.
Background
The pantograph-catenary system is a key link in a high-voltage power supply system of rail transit, and in the running process of a train, a pantograph and a catenary form a vibration system which is mutually oscillated and coupled through contact points, so that contact wires and carbon sliding plates are easily abraded, and the service life of the pantograph-catenary is shortened. In addition, serious faults such as abnormal pantograph structure and the like can occur due to the influence of external force such as foreign object impact and the like in the running process of the pantograph, and the running safety of a train is directly influenced.
The conventional pantograph fault detection system of the motor train unit mainly collects images of a pantograph and analyzes the abnormal condition of the pantograph by processing the collected images or videos, but due to the limitation of an image processing algorithm, only the structural abnormality of the pantograph can be judged, and the conditions such as foreign matter invasion cannot be detected.
In view of the above prior art, the technical staff in the field needs to solve the problem of finding a method for detecting the pantograph fault of a motor train unit, which can solve the problem of incomplete fault detection.
Disclosure of Invention
The application aims to provide a motor train unit pantograph fault detection method, a motor train unit pantograph fault detection device and a storage medium, which can detect the abnormity of a pantograph from multiple aspects, ensure the comprehensiveness and accuracy of pantograph fault detection and improve the driving safety.
In order to solve the technical problem, the application provides a method for detecting a pantograph fault of a motor train unit, which comprises the following steps:
constructing a fault detection algorithm model through historical monitoring images of the pantograph, wherein the historical monitoring images comprise corresponding monitoring images when foreign matters exist in the pantograph;
acquiring a monitoring image of the pantograph;
inputting the monitoring image into the fault detection algorithm model to obtain a foreign matter intrusion detection result;
judging whether the movement path of the target intrusion item takes the pantograph as an end point or not according to the foreign object intrusion detection result;
and if so, judging that the target invasion item is a foreign matter invasion item.
Preferably, after the acquiring the monitoring image, the fault detection algorithm model further includes:
carrying out foreground separation on each monitoring image so as to lock the target invasion item;
and acquiring the motion path of the target intrusion item through a tracking algorithm.
Preferably, the historical monitoring image further includes a monitoring image corresponding to the wear time of the carbon sliding plate of the pantograph, and the fault detection algorithm model further includes, after acquiring the monitoring image:
obtaining pre-stored thickness calibration values of different positions of the carbon sliding plate;
extracting a side image of the carbon sliding plate from the monitoring image;
obtaining thickness measurement values of different positions of the carbon sliding plate in the side image;
and calculating abrasion distribution data of the carbon slide plate according to the thickness calibration value and the thickness measurement value and outputting an abrasion detection result of the carbon slide plate of the pantograph.
Preferably, the historical monitoring image further includes a monitoring image corresponding to the pantograph when the structure of the pantograph is abnormal, and the fault detection algorithm model further includes, after acquiring the monitoring image:
carrying out image enhancement processing on the monitoring image;
performing feature extraction on the monitoring image subjected to image enhancement processing to obtain a feature distribution response diagram of the pantograph;
performing invariance analysis on the characteristic distribution response diagram to obtain a geometric shape estimation of the pantograph;
obtaining the standard values of the form parameters of the carbon sliding plate, the bracket and the cleat of the pantograph;
and performing correlation comparison on the geometric parameters in the geometric form estimation and the form parameter standard values and outputting an abnormal detection result of the bow structure.
Preferably, the historical monitoring image further includes a monitoring image corresponding to the pantograph when the structure of the pantograph is abnormal, and the fault detection algorithm model further includes, after acquiring the monitoring image:
weighting and offset calibrating a plurality of monitoring images before the current monitoring image and a plurality of monitoring images after the current monitoring image to obtain a target monitoring image;
and carrying out similarity judgment on the current monitoring image and the target monitoring image and outputting an abnormal detection result of the bow structure.
