CN115810010B - Train pantograph online detection method and system - Google Patents
Train pantograph online detection method and system Download PDFInfo
- Publication number
- CN115810010B CN115810010B CN202310059322.2A CN202310059322A CN115810010B CN 115810010 B CN115810010 B CN 115810010B CN 202310059322 A CN202310059322 A CN 202310059322A CN 115810010 B CN115810010 B CN 115810010B
- Authority
- CN
- China
- Prior art keywords
- pantograph
- train
- horn
- slide plate
- carbon slide
- 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.)
- Active
Links
Images
Abstract
The invention discloses an online detection method and system for a train pantograph, which comprises the steps of preprocessing a pantograph image to obtain a preprocessed image, acquiring positioning area information based on the preprocessed image to calculate the residual thickness of a carbon sliding plate for detecting defects of the carbon sliding plate, performing morphological processing according to the synthesized pantograph image to obtain goat horn position information for detecting goat horn states, judging whether information such as center deviation is abnormal or not as abnormal output results of the pantograph through a preset threshold value, and performing comprehensive online measurement and analysis on the pantograph, so that the overhaul efficiency is greatly improved, the problem that the pantograph is difficult to detect in the online running process of the train is fundamentally solved, faults and early warning can be timely reported for the pantograph faults, potential safety hazards are eliminated, and pantograph accidents are avoided.
Description
Technical Field
The invention relates to the technical field of train safety monitoring, in particular to a train pantograph online detection method and system.
Background
With the rapid development of the rail transit industry, the running environment of trains is more and more complex, the holding capacity and technical content of the metro vehicles are continuously improved, and the maintenance workload of the metro vehicles is increasingly increased. As the operational life of the equipment increases, the equipment of the train gradually enters a failure high-occurrence period, and the current maintenance work of the vehicle is still based on planned maintenance, so that the daily inspection and maintenance of the vehicle are emphasized. The problems of huge maintenance team, high maintenance labor cost and the like are faced. Meanwhile, the periodic inspection mode mainly based on manual inspection has many defects, such as omission of maintenance projects, long maintenance time consumption, high dependence of maintenance effect on quality of workers and the like. The pantograph is used as a key power supply component of the train, and the quality of the pantograph is important to the driving safety. The traditional pantograph inspection mode is that a train returns to a warehouse and then is maintained at a designated position, the pantograph of the train is maintained after power failure, and several trains are maintained according to a plan every day. This method has a great disadvantage that neither sudden pantograph failure of the main line operation can be found in time, nor existing pantograph failure can be found stably. Therefore, a mode that the state of the pantograph can be monitored in real time and the fault is reported under the condition that normal driving is not influenced is urgently needed, and the driving safety of the train is guaranteed.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the traditional pantograph inspection mode is power-off maintenance, so that sudden pantograph faults during the operation of a main line cannot be found in time, and existing pantograph faults are difficult to find stably; the invention aims to provide an on-line detection method and system for a train pantograph, which can capture the state information of the train pantograph in the on-line running under the condition of not influencing the normal running of the train, carry out on-line detection after pretreatment, greatly improve the maintenance efficiency, fundamentally solve the problem that the pantograph is difficult to detect in the on-line running process of the train, report faults and early warning on the pantograph faults in time, eliminate potential safety hazards and avoid pantograph accidents.
The invention is realized by the following technical scheme:
this scheme provides a train pantograph on-line measuring method, includes:
acquiring pantograph image information of a train from and to a train;
preprocessing pantograph image information;
carrying out online pantograph detection based on the preprocessed pantograph image information: firstly, determining the thickness of a pantograph carbon slide plate to detect the defects of the pantograph carbon slide plate, and determining the position of a horn to detect the state of the horn; and comprehensively judging the pantograph state based on the thickness of the pantograph carbon slide plate, the defect result of the pantograph carbon slide plate, the horn position and the horn state detection result to obtain the online detection result of the pantograph.