Preferably, the historical monitoring image further includes a monitoring image corresponding to a case where an included angle between a carbon sliding plate of the pantograph and the calibration horizontal line is greater than a preset threshold, and the fault detection algorithm model further includes, after acquiring the monitoring image:
determining a pantograph region in the monitoring image through a positioning model;
extracting a pantograph angle region in the pantograph region through a pantograph angle sub-model;
determining a carbon slide plate area through the bow angle area;
acquiring form information of the carbon sliding plate through a straight line fitting algorithm to determine an included angle between the carbon sliding plate and a calibration horizontal line;
and outputting the detection result of the inclination angle of the pantograph.
Preferably, the method further comprises the following steps:
acquiring a pantograph carbon slide plate abrasion detection result, a pantograph structure abnormity detection result, a foreign matter invasion detection result and a pantograph inclination angle detection result;
and analyzing and early warning the pantograph carbon slide plate abrasion detection result, the pantograph structure abnormity detection result, the foreign matter invasion detection result and the pantograph inclination angle detection result.
In order to solve the technical problem, the application still provides a EMUs pantograph fault detection device, includes:
the device comprises a construction module, a fault detection algorithm module and a fault detection module, wherein the construction module is used for constructing a fault detection algorithm model through historical monitoring images of the pantograph, and the historical monitoring images comprise corresponding monitoring images when foreign matters exist in the pantograph;
the acquisition module is used for acquiring a monitoring image of the pantograph;
the input module is used for inputting the monitoring image into the fault detection algorithm model to obtain a foreign matter intrusion detection result;
the judging module is used for judging whether the motion path of the target intrusion item takes the pantograph as a terminal point according to the foreign object intrusion detection result; and if so, judging that the target invasion item is a foreign matter invasion item.
In order to solve the technical problem, the application further provides a motor train unit pantograph fault detection device, which comprises a memory, a control unit and a control unit, wherein the memory is used for storing a computer program;
and the processor is used for realizing the steps of the motor train unit pantograph fault detection method when executing the computer program.
In order to solve the technical problem, the present application further provides a computer readable storage medium, where a computer program is stored, and the computer program, when executed by a processor, implements the steps of the method for detecting a pantograph fault of a motor train unit.
According to the method for detecting the pantograph fault of the motor train unit, firstly, a fault detection algorithm model is established through a historical monitoring image of the pantograph, and the historical monitoring image comprises a monitoring image corresponding to the pantograph when the pantograph has foreign matters, so that the foreign matters can be detected from the monitoring image and a foreign matter intrusion detection result can be obtained when the monitoring image of the pantograph is obtained, then whether the target intrusion item takes the pantograph as a terminal point or not is judged according to a motion path of the target intrusion item in the foreign matter intrusion detection result, and if the target intrusion item is the real foreign matter intrusion item. By applying the technical scheme, the foreign matter invasion of the pantograph can be detected, the comprehensiveness of pantograph fault detection is ensured, and the driving safety is improved. In addition, the historical monitoring image adopted in the training of the fault detection algorithm model is a real image in actual monitoring, so that the accuracy of the pantograph fault detection result is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present application, the drawings needed for the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
Fig. 1 is a flowchart of a method for detecting a pantograph fault of a motor train unit according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a pantograph fault detection device of a motor train unit according to an embodiment of the present application;
fig. 3 is a structural diagram of a pantograph fault detection device of a motor train unit according to another embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without any creative effort belong to the protection scope of the present application.
The core of the application is to provide a motor train unit pantograph fault detection method, a motor train unit pantograph fault detection device and a storage medium, which can detect the abnormity of a pantograph from multiple aspects, ensure the comprehensiveness and accuracy of pantograph fault detection and improve the driving safety.
In order that those skilled in the art will better understand the disclosure, the following detailed description will be given with reference to the accompanying drawings.
Fig. 1 is a flowchart of a method for detecting a pantograph fault of a motor train unit according to an embodiment of the present application. As shown in fig. 1, the method includes:
s10: and constructing a fault detection algorithm model through historical monitoring images of the pantograph, wherein the historical monitoring images comprise corresponding monitoring images when foreign matters exist in the pantograph.