The working principle of the scheme is as follows: the invention aims to provide an online detection method and system for a pantograph of a train, which can capture the state information of the pantograph of the train running on a positive line under the condition of not influencing the normal running of the train, carry out online detection after pretreatment, greatly improve the maintenance efficiency, fundamentally solve the problem that the pantograph is difficult to detect in the running process of the positive line of the train, report faults and early warning on the pantograph faults in time, eliminate potential safety hazards and avoid pantograph accidents.
The further optimization scheme is that the pantograph image information acquisition method comprises the following steps:
a group of acquisition devices are respectively arranged on two sides of the acquisition point position and used for simultaneously acquiring image data of the left side and the right side of the pantograph, and each acquisition device comprises a camera and an explosion flash lamp;
acquiring an incoming signal of a train;
and taking the coming vehicle signal as an opening signal of the acquisition device to acquire the image information of the pantograph.
The further optimization scheme is that the method for acquiring the train coming signal of the train comprises the following steps:
acquiring the train number and judging whether the train number is wrong or not;
when the train number is correct, the coming train signal is generated:
each coming train magnetic steel or leaving train magnetic steel of the train is used as a trigger signal, and a coming train signal is generated when the generation times of the trigger signal in the preset time exceeds a threshold value.
The further optimization scheme is that the pretreatment comprises the following steps:
acquiring image data of the left side and the right side of a pantograph;
correcting image data on the left side and the right side of the pantograph based on calibration parameters of the acquisition point positions, and splicing the image data on the left side and the right side of the pantograph to obtain a complete pantograph image; the calibration parameters are obtained according to the field calibration of the acquisition point location and comprise camera external parameters and camera internal parameters;
and extracting a pantograph carbon slide plate detection area and two side horn detection areas in the complete pantograph image.
The further optimization scheme is that the method for determining the thickness of the pantograph carbon slide plate comprises the following steps:
s1, performing median filtering, image enhancement and edge sharpening on a carbon slide plate detection area of a pantograph;
s2, analyzing the background brightness characteristics of the pantograph carbon slide plate detection area, and carrying out edge sharpening processing on the carbon slide plate edge again on the pantograph carbon slide plate detection area obtained in the S1 based on the background brightness characteristics;
s3, performing deep learning edge extraction processing on the carbon slide plate in the detection area of the pantograph carbon slide plate obtained in the S2 to obtain a carbon slide plate outline;
s4, segmenting the upper edge and the lower edge of the carbon sliding plate along the outline of the carbon sliding plate;
s5, subdividing the upper edge of the carbon sliding plate and the lower edge of the carbon sliding plate into a plurality of contour points; and (3) carrying out sub-pixel edge detection on each contour point, namely subdividing each pixel into smaller 4 x 4 equal divisions, and subdividing the transition edge by applying an interpolation method to the 4 x 4 pixel matrix, so that the measurement precision of the system is improved, and the upper edge contour point is obtained.
S6, carrying out segmentation extraction on contour points of the lower edge of the carbon sliding plate to fit a plurality of straight line segments, calculating the distance from each contour point of the upper edge of the carbon sliding plate to the corresponding contour point of the lower edge to obtain a distance set, and screening out the minimum distance in the distance set as the minimum thickness of the carbon sliding plate;
and S7, obtaining the coordinate of the minimum thickness of the carbon sliding plate, collecting the thickness values of n points around the coordinate, and taking the average value of the n thickness values as the thickness of the carbon sliding plate of the pantograph to output.
The further optimization scheme is that the method for detecting the defects of the carbon pantograph slider comprises the following steps:
and preliminarily judging all elements in the distance set to determine the suspicious defect positions: sequentially comparing the threshold values of all elements in the distance set, judging that a defect exists when m continuous elements exceed the threshold values, and taking one or two elements which are positioned at the middlemost of the m elements as defect positions;
and inputting the defect suspicious position into a deep learning model to judge and obtain the position and the size of the defect.
The further optimization scheme is that the method for determining the position of the goat horn comprises the following steps:
performing morphological analysis on the horn detection areas on the two sides to obtain horn positions;
and performing interference removing algorithm, filtering and Blob analysis processing on the cavum detection areas on the two sides, and performing contour extraction at the cavum position to obtain precise information of the cavum position and cavum contour information.