In specific implementation, the fault detection algorithm model takes historical fault data of a pantograph as a sample, and is obtained through a YOLO algorithm test and training, historical monitoring images of the pantograph can be selected in various scenes such as daytime, night and tunnel, and the historical monitoring images can include monitoring images corresponding to the pantograph when a foreign object exists, monitoring images corresponding to the pantograph when a carbon sliding plate is worn, monitoring images corresponding to the pantograph when the pantograph structure is abnormal, and monitoring images corresponding to the pantograph when an included angle between the carbon sliding plate and a calibration horizontal line is greater than a preset threshold value.
S11: and acquiring a monitoring image of the pantograph.
Specifically, the monitoring image is acquired and extracted by a pantograph image acquisition device, and the monitoring image may be an image obtained by shooting a pantograph or an image frame including the pantograph captured from a monitoring video of the pantograph.
S12: and inputting the monitoring image into a fault detection algorithm model to obtain a foreign matter intrusion detection result.
S13: and judging whether the motion path of the target intrusion item takes the pantograph as a terminal point or not according to the foreign object intrusion detection result. If yes, the process proceeds to S14.
S14: and judging the target invasion item as a foreign matter invasion item.
In specific implementation, the fault detection algorithm model performs corresponding processing on the acquired monitoring image, and adopts technologies such as feature extraction and the like to judge and obtain a foreign object intrusion detection result.
Further, after the monitoring image is acquired, the fault detection algorithm model further includes:
carrying out foreground separation on each monitoring image to lock a target invasion item;
and acquiring the motion path of the target intrusion item through a tracking algorithm.
In the specific implementation, the fault detection algorithm model carries out foreground separation on each frame of monitoring image, the method can effectively detect the change of the image, lock all potential invasion items, and adopt the efficient tracking algorithm for each invasion item to obtain the motion path of the target invasion item. The method of combining optical flow and random forest is adopted for tracking, and the accuracy and the integrity of the tracking are ensured to the greatest extent so as to be convenient for analyzing the motion path of the invasion item. Under the condition that the motion path has no obvious change, the target intrusion item is judged to be an environmental interference item, the characteristic statistic change is not obvious, or the intrusion item of which the motion path takes the image boundary as an end point is mostly an environmental interference item. And recording the intrusion item of which the feature statistic changes greatly and the motion path takes the pantograph region as an end point, and outputting a foreign matter intrusion detection result.
According to the method for detecting the pantograph fault of the motor train unit, firstly, a fault detection algorithm model is established through a historical monitoring image of the pantograph, and the historical monitoring image comprises a monitoring image corresponding to the pantograph when the pantograph has foreign matters, so that the foreign matters can be detected from the monitoring image and a foreign matter intrusion detection result can be obtained when the monitoring image of the pantograph is obtained, then whether the target intrusion item takes the pantograph as a terminal point or not is judged according to a motion path of the target intrusion item in the foreign matter intrusion detection result, and if the target intrusion item is the real foreign matter intrusion item. By applying the technical scheme, the foreign matter invasion of the pantograph can be detected, the comprehensiveness of pantograph fault detection is ensured, and the driving safety is improved. In addition, the historical monitoring image adopted in the training of the fault detection algorithm model is a real image in actual monitoring, so that the accuracy of the pantograph fault detection result is ensured.
On the basis of the foregoing embodiment, as a preferred embodiment, the history monitoring image further includes a monitoring image corresponding to the wear time of the carbon sliding plate of the pantograph, and the fault detection algorithm model further includes, after acquiring the monitoring image:
obtaining pre-stored thickness calibration values of different positions of the carbon sliding plate;
extracting a side image of the carbon sliding plate from the monitoring image;
obtaining thickness measurement values of different positions of the carbon sliding plate in the side image;
and calculating abrasion distribution data of the carbon slide plate according to the thickness calibration value and the thickness measurement value and outputting an abrasion detection result of the pantograph carbon slide plate.
In specific implementation, a high-definition image is acquired by adjusting the focal length of a lens of a pantograph camera, an image basis is provided for accurately extracting the edge information of the sliding plate, the intelligent analysis host machine applies an image automatic identification algorithm to extract the edge of the pantograph, extracts the continuous edge information of the carbon sliding plate, and then calculates the thickness of the sliding plate through the prestored thickness calibration values at different positions of the carbon sliding plate. It will be appreciated that successive thickness measurements can be calculated by polling the preset points with a camera to obtain complete wear profile data.
In specific implementation, the structural abnormality monitoring is divided into two parts, namely geometric morphology monitoring and comparison monitoring.
On the basis of the foregoing embodiment, as a preferred embodiment, the history monitoring image further includes a monitoring image corresponding to the pantograph when the structure of the pantograph is abnormal, and the fault detection algorithm model further includes, after acquiring the monitoring image:
carrying out image enhancement processing on the monitoring image;
performing feature extraction on the monitoring image subjected to image enhancement processing to obtain a feature distribution response diagram of the pantograph;
carrying out invariance analysis on the characteristic distribution response diagram to obtain the geometric shape estimation of the pantograph;
obtaining the standard values of the form parameters of a carbon sliding plate, a bracket and a cleat of a pantograph;
and performing correlation comparison on the geometric parameters in the geometric form estimation and the form parameter standard values and outputting an abnormal detection result of the bow structure.
In this embodiment, the pantograph structure abnormality detection result is obtained by geometric form monitoring, image enhancement processing is performed on the monitored image, feature extraction is performed by using a gradient operator to obtain a feature distribution response map of the pantograph, and invariance analysis is performed on the feature distribution response map to obtain geometric form estimation of the pantograph. It is to be appreciated that the Hu moment is typically applied to achieve invariance analysis.
On the basis, the geometric parameters in the geometric form estimation are defined in a correlation mode according to the form parameter standard values of the carbon sliding plate, the support and the cleat in the pantograph structure, and the area where the geometric parameters do not meet the standard is recorded.
On the basis of the foregoing embodiment, as a preferred embodiment, the history monitoring image further includes a monitoring image corresponding to the pantograph when the structure of the pantograph is abnormal, and the fault detection algorithm model further includes, after acquiring the monitoring image:
weighting and offset calibrating a plurality of monitoring images before the current monitoring image and a plurality of monitoring images after the current monitoring image to obtain a target monitoring image;
and carrying out similarity judgment on the current monitoring image and the target monitoring image and outputting an abnormal detection result of the bow structure.
In this embodiment, the detection result of the bow structure abnormality is obtained through comparison and monitoring. Weighting and offset calibrating a plurality of frames of monitoring images before the current monitoring image and a plurality of frames of monitoring images after the current monitoring image to obtain a target monitoring image, wherein the plurality of frames of monitoring images before the current monitoring image and the plurality of frames of monitoring images after the current monitoring image are selected based on the standard of no abnormity, and on the basis, similarity judgment is carried out on the current monitoring image and the target monitoring image, and correlation estimation can better realize similarity judgment and has better noise resistance. And if the similarity judgment result is smaller than a preset threshold value, judging that the bow structure is abnormal and outputting a detection result of the bow structure abnormality. It can be understood that the selection of the preset threshold is not limited in the present application, and may be specifically limited according to the actual application scenario. In other embodiments, the classifier may be used to monitor whether the region element exists, and if not, the region element is directly determined to be abnormal.
On the basis of the foregoing embodiment, as a preferred embodiment, the historical monitoring image further includes a monitoring image corresponding to a case where an included angle between a carbon sliding plate of the pantograph and the calibration horizontal line is greater than a preset threshold, and the fault detection algorithm model further includes, after acquiring the monitoring image:
determining a pantograph region in the monitoring image through a positioning model;
extracting a pantograph angle region in the pantograph region through a pantograph angle sub-model;
determining the area of the carbon sliding plate through the bow angle area;
acquiring form information of the carbon sliding plate through a straight line fitting algorithm to determine an included angle between the carbon sliding plate and a calibration horizontal line;
and outputting the detection result of the inclination angle of the pantograph.
In the specific implementation, the pantograph region in the monitoring image is firstly determined through a positioning model, namely the total position of the pantograph is determined, and the positioning model has better compatibility to various forms including a typical fault form and various interference imaging forms so as to provide a basis for the subsequent monitoring step. And then, the pantograph angle submodel is used for extracting the pantograph angle position in the pantograph region, and the pantograph angle submodel is used for accurately regressing the position information through big data training, so that the subsequent monitoring region is reduced, the interference is reduced, and the monitoring precision is improved. And then determining the area of the carbon sliding plate through regression data, obtaining the form information of the carbon sliding plate by using a straight line fitting algorithm, further determining the included angle between the carbon sliding plate and a calibration horizontal line, and outputting the detection result of the inclination angle of the pantograph according to the included angle.