The further optimization scheme is that the goat horn state detection method comprises the following steps:
fitting a pantograph contour based on the accurate horn position information and the horn contour information;
and (4) performing projection comparison on the pantograph outline and the standard outline, judging the conditions of projection superposition, projection dislocation or projection missing, and correspondingly outputting a normal state, a dislocated state or a missing state of the cavel.
This scheme still provides an online detecting system of train pantograph for realize the digital scheme the online detecting method of train pantograph, include:
the acquisition module is used for acquiring pantograph image information of coming and going trains;
the preprocessing module is used for preprocessing the pantograph image information;
the detection module is used for determining the thickness of the pantograph carbon slide plate to detect the pantograph carbon slide plate defect and determining the position of a horn to detect the horn state; and comprehensively judging the pantograph state based on the thickness of the pantograph carbon slide plate, the defect result of the pantograph carbon slide plate, the horn position and the horn state detection result to obtain the online detection result of the pantograph.
The further optimization scheme is that the acquisition module comprises at least 4 cameras and 8 flashing lamps; and 1 camera and 2 flashing lights are respectively arranged on the periphery of the acquisition point position. The collection module of this system adopts 4 cameras and 8 flashing light to detect the bow around the pantograph, and every camera and two flashing lights correspond half limit pantograph and detect to outstanding detection precision and detail, when the carbon slide triggered infrared sensor before the pantograph driving direction was gone up, the camera that corresponds triggered and is shot, and the position of guaranteeing to shoot at every turn is best. The mutual noninterference of shooing between camera about guaranteeing to weaken the error that the background interference thing brought.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the invention provides a train pantograph online detection method and a train pantograph online detection system; the method comprises the steps of preprocessing a pantograph image to obtain a preprocessed image, calculating the residual thickness of a carbon sliding plate for detecting the defect of the carbon sliding plate based on the preprocessed image to obtain positioning area information, performing morphological processing according to the synthesized pantograph image to obtain goat's horn position information for detecting the goat's horn state, judging whether the pantograph reaches a critical value of manual interference or not by judging whether the goat's horn state, the carbon sliding plate defect and other information are abnormal or not according to a preset threshold value, comprehensively measuring and analyzing the pantograph, greatly improving the overhauling efficiency, fundamentally solving the problem that the pantograph is difficult to detect in the train on-line operation process, timely reporting faults and early warning of the pantograph faults, eliminating potential safety hazards and avoiding pantograph accidents.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and that for those skilled in the art, other related drawings can be obtained from these drawings without inventive effort. In the drawings:
fig. 1 is a schematic flow chart of a train pantograph online detection method.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
The traditional pantograph checking mode is power-off maintenance, so that sudden pantograph faults during the operation of a main line cannot be found in time, and the existing pantograph faults are difficult to find stably.
In view of the above, the present invention provides the following embodiments to solve the above technical problems:
example 1
The embodiment provides an online detection method for a train pantograph, as shown in fig. 1, including:
firstly, acquiring pantograph image information of a train from and to a train;
the pantograph image information acquisition method comprises the following steps:
a group of acquisition devices are respectively arranged on two sides of the acquisition point position and used for simultaneously acquiring image data of the left side and the right side of the pantograph, and each acquisition device comprises a camera and an explosion flash lamp;
acquiring an incoming signal of a train; when a first train triggers a train number camera to take a picture to obtain a train number image, and OCR recognition is carried out on the train number image to obtain a train number;
the method for acquiring the train coming signal of the train comprises the following steps:
acquiring the train number and judging whether the train number is wrong or not; creating a folder by naming the serial number obtained by the incoming vehicle signal, naming the files of the pantograph images, and acquiring the quantity of the off-vehicle magnetic steels;
acquiring a departure signal based on the number of the departure magnetic steels, and calling a name verification rule based on the departure signal to verify the name of the file name;
when the train number is correct, the coming train signal is generated:
each coming magnetic steel or leaving magnetic steel of the train is used as a trigger signal, and a coming signal is generated when the generation times of the trigger signal in the preset time exceed a threshold value.
Creating a folder by naming the serial number obtained by the incoming vehicle signal, naming the files of the pantograph images, and acquiring the quantity of the off-vehicle magnetic steels; calling a name verification rule based on the departure signal to verify the name of the file name; acquiring the number of the off-train magnetic steels, and generating an on-train signal when the number of the off-train magnetic steels is 4M (M is the train grouping number); or when the quantity of the off-vehicle magnetic steel is 4M-1, delaying according to preset delay time to generate an on-vehicle signal.
And taking the coming vehicle signal as an opening signal of the acquisition device to acquire the pantograph image information.
Then, preprocessing pantograph image information; the pretreatment comprises the following steps:
acquiring image data of the left side and the right side of a pantograph;
correcting the image data of the left side and the right side of the pantograph based on the calibration parameters of the acquisition point positions, and splicing the image data of the left side and the right side of the pantograph to obtain a complete pantograph image; the calibration parameters are obtained according to the field calibration of the acquisition point location and comprise camera external parameters and camera internal parameters;
and extracting a pantograph carbon slide plate detection area and two side horn detection areas in the complete pantograph image.
And finally, carrying out online pantograph detection based on the preprocessed pantograph image information: firstly, determining the thickness of a pantograph carbon slide plate to detect the defects of the pantograph carbon slide plate, and determining the position of a horn to detect the state of the horn; and comprehensively judging the pantograph state based on the thickness of the pantograph carbon slide plate, the defect result of the pantograph carbon slide plate, the horn position and the horn state detection result to obtain the online detection result of the pantograph.
The method for determining the thickness of the pantograph carbon slide plate comprises the following steps:
s1, performing median filtering, image enhancement and edge sharpening on a carbon slide plate in a pantograph carbon slide plate detection area;
s2, analyzing background brightness characteristics of a pantograph carbon slide detection area, and carrying out carbon slide edge sharpening processing on the pantograph carbon slide detection area obtained in the S1 again on the basis of the background brightness characteristics; the detection precision of the carbon slide plate of the pantograph is mainly influenced by the sharpness of the edge of the image of the carbon slide plate, the purity of the background and the exposure time of a camera; therefore, the brightness and uniformity of the flashing light can be used as a way of improving the data result.
S3, performing deep learning edge extraction processing on the carbon slide plate in the detection area of the pantograph carbon slide plate obtained in the S2 to obtain the outline of the carbon slide plate;
s4, dividing the upper edge and the lower edge of the carbon sliding plate along the outline of the carbon sliding plate;
s5, subdividing the upper edge of the carbon sliding plate and the lower edge of the carbon sliding plate into a plurality of contour points; and (3) carrying out sub-pixel edge detection on each contour point, namely subdividing each pixel into smaller 4 x 4 equal divisions, and subdividing the transition edge by applying an interpolation method to the 4 x 4 pixel matrix, so that the measurement precision of the system is improved, and the upper edge contour point is obtained.
S6, carrying out segmentation extraction on contour points of the lower edge of the carbon sliding plate to fit a plurality of straight line segments, calculating the distance from each contour point of the upper edge of the carbon sliding plate to the corresponding contour point of the lower edge to obtain a distance set, and screening out the minimum distance in the distance set as the minimum thickness of the carbon sliding plate;
and S7, obtaining the coordinate of the minimum thickness of the carbon sliding plate, collecting the thickness values of n points around the coordinate, and taking the average value of the n thickness values as the thickness of the carbon sliding plate of the pantograph to output.
The pantograph carbon slide plate defect detection method comprises the following steps:
and preliminarily judging all elements in the distance set to determine the suspicious defect positions: sequentially comparing the threshold values of all elements in the distance set, judging that a defect exists when m continuous elements exceed the threshold values, and taking one or two elements which are positioned at the middlemost of the m elements as defect positions;
and inputting the defect suspicious position into a deep learning model to judge and obtain the position and the size of the defect.
The goat horn position determining method comprises the following steps:
performing morphological analysis on the goat horn detection areas on the two sides to obtain goat horn positions;
and performing interference removing algorithm, filtering and Blob analysis processing on the goat horn detection areas on the two sides, and performing contour extraction at the goat horn positions to obtain accurate goat horn position information and goat horn contour information.