It should be noted that, if the straight line fitting fails or the fitting information does not conform to the prior setting, the position of the carbon slide plate is determined according to the positions of the two bow angles according to regression data in the bow angle sub-model, so as to measure and calculate the angle, and the obviously abnormal situation is processed according to the fault-oriented safety principle.
According to the method for detecting the pantograph fault of the motor train unit, the process of detecting the abnormity of the pantograph is introduced in detail from four aspects, so that the accuracy of pantograph fault detection is ensured, and the driving safety is improved.
On the basis of the above embodiment, as a preferred embodiment, the method further includes:
acquiring a pantograph carbon slide plate abrasion detection result, a pantograph structure abnormity detection result, a foreign matter invasion detection result and a pantograph inclination angle detection result;
and analyzing and early warning a pantograph carbon slide plate abrasion detection result, a pantograph structure abnormity detection result, a foreign matter invasion detection result and a pantograph inclination angle detection result.
In this embodiment, the controller acquires pantograph carbon slide abrasion detection result, bow structure anomaly detection result, foreign matter invasion detection result and pantograph inclination angle detection result, and the controller carries out analysis comparison with preset's threshold value according to data such as the wearing and tearing condition of carbon slide and the size of pantograph inclination angle to in time early warning under the unusual condition of judgement, so that relevant staff in time looks over, improved driving safety.
In the above embodiments, the method for detecting the pantograph fault of the motor train unit is described in detail, and the application also provides embodiments corresponding to the pantograph fault detection device of the motor train unit. It should be noted that the present application describes the embodiments of the apparatus portion from two perspectives, one from the perspective of the function module and the other from the perspective of the hardware.
Fig. 2 is a schematic structural diagram of a pantograph fault detection device of a motor train unit according to an embodiment of the present application. As shown in fig. 2, the apparatus includes, based on the angle of the function module:
the fault detection system comprises a construction module 10, a fault detection algorithm model and a fault detection module, wherein the construction module is used for constructing the fault detection algorithm model through historical monitoring images of the pantograph, and the historical monitoring images comprise corresponding monitoring images when foreign matters exist in the pantograph;
the acquisition module 11 is used for acquiring a monitoring image of the pantograph;
the input module 12 is used for inputting the monitoring image into the fault detection algorithm model to obtain a foreign matter intrusion detection result;
the judging module 13 is configured to judge whether the motion path of the target intrusion item takes the pantograph as an end point according to the foreign object intrusion detection result; and if so, judging that the target invasion item is a foreign matter invasion item.
Since the embodiments of the apparatus portion and the method portion correspond to each other, please refer to the description of the embodiments of the method portion for the embodiments of the apparatus portion, which is not repeated here.
The utility model provides a EMUs pantograph fault detection device, at first construct the fault detection algorithm model through the historical monitoring image of pantograph, because historical monitoring image includes the monitoring image that corresponds when the foreign matter exists in the pantograph, so when obtaining the monitoring image of pantograph, can detect the foreign matter and obtain the foreign matter invasion testing result from the monitoring image, then judge whether this target invasion item uses the pantograph as the terminal point according to the motion path of target invasion item in the foreign matter invasion testing result, if, then be real foreign matter invasion item. By applying the technical scheme, the foreign matter invasion of the pantograph can be detected, the comprehensiveness of pantograph fault detection is ensured, and the driving safety is improved. In addition, the historical monitoring image adopted in the training of the fault detection algorithm model is a real image in actual monitoring, so that the accuracy of the pantograph fault detection result is ensured.
Fig. 3 is a structural diagram of a pantograph fault detection device of a motor train unit according to another embodiment of the present application, and as shown in fig. 3, the device includes, based on a hardware structure:
a memory 20 for storing a computer program;
and the processor 21 is used for implementing the steps of the pantograph fault detection method of the motor train unit in the embodiment when executing the computer program.