The goat horn state detection method comprises the following steps:
fitting out a pantograph contour based on the accurate information of the goat's horn position and the goat's horn contour information;
and (4) performing projection comparison on the pantograph outline and the standard outline, judging the conditions of projection superposition, projection dislocation or projection missing, and correspondingly outputting a normal state, a dislocated state or a missing state of the cavel.
The model base training deep learning model can be established by using several common conditions according to the conditions of complete superposition, projection dislocation, projection loss and the like which can occur among projections; and (4) introducing a deep learning model to judge the error type, and finally outputting the state of the goat horn.
Carrying out comprehensive judgment on the pantograph state based on the thickness of the pantograph carbon slide plate, the defect result of the pantograph carbon slide plate, the horn position and the horn state detection result information; and judging whether the pantograph reaches a critical value of manual intervention or not according to a set threshold value.
Example 2
The embodiment provides an online detection system for a train pantograph, which is used for implementing the online detection method for the train pantograph in the previous embodiment, and the online detection system comprises:
the acquisition module is used for acquiring pantograph image information of the trains from and to;
the preprocessing module is used for preprocessing the pantograph image information;
the detection module is used for determining the thickness of the pantograph carbon slide plate to detect the pantograph carbon slide plate defect and determining the position of the horn to detect the state of the horn; and comprehensively judging the state of the pantograph based on the thickness of the carbon pantograph slider, the defect result of the carbon pantograph slider, the position of the ram horn and the detection result of the ram horn state to obtain the online detection result of the pantograph.
The acquisition module comprises at least 4 cameras and 8 flashing lamps; and 1 camera and 2 flashing lights are respectively arranged on the periphery of the acquisition point position. The collection module of this system adopts 4 cameras, 8 flashing lights to detect the pantograph all around, and every camera and two flashing lights correspond half limit pantograph and detect to outstanding detection precision and detail, when the carbon slide triggered infrared sensor before the pantograph driving direction, the camera that corresponds triggered and shoots, guaranteed the position of shooing at every turn best.
And the detection module calculates the pantograph overall information such as the lowest wear point of the carbon sliding plate, the carbon sliding plate gap, the center offset, the inclination angle, the horn deformation and the like according to the preprocessed pantograph image and a program algorithm, and finally outputs the pantograph overall information as a result after data comprehensive judgment.
2 cameras in the acquisition module respectively and relatively acquire in front of and behind the pantograph, avoid mutual interference between the light source to accomplish the measurement of the pantograph higher accuracy, solve the accuracy of pantograph data, the processing mode of integrality. The flashing light adopts spotlight effect, can avoid the flashing light to disperse the bright area that brings and overlap, promotes image quality.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only examples of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1. An online detection method for a train pantograph is characterized by comprising the following steps: acquiring pantograph image information of a train from and to a train; preprocessing pantograph image information;
carrying out online pantograph detection based on the preprocessed pantograph image information: determining the thickness of the pantograph carbon slide plate to detect the defects of the pantograph carbon slide plate, and determining the position of a horn to detect the state of the horn; then carrying out comprehensive judgment on the pantograph state based on the thickness of the pantograph carbon slide plate, the defect result of the pantograph carbon slide plate, the horn position and the horn state detection result to obtain an online pantograph detection result;
the pantograph image information acquisition method comprises the following steps:
a group of acquisition devices are respectively arranged on two sides of the acquisition point position and used for simultaneously acquiring image data of the left side and the right side of the pantograph, and each acquisition device comprises a camera and an explosion flash lamp;
acquiring an incoming signal of a train;
collecting pantograph image information by taking the coming vehicle signal as a starting signal of a collecting device;
the method for determining the thickness of the pantograph carbon slide plate comprises the following steps:
s1, performing median filtering, image enhancement and edge sharpening on a carbon slide plate in a pantograph carbon slide plate detection area;
s2, analyzing the background brightness characteristics of the pantograph carbon slide plate detection area, and carrying out edge sharpening processing on the carbon slide plate edge again on the pantograph carbon slide plate detection area obtained in the S1 based on the background brightness characteristics;
s3, performing deep learning edge extraction processing on the carbon slide plate in the detection area of the pantograph carbon slide plate obtained in the S2 to obtain the outline of the carbon slide plate;
s4, segmenting the upper edge and the lower edge of the carbon sliding plate along the outline of the carbon sliding plate;
s5, subdividing the upper edge of the carbon sliding plate and the lower edge of the carbon sliding plate into a plurality of contour points;
s6, carrying out segmentation extraction on contour points of the lower edge of the carbon sliding plate to fit a plurality of straight line segments, calculating the distance from each contour point of the upper edge of the carbon sliding plate to the corresponding contour point of the lower edge to obtain a distance set, and screening out the minimum distance in the distance set as the minimum thickness of the carbon sliding plate;
and S7, obtaining the coordinate of the minimum thickness of the carbon sliding plate, collecting the thickness values of n points around the coordinate, and taking the average value of the n thickness values as the thickness of the carbon sliding plate of the pantograph to output.