Memory 20 may include, among other things, one or more computer-readable storage media, which may be non-transitory. Memory 20 may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices, in either a transitory or persistent manner. The memory 20 may be an internal storage unit of the pantograph fault detection device of the motor train unit in some embodiments.
The processor 21 may be, in some embodiments, a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor or other data Processing chip, and is configured to run program codes stored in the memory 20 or process data, for example, execute a program corresponding to a pantograph fault detection method of the motor train Unit.
In some embodiments, the bus 22 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 3, but this does not mean only one bus or one type of bus.
Those skilled in the art will appreciate that the configuration shown in fig. 3 does not constitute a limitation of the pantograph fault detection device of the motor train unit, and may include more or less components than those shown.
The device for detecting the pantograph fault of the motor train unit comprises a memory and a processor, wherein when the processor executes a program stored in the memory, the following method can be realized: firstly, a fault detection algorithm model is constructed through a historical monitoring image of a pantograph, and the historical monitoring image comprises a monitoring image corresponding to the pantograph when the pantograph has foreign matters, so that the foreign matters can be detected from the monitoring image and a foreign matter intrusion detection result can be obtained when the monitoring image of the pantograph is obtained, then whether a target intrusion item takes the pantograph as a terminal point or not is judged according to a motion path of the target intrusion item in the foreign matter intrusion detection result, and if so, the target intrusion item is a real foreign matter intrusion item. By applying the technical scheme, the foreign matter invasion of the pantograph can be detected, the comprehensiveness of pantograph fault detection is ensured, and the driving safety is improved. In addition, the historical monitoring image adopted in the training of the fault detection algorithm model is a real image in actual monitoring, so that the accuracy of the pantograph fault detection result is ensured.
Finally, the application also provides a corresponding embodiment of the computer readable storage medium. The computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps as set forth in the above-mentioned method embodiments.
It is to be understood that if the method in the above embodiments is implemented in the form of software functional units and sold or used as a stand-alone product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium and executes all or part of the steps of the methods described in the embodiments of the present application, or all or part of the technical solutions. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The method, the device and the storage medium for detecting the pantograph fault of the motor train unit are described in detail above. The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (10)
1. A motor train unit pantograph fault detection method is characterized by comprising the following steps:
constructing a fault detection algorithm model through historical monitoring images of the pantograph, wherein the historical monitoring images comprise corresponding monitoring images when foreign matters exist in the pantograph;
acquiring a monitoring image of the pantograph;
inputting the monitoring image into the fault detection algorithm model to obtain a foreign matter intrusion detection result;
judging whether the movement path of the target intrusion item takes the pantograph as an end point or not according to the foreign object intrusion detection result;
and if so, judging that the target invasion item is a foreign matter invasion item.
2. The method for detecting the pantograph fault of the motor train unit according to claim 1, wherein after the fault detection algorithm model acquires the monitoring image, the method further comprises the following steps:
carrying out foreground separation on each monitoring image so as to lock the target invasion item;
and acquiring the motion path of the target intrusion item through a tracking algorithm.
3. The method for detecting the fault of the pantograph of the motor train unit according to claim 1, wherein the historical monitoring images further include monitoring images corresponding to the wear-out time of the carbon sliding plate of the pantograph, and the fault detection algorithm model further includes, after acquiring the monitoring images:
obtaining pre-stored thickness calibration values of different positions of the carbon sliding plate;
extracting a side image of the carbon sliding plate from the monitoring image;
obtaining thickness measurement values of different positions of the carbon sliding plate in the side image;
and calculating abrasion distribution data of the carbon slide plate according to the thickness calibration value and the thickness measurement value and outputting an abrasion detection result of the carbon slide plate of the pantograph.
4. The method for detecting the fault of the pantograph of the motor train unit according to claim 1, wherein the historical monitoring images further include corresponding monitoring images when the structure of the pantograph is abnormal, and the fault detection algorithm model further includes, after acquiring the monitoring images:
carrying out image enhancement processing on the monitoring image;
performing feature extraction on the monitoring image subjected to image enhancement processing to obtain a feature distribution response diagram of the pantograph;
performing invariance analysis on the characteristic distribution response diagram to obtain a geometric shape estimation of the pantograph;
obtaining the standard values of the form parameters of the carbon sliding plate, the bracket and the cleat of the pantograph;
and performing correlation comparison on the geometric parameters in the geometric form estimation and the form parameter standard values and outputting an abnormal detection result of the bow structure.
5. The method for detecting the fault of the pantograph of the motor train unit according to claim 1, wherein the historical monitoring images further include corresponding monitoring images when the structure of the pantograph is abnormal, and the fault detection algorithm model further includes, after acquiring the monitoring images:
weighting and offset calibrating a plurality of monitoring images before the current monitoring image and a plurality of monitoring images after the current monitoring image to obtain a target monitoring image;
and carrying out similarity judgment on the current monitoring image and the target monitoring image and outputting an abnormal detection result of the bow structure.
6. The method for detecting the fault of the pantograph of the motor train unit according to claim 1, wherein the historical monitoring images further include corresponding monitoring images when an included angle between a carbon sliding plate of the pantograph and a calibration horizontal line is larger than a preset threshold value, and the fault detection algorithm model further includes, after acquiring the monitoring images:
determining a pantograph region in the monitoring image through a positioning model;
extracting a pantograph angle region in the pantograph region through a pantograph angle sub-model;
determining a carbon slide plate area through the bow angle area;
acquiring form information of the carbon sliding plate through a straight line fitting algorithm to determine an included angle between the carbon sliding plate and a calibration horizontal line;
and outputting the detection result of the inclination angle of the pantograph.
7. The method for detecting the pantograph fault of the motor train unit according to any one of claims 2 to 6, further comprising:
acquiring a pantograph carbon slide plate abrasion detection result, a pantograph structure abnormity detection result, a foreign matter invasion detection result and a pantograph inclination angle detection result;
and analyzing and early warning the pantograph carbon slide plate abrasion detection result, the pantograph structure abnormity detection result, the foreign matter invasion detection result and the pantograph inclination angle detection result.
8. The utility model provides a EMUs pantograph fault detection device which characterized in that includes:
the device comprises a construction module, a fault detection algorithm module and a fault detection module, wherein the construction module is used for constructing a fault detection algorithm model through historical monitoring images of the pantograph, and the historical monitoring images comprise corresponding monitoring images when foreign matters exist in the pantograph;
the acquisition module is used for acquiring a monitoring image of the pantograph;
the input module is used for inputting the monitoring image into the fault detection algorithm model to obtain a foreign matter intrusion detection result;
the judging module is used for judging whether the motion path of the target intrusion item takes the pantograph as a terminal point according to the foreign object intrusion detection result; and if so, judging that the target invasion item is a foreign matter invasion item.
9. The device for detecting the pantograph fault of the motor train unit is characterized by comprising a memory, a first detection module, a second detection module and a third detection module, wherein the memory is used for storing a computer program;
a processor for implementing the steps of the method for detecting a pantograph fault of a motor train unit according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, wherein the computer-readable storage medium has a computer program stored thereon, which, when being executed by a processor, implements the steps of the method for detecting a pantograph fault of a motor train unit according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110348306.6A CN112991318A (en) | 2021-03-31 | 2021-03-31 | Motor train unit pantograph fault detection method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110348306.6A CN112991318A (en) | 2021-03-31 | 2021-03-31 | Motor train unit pantograph fault detection method and device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112991318A true CN112991318A (en) | 2021-06-18 |
Family
ID=76338625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110348306.6A Pending CN112991318A (en) | 2021-03-31 | 2021-03-31 | Motor train unit pantograph fault detection method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112991318A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763491A (en) * | 2021-08-26 | 2021-12-07 | 浙江中烟工业有限责任公司 | Visual detection method for tobacco shred barrel residues |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012015698A (en) * | 2010-06-30 | 2012-01-19 | Meidensha Corp | Pantograph detection device and method thereof |
| CN104463904A (en) * | 2014-09-22 | 2015-03-25 | 国家电网公司 | High-voltage line foreign matter invasion target detection method |
| CN107742288A (en) * | 2017-10-11 | 2018-02-27 | 成都国铁电气设备有限公司 | A kind of pantograph beats bow defect inspection method and system |
| CN109376609A (en) * | 2018-09-27 | 2019-02-22 | 易讯科技股份有限公司 | Recognition methods, device and the intelligent terminal of pantograph abrasion |
| CN110378897A (en) * | 2019-07-25 | 2019-10-25 | 中车青岛四方机车车辆股份有限公司 | A kind of pantograph running state real-time monitoring method and device based on video |
| CN111260629A (en) * | 2020-01-16 | 2020-06-09 | 成都地铁运营有限公司 | Pantograph structure abnormity detection algorithm based on image processing |
-
2021
- 2021-03-31 CN CN202110348306.6A patent/CN112991318A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012015698A (en) * | 2010-06-30 | 2012-01-19 | Meidensha Corp | Pantograph detection device and method thereof |
| CN104463904A (en) * | 2014-09-22 | 2015-03-25 | 国家电网公司 | High-voltage line foreign matter invasion target detection method |
| CN107742288A (en) * | 2017-10-11 | 2018-02-27 | 成都国铁电气设备有限公司 | A kind of pantograph beats bow defect inspection method and system |
| CN109376609A (en) * | 2018-09-27 | 2019-02-22 | 易讯科技股份有限公司 | Recognition methods, device and the intelligent terminal of pantograph abrasion |
| CN110378897A (en) * | 2019-07-25 | 2019-10-25 | 中车青岛四方机车车辆股份有限公司 | A kind of pantograph running state real-time monitoring method and device based on video |
| CN111260629A (en) * | 2020-01-16 | 2020-06-09 | 成都地铁运营有限公司 | Pantograph structure abnormity detection algorithm based on image processing |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763491A (en) * | 2021-08-26 | 2021-12-07 | 浙江中烟工业有限责任公司 | Visual detection method for tobacco shred barrel residues |
| CN113763491B (en) * | 2021-08-26 | 2024-03-12 | 浙江中烟工业有限责任公司 | Visual detection method for tobacco shred barrel residues |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111310645B (en) | Method, device, equipment and storage medium for warning overflow bin of goods accumulation | |
| US7218757B2 (en) | Method and device for detecting obstruction in image sensor systems | |
| CN107743577B (en) | Method and apparatus for detecting vibration information of electric railway vehicle | |
| CN111566493B (en) | Method and system for circuit breaker condition monitoring | |
| KR102032459B1 (en) | Apparatus and method for monitoring of pantograph in electric railway | |
| CN111105437B (en) | Vehicle track abnormality judging method and device | |
| CN108009574B (en) | Track fastener detection method | |
| KR102006763B1 (en) | Method and System for Analyzing Road Congestion Using CCTV | |
| CN112906647B (en) | Method and device for monitoring load of small-span bridge, computer equipment and storage medium | |
| CN112197715B (en) | Elevator brake wheel and brake shoe gap detection method based on image recognition | |
| EP3243671A1 (en) | Method and apparatus for classifying a tyre | |
| CN104378539A (en) | Scene-adaptive video structuring semantic extraction camera and method thereof | |
| CN112991318A (en) | Motor train unit pantograph fault detection method and device and storage medium | |
| CN111862073A (en) | Temperature acquisition method and device for power equipment | |
| CN114820626A (en) | Intelligent detection method for automobile front part configuration | |
| CN112417952B (en) | Environment video information availability evaluation method of vehicle collision prevention and control system | |
| CN113639685A (en) | Displacement detection method, device, equipment and storage medium | |
| CN112104838B (en) | Image distinguishing method, monitoring camera and monitoring camera system thereof | |
| KR102133330B1 (en) | Apparatus and method for recognizing crack in sturcutre | |
| CN113049595A (en) | Pantograph wear measurement method and system | |
| CN105512633A (en) | Power system dangerous object identification method and apparatus | |
| WO2017077261A1 (en) | A monocular camera cognitive imaging system for a vehicle | |
| Guo et al. | Wheel tread defects inspection based on SVM | |
| WO2009115918A1 (en) | Object detection device | |
| CN109243150A (en) | A kind of vehicle early warning method and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210618 |