2. The on-line detection method for the pantograph of the train as claimed in claim 1, wherein the method for acquiring the incoming train signal of the train comprises:
acquiring the train number and judging whether the train number is wrong;
when the train number is correct, the coming train signal is generated:
each coming train magnetic steel or leaving train magnetic steel of the train is used as a trigger signal, and a coming train signal is generated when the generation times of the trigger signal in the preset time exceeds a threshold value.
3. The on-line detection method for the pantograph of the train as claimed in claim 1, wherein said preprocessing comprises the process of:
acquiring image data of the left side and the right side of a pantograph;
correcting the image data of the left side and the right side of the pantograph based on the calibration parameters of the acquisition point positions, and splicing the image data of the left side and the right side of the pantograph to obtain a complete pantograph image; the calibration parameters are obtained according to the field calibration of the acquisition point location and comprise camera external parameters and camera internal parameters;
and extracting a pantograph carbon slide plate detection area and two side horn detection areas in the complete pantograph image.
4. The on-line detection method for the pantograph of the train as claimed in claim 1, wherein the pantograph carbon slide plate defect detection method comprises the following steps:
and preliminarily judging all elements in the distance set to determine the suspicious defect positions: sequentially comparing the threshold values of all elements in the distance set, judging that a defect exists when m continuous elements exceed the threshold values, and taking one or two elements which are positioned at the middlemost of the m elements as defect positions;
and inputting the suspicious defect position into a deep learning model to judge the suspicious defect position to obtain the position and the size of the defect.
5. The on-line detection method for the pantograph of the train as claimed in claim 1, wherein the goat's horn position determination method comprises:
performing morphological analysis on the goat horn detection areas on the two sides to obtain goat horn positions;
and performing interference removing algorithm, filtering and Blob analysis processing on the goat horn detection areas on the two sides, and performing contour extraction at the goat horn positions to obtain accurate goat horn position information and goat horn contour information.
6. The on-line detection method for the pantograph of the train as claimed in claim 5, wherein the method for detecting the state of the goat's horn comprises:
fitting out a pantograph contour based on the accurate information of the goat's horn position and the goat's horn contour information;
and (4) comparing the pantograph outline with the standard outline in a projection manner, judging the conditions of projection coincidence, projection dislocation or projection deficiency, and correspondingly outputting a cavum normal state, a cavum dislocation state or a cavum deficiency state.
7. An on-line train pantograph detection system, for implementing the on-line train pantograph detection method according to any one of claims 1 to 6, comprising:
the acquisition module is used for acquiring pantograph image information of coming and going trains;
the preprocessing module is used for preprocessing the pantograph image information;
the detection module is used for determining the thickness of the pantograph carbon slide plate to detect the pantograph carbon slide plate defect and determining the position of the horn to detect the state of the horn; and comprehensively judging the pantograph state based on the thickness of the pantograph carbon slide plate, the defect result of the pantograph carbon slide plate, the horn position and the horn state detection result to obtain the online detection result of the pantograph.
8. The on-line train pantograph detection system according to claim 7, wherein said acquisition module comprises at least 4 cameras and 8 flashing lights; and 1 camera and 2 flashing lights are respectively arranged around the acquisition point position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310059322.2A CN115810010B (en) | 2023-01-17 | 2023-01-17 | Train pantograph online detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310059322.2A CN115810010B (en) | 2023-01-17 | 2023-01-17 | Train pantograph online detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115810010A CN115810010A (en) | 2023-03-17 |
| CN115810010B true CN115810010B (en) | 2023-04-18 |
Family
ID=85487411
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310059322.2A Active CN115810010B (en) | 2023-01-17 | 2023-01-17 | Train pantograph online detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115810010B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| IT1401952B1 (en) * | 2010-09-22 | 2013-08-28 | Henesis S R L | SYSTEM AND METHOD FOR PANTOGRAPH MONITORING. |
| CN109269474B (en) * | 2018-08-29 | 2021-03-30 | 广西大学 | Online image detection device and method for train-mounted pantograph running state |
| CN113324864B (en) * | 2020-02-28 | 2022-09-20 | 南京理工大学 | Pantograph carbon slide plate abrasion detection method based on deep learning target detection |
| CN111738907B (en) * | 2020-06-08 | 2022-08-23 | 广州运达智能科技有限公司 | Train pantograph detection method based on binocular calibration and image algorithm |
| CN112733976B (en) * | 2020-12-18 | 2023-05-09 | 攀枝花容则钒钛有限公司 | Pantograph carbon slide plate abrasion detection system |
| CN115265386A (en) * | 2022-08-01 | 2022-11-01 | 中车青岛四方机车车辆股份有限公司 | Carbon sliding plate abrasion detection method and related components |
-
2023
- 2023-01-17 CN CN202310059322.2A patent/CN115810010B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115810010A (en) | 2023-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102759347B (en) | Online in-process quality control device and method for high-speed rail contact networks and composed high-speed rail contact network detection system thereof | |
| CN105243381B (en) | Failure automatic identification detection system and method based on 3D information | |
| CN113112501B (en) | Vehicle-mounted track inspection device and method based on deep learning | |
| Karakose et al. | A new approach for condition monitoring and detection of rail components and rail track in railway | |
| CN105741291A (en) | Method for detecting faults of equipotential lines of high-speed railway overhead line system suspension devices | |
| CN108257171A (en) | Car radar assembling aperture detection method based on light vision | |
| CN114037703B (en) | Subway valve state detection method based on two-dimensional positioning and three-dimensional attitude calculation | |
| CN110186375A (en) | Intelligent high-speed rail white body assemble welding feature detection device and detection method | |
| CN113371028A (en) | Intelligent inspection system and method for electric bus-mounted track | |
| CN103422417A (en) | Dynamic identification system and method for detecting road surface damages | |
| CN115810010B (en) | Train pantograph online detection method and system | |
| CN113487570A (en) | High-temperature continuous casting billet surface defect detection method based on improved yolov5x network model | |
| CN109102499B (en) | Detection method and system for top of bullet train | |
| CN116071726A (en) | Road inspection system and method based on edge calculation | |
| KR20190119801A (en) | Vehicle Headlight Alignment Calibration and Classification, Inspection of Vehicle Headlight Defects | |
| CN113639685A (en) | Displacement detection method, device, equipment and storage medium | |
| CN114445636A (en) | Train bottom item mapping method | |
| CN113504243A (en) | Imaging device and imaging method for connecting area of contact net elastic sling and carrier cable | |
| CN113191239A (en) | Vehicle overall dimension dynamic detection system based on computer vision | |
| CN116424802B (en) | Scraper conveyor chain working condition monitoring system and monitoring method | |
| CN117557570A (en) | Rail vehicle abnormality detection method and system | |
| CN116071353B (en) | Bolt assembly detection method and system | |
| CN117593528B (en) | Rail vehicle bolt loosening detection method based on machine vision | |
| CN113962956B (en) | Foreign matter detection method for coal conveying belt conveyor | |
| CN112183342B (en) | Comprehensive convertor station defect identification method with template |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |