CN117876368A - Method and system for detecting abrasion and crack of carbon slide plate of contact rail collector shoe - Google Patents
Method and system for detecting abrasion and crack of carbon slide plate of contact rail collector shoe Download PDFInfo
- Publication number
- CN117876368A CN117876368A CN202410269942.3A CN202410269942A CN117876368A CN 117876368 A CN117876368 A CN 117876368A CN 202410269942 A CN202410269942 A CN 202410269942A CN 117876368 A CN117876368 A CN 117876368A
- Authority
- CN
- China
- Prior art keywords
- carbon slide
- slide plate
- point cloud
- abrasion
- cloud data
- 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
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 134
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 134
- 238000005299 abrasion Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims abstract description 13
- 238000010801 machine learning Methods 0.000 claims abstract description 6
- 238000012163 sequencing technique Methods 0.000 claims abstract description 6
- 238000003384 imaging method Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000004364 calculation method Methods 0.000 description 8
- 230000007547 defect Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000010891 electric arc Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the technical field of image processing, and discloses a method and a system for detecting abrasion and cracks of a carbon slide plate of a contact rail collector shoe, wherein the method comprises the following steps: acquiring high-quality contact rail image data by adopting an embedded 2D camera to obtain original point cloud data; sequencing, dividing and clustering the original point cloud data by adopting a machine learning algorithm to obtain processed point cloud data of the carbon slide plate area; extracting a plurality of groups of carbon slide plate key characteristic points by traversing the point cloud data of each carbon slide plate area, wherein the plurality of groups of carbon slide plate key characteristic points comprise a starting position key characteristic point I and an abrasion data key characteristic point II; and calculating the abrasion value and/or the crack length of the carbon slide plate according to the key characteristic points of the carbon slide plates, so as to judge whether the abrasion of the carbon slide plate is abnormal and/or whether the carbon slide plate has cracks. The invention realizes the identification and analysis of the abrasion and crack of the carbon slide plate of the collector shoe of all trains in the whole line through the steps.
Description
Technical Field
The invention relates to the technical field of collector shoe image processing, in particular to a method and a system for detecting abrasion and cracks of a carbon slide plate of a contact rail collector shoe.
Background
The collector shoe is used as another traction power supply mode of the contact line current taking, is an important device of the contact current taking of the electric bus and the third rail, and in the train running process, problems such as arc discharge, burning and the like can occur on the surface of the collector shoe carbon slide plate and the third rail, so that the surface of the carbon slide plate is abnormal in abrasion, cracks and the like, and when the problems are serious, the power of the vehicle is cut off, the running safety of the train is affected, and how to quickly and accurately detect the abrasion crack defect of the collector shoe carbon slide plate is an important link for ensuring the safe running of the train.
The collector shoe is usually detected by using a camera arranged at the bottom of the car body, a plurality of groups of cameras are matched with laser scanning to form an image of the carbon slide plate, and the analysis of abrasion and cracks of the carbon slide plate is completed through an image processing technology. Because the carbon slide plate and the third rail can generate friction in the process of taking the flow, the problem of uneven abrasion on the surface of the carbon slide plate can be caused by shaking of a vehicle body and uneven surface of the third rail or the carbon slide plate, the requirements of objects and collected images are higher, and the quality of images obtained by different vehicles running under different lines is different for the collector shoe carbon slide plate exposed in an external environment, so that the acquisition of high-quality image data is the key for calculating abrasion and cracks by adopting an image processing algorithm.
At present, an image processing method is generally adopted for the processing method of the defects of the carbon skateboard; firstly, a deep learning model is used for identifying defects of a carbon slide plate, but a large amount of time is consumed, and the requirement on the performance of a computer is high; and secondly, the traditional image processing method is used for extracting the carbon slide plate, but the threshold selection difference is larger, and the generalization capability is not strong. The method for detecting the abrasion abnormality and crack defect of the carbon slide plate of the contact rail collector shoe is provided by combining an image processing algorithm, adopting a non-contact embedded 2D image measurement technology to realize the abrasion calculation and crack analysis of the carbon slide plate of the collector shoe of all trains.
Disclosure of Invention
The invention aims at: aiming at the abnormal phenomena such as abrasion and crack of the carbon slide plate of the contact rail collector shoe at present, the invention provides a method for detecting the abrasion and crack of the carbon slide plate of the contact rail collector shoe, which comprises the steps of collecting point cloud data of the carbon slide plate, preprocessing the point cloud data to filter interference data, extracting key characteristic points of the carbon slide plate, calculating an abrasion value, extracting crack information and calculating crack length and slope through an embedded 2D imaging technology, and can quickly and efficiently identify the abnormal situation of the abrasion or crack in the image of the carbon slide plate of the contact rail collector shoe so as to avoid the problem of abnormal abrasion or crack and the like on the surface of the carbon slide plate, thereby causing power failure of a vehicle and guaranteeing the running safety of a train.
The technical scheme of the invention is as follows:
a method for detecting abrasion and cracks of a carbon slide plate of a contact rail collector shoe comprises the following steps:
s1, acquiring a contact rail image through an embedded 2D camera to obtain point coordinate information of each position on the contact rail, namely original point cloud data;
s2, sequentially carrying out sorting treatment, segmentation treatment and clustering treatment on the original point cloud data by adopting a machine learning algorithm to obtain point cloud data of the carbon slide plate area;
s3, extracting a plurality of groups of key characteristic points of the carbon slide plate by traversing the point cloud data of each carbon slide plate area; the key characteristic points of the carbon slide plates comprise a first key characteristic point of the initial position and a second key characteristic point of abrasion data;
and S4, calculating and obtaining a carbon slide plate abrasion value and/or a carbon slide plate crack length according to the key characteristic points of the plurality of groups of carbon slide plates, so as to judge whether the abrasion of the carbon slide plate is abnormal and/or whether the carbon slide plate has cracks.
Further, in step S2, the sorting process is performed on the original point cloud data, which specifically includes:
sorting the original point cloud data from large to small according to the ordinate value of the original point cloud data, and coarsely filtering interference light bars in the original point cloud data to obtain sorted point cloud data, thereby obtaining the point cloud of the collector shoe region.
Further, in step S2, the segmentation processing is performed on the original point cloud data, which specifically includes:
and dividing the ordered point cloud data through a preset ROI area to remove the interference point cloud data, and obtaining the point cloud data of the carbon slide plate area.
Further, in step S2, clustering is performed on the original point cloud data, including:
and clustering the segmented point cloud data by adopting a K-neighbor clustering algorithm to finish extraction of the point cloud data of the carbon slide plate area.
Further, K clustering centers are randomly selected from the carbon slide plate point cloud data, and cluster distribution is carried out;
calculating the distance between each center point and the previous center point through Euclidean formula, and re-obtaining the clustering center to finish center movement;
and repeating the steps until the number of K clusters is stopped, and obtaining the complete carbon slide plate area point cloud data.
Further, in step S3, the first key feature point of the initial position is the point of the minimum value of the ordinate in the point cloud data, i.e. the lowest point; the second abrasion data key characteristic point is the point cloud data which is traversed rightward by taking the first initial position key characteristic point as an initial position, when discontinuous abrupt change occurs to the abscissa value of two adjacent points, the difference of the ordinate values of the two adjacent points is larger than a threshold value, and the point with the maximum value of the abscissa value is the second abrasion data characteristic point.
Further, in step S4, according to the key feature points of the plurality of groups of carbon skateboards, the abrasion value of the carbon skateboards is calculated, so as to determine whether the abrasion of the carbon skateboards is abnormal, which specifically includes:
calculating the abrasion value of each group of carbon skateboards by utilizing the first key characteristic point of the initial position and the second key characteristic point of the abrasion data;
selecting a maximum abrasion value from a plurality of groups of data as a current abrasion value;
and when the current abrasion value is larger than the preset threshold value, judging that the current abrasion value is abnormal. And judging that the abrasion of the carbon slide plate is abnormal.
Further, in step S3, the plurality of groups of carbon slide key feature points further include a crack data key feature point three, wherein the crack data key feature point three uses the initial position key feature point one as an initial position, traverses the point cloud data rightward, and when the abscissa values of two adjacent points do not have discontinuous abrupt changes, but the difference of the ordinate values of two adjacent points is greater than a threshold value, namely, a crack appears at the position; when a plurality of crack positions are found, the maximum vertical coordinate difference value is used as crack data, and the point at the corresponding position is the key feature point III of the crack data.
Further, S4, according to key characteristic points of a plurality of groups of carbon sliding plates, calculating the crack length of the carbon sliding plates, so as to judge whether the carbon sliding plates have cracks or not, and specifically comprising the following steps:
combining key feature points III of crack data in the key feature point data of the plurality of groups of carbon slide plates to obtain crack information of the current carbon slide plate;
and calculating the crack length and the slope by using the ordinate value of the key feature point III of the crack data, and judging the crack trend.
Based on the method for detecting the abrasion and the crack of the carbon slide plate of the contact rail collector shoe, the invention also provides a system for detecting the abrasion and the crack of the carbon slide plate of the contact rail collector shoe, which is used for executing the method for detecting the abrasion and the crack of the carbon slide plate of the contact rail collector shoe, and particularly comprises a plurality of groups of 2D imaging devices, an embedded ARM control unit and a data processing unit. The 2D imaging device is arranged at the bottom of the vehicle body, the ARM control unit is in communication connection with the 2D imaging device and is used for completing acquisition of carbon slide point cloud data, the carbon slide point cloud data are transmitted to the data processing unit to detect abrasion and cracks of the carbon slide, and recognition and analysis of abrasion and cracks of the carbon slide of the collector shoe of all trains in the whole line are realized.
Compared with the prior art, the invention has the beneficial effects that:
1. the method for detecting the abrasion and the crack of the carbon slide plate has relatively small calculated amount, does not need to collect a large number of defect samples to perform long-time model training, has high speed, meets the requirement of online real-time detection, and simultaneously realizes the rapid detection of the abrasion abnormality and the crack defect of the carbon slide plate.
2. The method and the device can calculate the abrasion loss of the carbon slide plate of the collector shoe with high precision, and can analyze the distribution situation of the section abrasion loss of the carbon slide plate and the overall state of the abrasion loss of the carbon slide plate.
3. According to the invention, the cracks of the carbon slide plate are indirectly detected by adopting the distribution state of the abrasion of the carbon slide plate, and the cracks are not required to be extracted through a pixel level, so that the interference caused by factors such as environment and the like is reduced, and the detection accuracy is improved.
Drawings
FIG. 1 is a schematic flow chart of a method for detecting carbon slide wear and cracks in contact rail collector shoes.
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
Detailed Description
The conception, specific embodiments, and technical effects produced by the present invention will be clearly and completely described below with reference to examples and drawings to fully understand the objects, features, and effects of the present invention.
Example 1
The invention discloses a method for detecting abrasion and cracks of a carbon slide plate of a contact rail collector shoe, which comprises the following steps of:
s1, acquiring contact rail images through an embedded 2D camera to obtain points of each position on the contact railx,y) Coordinate information, i.e. origin cloud data. Wherein,，point cloud coordinate information respectively representing the first points toIndicating this point.
S2, because more interference exists in point cloud image data shot by the embedded 2D camera at different moments, the point cloud data needs to be preprocessed to filter interference light bars. The method comprises the following specific steps:
and sequentially carrying out y-direction sequencing treatment, segmentation treatment and clustering treatment on the original point cloud data by adopting a machine learning algorithm to obtain the point cloud data of the carbon slide plate area.
Further, a machine learning algorithm is adopted to sequentially perform y-direction sequencing, segmentation and clustering treatment on the original point cloud data, so as to obtain the point cloud data of the carbon slide plate area, which is specifically as follows:
s21, using the original point cloud dataIs (are) the longitudinal coordinate values of (a)Sequencing the original point cloud data from large to small to coarsely filter interference light bars in the original point cloud data to obtain sequenced point cloud data, and obtaining a collector shoe region point cloud data set M;
wherein y is 1 ＞y 2 ＞y3＞...＞y i ＞...＞y n ,,As the coordinate information of the nth point,。
s22, dividing the ordered point cloud data through a preset ROI area to remove interference point cloud data, and obtaining carbon slide plate area point cloud data. So as to improve the processing efficiency of the point cloud data and reduce the clustering time, thereby improving the detection efficiency of abrasion and cracks of the carbon slide plate.
S23, through the data processing, light bar information containing the carbon slide plate is obtained approximately, but the light bar imaged by the camera is discontinuous due to imaging non-uniformity and the like, so that subsequent calculation and extraction of the carbon slide plate are affected. In order to improve the subsequent calculation efficiency and the extraction speed of the carbon slide, the clustering processing is performed on the point cloud data of the carbon slide area obtained in the step S22 by using a machine learning clustering algorithm, so as to further determine the light bar area of the carbon slide, realize the clustering of discontinuous areas, and extract the point cloud data of the complete carbon slide and the carbon slide base, and specifically comprise the following steps:
and clustering the segmented point cloud data by adopting a K-neighbor clustering algorithm to finish extraction of the point cloud data of the carbon slide plate area.
Further, clustering is carried out on the point cloud data after the segmentation processing by adopting a K-neighbor clustering algorithm, and the clustering method specifically comprises the following steps:
randomly selecting K clustering centers from the carbon slide plate point cloud data, and performing cluster distribution;
calculating the distance between each center point and the previous center point through Euclidean formula, and re-obtaining the clustering center to finish center movement;
repeating the steps until the number of K clusters is stopped, and completing the clustering of the point cloud data of the carbon slide plate area.
S3, extracting a plurality of groups of key characteristic points of the carbon slide plate by traversing the point cloud data of each carbon slide plate area; the key characteristic points of the carbon slide plate comprise a first key characteristic point of the initial position and a second key characteristic point of abrasion data.
Further, the minimum ordinate in the collector shoe region point cloud data set M is usedCorresponding pointAs the lowest point, namely the key feature point I of the initial position;
from the key feature point of the initial positionTraversing the point cloud data set to the right when the abscissa of two adjacent pointsAnd (3) withDiscontinuous abrupt changes in the values of (2) occur and the ordinate of two adjacent pointsAnd (3) withWhen the difference between (1) and (b) is greater than a threshold value, i.e. the upper edge of the carbon slide is reached and the maximum value is taken on the abscissaPoints of (2)The second key characteristic point of the abrasion data is recorded as。
Further, the key feature points further comprise a crack data key feature point III. The method comprises the following steps: traversing the point cloud data rightward by using the first key characteristic point at the initial position, and determining the abscissa of two adjacent pointsAnd (3) withNo discontinuous abrupt change in the values of (2) but the ordinate of two adjacent pointsAnd (3) withThe difference of (2) is greater than a threshold, i.e. a crack occurs at that location; if a plurality of crack positions are found, the maximum difference value of the vertical coordinates is taken as crack data, and the point at the corresponding position is taken as a key characteristic point III and is recorded as。
And S4, calculating and obtaining a carbon slide plate abrasion value and/or a carbon slide plate crack length according to the key characteristic points of the plurality of groups of carbon slide plates, so as to judge whether the abrasion of the carbon slide plate is abnormal and/or whether the carbon slide plate has cracks. The method comprises the following steps:
processing each piece of 2D point cloud data to obtain a plurality of groups of carbon slide plate key characteristic points, wherein each group of characteristic points comprises any one or more of a first initial position key characteristic point, a second abrasion data key characteristic point and a third crack data key characteristic point;
and calculating a wear value or a crack value by taking n as a metering index and taking every n groups of data as a final result, wherein the crack value comprises a crack length and a crack slope.
Further, in step S4, the abrasion value calculation specifically includes:
calculating the abrasion value of each group of carbon skateboards by utilizing the first key characteristic point of the initial position and the second key characteristic point of the abrasion data;
selecting a maximum abrasion value from a plurality of groups of data as a current abrasion value;
and when the current abrasion value is larger than the preset threshold value, judging that the current abrasion value is abnormal.
Further, the specific formula for the abrasion value calculation is:，is the abrasion value. Outputting the abrasion value once every n groups of data, and selecting the abrasion value with the largest abrasion value as the final abrasion valueAI.e.，The wear value of the nth data is shown.
Further, in step S4, the crack value calculation specifically includes:
combining key feature points III of the crack data in the plurality of groups of data to obtain crack information of the current carbon slide plate;
and calculating the crack length and the slope by using the ordinate value of the key feature point III of the crack data, so as to judge the crack trend.
Further, the specific formula of the crack length calculation is:wherein, the method comprises the steps of, wherein,the ordinate value representing the starting point,representing the ordinate value of the last point.
Further, the specific formula of crack slope calculation is as follows：，Indicating the slope of the crack, i.e. indicating the crack progression. By calculating the starting pointTo the end pointTo determine the crack travel.
Example two
On the basis of the first embodiment, the invention also provides a system for detecting the abrasion and the crack of the carbon slide plate of the contact rail collector shoe, which is used for executing the method for detecting the abrasion and the crack of the carbon slide plate of the contact rail collector shoe, and comprises the following steps: the device comprises a plurality of groups of 2D imaging devices, an embedded ARM control unit and a data processing unit. The 2D imaging device is arranged at the bottom of the vehicle body, the ARM control unit is in communication connection with the 2D imaging device and is used for completing acquisition of carbon slide point cloud data, the carbon slide point cloud data are transmitted to the data processing unit to detect abrasion and cracks of the carbon slide, and recognition and analysis of abrasion and cracks of the carbon slide of the collector shoe of all trains in the whole line are realized.
The foregoing examples merely represent specific embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that, for those skilled in the art, several variations and modifications can be made without departing from the technical solution of the present application, which fall within the protection scope of the present application.
Claims (10)
1. The method for detecting the abrasion and the crack of the carbon slide plate of the contact rail collector shoe is characterized by comprising the following steps:
s1, acquiring a contact rail image through an embedded 2D camera to obtain point coordinate information of each position on a contact rail, namely original point cloud data;
s2, sequentially carrying out sorting treatment, segmentation treatment and clustering treatment on the original point cloud data by adopting a machine learning algorithm to obtain point cloud data of the carbon slide plate area;
s3, extracting a plurality of groups of key characteristic points of the carbon slide plate by traversing the point cloud data of each carbon slide plate area; the plurality of groups of carbon slide plate key characteristic points comprise a first initial position key characteristic point and a second abrasion data key characteristic point;
and S4, calculating and obtaining a carbon slide abrasion value and/or a carbon slide crack length according to the key characteristic points of the plurality of groups of carbon slide plates, so as to judge whether the carbon slide plates are abnormal in abrasion and/or whether the carbon slide plates have cracks.
2. The method for detecting wear and tear of a carbon slide of a contact rail collector shoe according to claim 1, wherein the sequencing process comprises:
and sequencing the original point cloud data from large to small according to the ordinate value of the original point cloud data, and coarsely filtering the interference light bars in the original point cloud data to obtain sequenced point cloud data, thereby obtaining the point cloud of the collector shoe region.
3. The method for detecting wear and tear of a carbon slide of a contact rail collector shoe according to claim 1, wherein the dividing process comprises:
and dividing the ordered point cloud data through a preset ROI area to remove the interference point cloud data, and obtaining the point cloud data of the carbon slide plate area.
4. The method for detecting wear and tear of a carbon slide plate of a contact rail collector shoe according to claim 1, wherein the clustering process comprises:
and clustering the segmented point cloud data by adopting a K-neighbor clustering algorithm to finish extraction of the point cloud data of the carbon slide plate area.
5. The method for detecting abrasion and cracks of the carbon slide plate of the contact rail collector shoe according to claim 4, wherein the clustering processing is carried out on the point cloud data after the segmentation processing by adopting a K-proximity clustering algorithm, specifically;
randomly selecting K clustering centers from the carbon slide plate point cloud data, and performing cluster distribution;
calculating the distance between each center point and the previous center point through Euclidean formula, and re-obtaining the clustering center to finish center movement;
and repeating the steps until the number of K clusters is stopped, and obtaining the complete carbon slide plate area point cloud data.
6. The method for detecting abrasion and crack of carbon slide plate of contact rail collector shoe according to claim 1, wherein,
the first key feature point of the initial position is a point with the minimum value of the ordinate in the point cloud data, namely the lowest point;
and the second abrasion data key characteristic point is the point cloud data which is traversed rightward by taking the first initial position key characteristic point as an initial position, when discontinuous abrupt change occurs to the abscissa value of two adjacent points, the difference of the ordinate values of the two adjacent points is larger than a threshold value, and the point with the maximum value of the abscissa value is taken as the second abrasion data characteristic point.
7. The method for detecting abrasion and crack of carbon slide plate of contact rail collector shoe according to claim 1, wherein,
calculating the abrasion value of each group of carbon sliding plates by utilizing the initial position key characteristic point I and the abrasion data key characteristic point II;
selecting a maximum abrasion value from a plurality of groups of data as a current abrasion value;
and when the current abrasion value is larger than a preset threshold value, judging that the current abrasion value is abnormal.
8. The method for detecting wear and tear of carbon sliding plates of contact rail collector shoes according to claim 1, wherein the plurality of groups of carbon sliding plate key characteristic points further comprise crack data key characteristic points III,
the third key characteristic point of the crack data takes the first key characteristic point of the initial position as the initial position, the point cloud data is traversed rightwards, and when the abscissa value of two adjacent points does not generate discontinuous abrupt change, but the difference of the ordinate values of the two adjacent points is larger than a threshold value, namely the position is cracked;
when a plurality of crack positions are found, the maximum vertical coordinate difference value is used as crack data, and the point at the corresponding position is the key feature point III of the crack data.
9. The method for detecting wear and tear of a carbon slide of a contact rail collector shoe according to claim 8, characterized in that,
combining key feature points III of the crack data in the plurality of groups of data to obtain crack information of the current carbon slide plate;
and calculating the crack length and the slope by using the ordinate value of the key feature point III of the crack data, and judging the crack trend.
10. A contact rail collector shoe carbon slide wear and crack detection system for executing a contact rail collector shoe carbon slide wear and crack detection method according to any one of claims 1-9, characterized by comprising a plurality of sets of 2D imaging devices, an embedded ARM control unit and a data processing unit;
the 2D imaging device is arranged at the bottom of the vehicle body, and the ARM control unit is connected with the 2D imaging device in a communication manner and is used for completing acquisition of point cloud data of the carbon skateboard.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410269942.3A CN117876368A (en) | 2024-03-11 | 2024-03-11 | Method and system for detecting abrasion and crack of carbon slide plate of contact rail collector shoe |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410269942.3A CN117876368A (en) | 2024-03-11 | 2024-03-11 | Method and system for detecting abrasion and crack of carbon slide plate of contact rail collector shoe |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117876368A true CN117876368A (en) | 2024-04-12 |
Family
ID=90595183
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410269942.3A Pending CN117876368A (en) | 2024-03-11 | 2024-03-11 | Method and system for detecting abrasion and crack of carbon slide plate of contact rail collector shoe |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117876368A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009018612A1 (en) * | 2007-08-06 | 2009-02-12 | Qr Limited | Pantograph damage and wear monitoring system |
| CN110853018A (en) * | 2019-11-13 | 2020-02-28 | 燕山大学 | Computer vision-based vibration table fatigue crack online detection system and detection method |
| DE102019127493A1 (en) * | 2019-10-11 | 2021-04-15 | IFSB Institut für Schadensbewertung GmbH | Procedure for crack classification in a building structure |
| CN112950532A (en) * | 2021-01-14 | 2021-06-11 | 成都铁安科技有限责任公司 | Train pantograph state detection method |
| CN114897921A (en) * | 2022-05-23 | 2022-08-12 | 合肥职业技术学院 | Pantograph abrasion value and pantograph abnormity real-time detection method based on machine vision |
| CN115439406A (en) * | 2022-07-29 | 2022-12-06 | 成都唐源电气股份有限公司 | Contact rail collector shoe carbon sliding plate defect identification method |
| CN115541591A (en) * | 2022-09-23 | 2022-12-30 | 北京交通大学 | Method and system for detecting abrasion edge of carbon pantograph slider of train |
| CN115876109A (en) * | 2022-12-01 | 2023-03-31 | 西南交通大学 | Novel subway pantograph abrasion detection method based on 2D laser measurement |
| CN116164652A (en) * | 2022-12-19 | 2023-05-26 | 东莞市诺丽科技股份有限公司 | Pantograph carbon slide plate detection method and system based on three-dimensional reconstruction technology |
| CN116519787A (en) * | 2023-07-05 | 2023-08-01 | 成都盛锴科技有限公司 | Third rail power receiving boot detection system and method |
| WO2023160272A1 (en) * | 2022-02-24 | 2023-08-31 | 北京长木谷医疗科技有限公司 | Deep learning-based hip replacement postoperative image evaluation method and system |
| CN117611525A (en) * | 2023-10-31 | 2024-02-27 | 西南交通大学 | Visual detection method and system for abrasion of pantograph slide plate |
-
2024
- 2024-03-11 CN CN202410269942.3A patent/CN117876368A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009018612A1 (en) * | 2007-08-06 | 2009-02-12 | Qr Limited | Pantograph damage and wear monitoring system |
| DE102019127493A1 (en) * | 2019-10-11 | 2021-04-15 | IFSB Institut für Schadensbewertung GmbH | Procedure for crack classification in a building structure |
| CN110853018A (en) * | 2019-11-13 | 2020-02-28 | 燕山大学 | Computer vision-based vibration table fatigue crack online detection system and detection method |
| CN112950532A (en) * | 2021-01-14 | 2021-06-11 | 成都铁安科技有限责任公司 | Train pantograph state detection method |
| WO2023160272A1 (en) * | 2022-02-24 | 2023-08-31 | 北京长木谷医疗科技有限公司 | Deep learning-based hip replacement postoperative image evaluation method and system |
| CN114897921A (en) * | 2022-05-23 | 2022-08-12 | 合肥职业技术学院 | Pantograph abrasion value and pantograph abnormity real-time detection method based on machine vision |
| CN115439406A (en) * | 2022-07-29 | 2022-12-06 | 成都唐源电气股份有限公司 | Contact rail collector shoe carbon sliding plate defect identification method |
| CN115541591A (en) * | 2022-09-23 | 2022-12-30 | 北京交通大学 | Method and system for detecting abrasion edge of carbon pantograph slider of train |
| CN115876109A (en) * | 2022-12-01 | 2023-03-31 | 西南交通大学 | Novel subway pantograph abrasion detection method based on 2D laser measurement |
| CN116164652A (en) * | 2022-12-19 | 2023-05-26 | 东莞市诺丽科技股份有限公司 | Pantograph carbon slide plate detection method and system based on three-dimensional reconstruction technology |
| CN116519787A (en) * | 2023-07-05 | 2023-08-01 | 成都盛锴科技有限公司 | Third rail power receiving boot detection system and method |
| CN117611525A (en) * | 2023-10-31 | 2024-02-27 | 西南交通大学 | Visual detection method and system for abrasion of pantograph slide plate |
Non-Patent Citations (4)
| Title |
|---|
| CANAN TASTIMUR等: "A novel method based on deep learning and Image Processing Techniques for Wearing Inspection on the Pantograph Surface", 《2021 INNOVATIONS IN INTELLIGENT SYSTEMS AND APPLICATIONS CONFERENCE》, 18 November 2021 (2021-11-18), pages 1 - 7 * |
| 吕文阁;刘少册;郑云龙;谭志忠;: "基于线结构激光的侧轨受电弓磨耗视觉测量系统开发", 机车电传动, no. 02, 10 March 2017 (2017-03-10), pages 114 - 117 * |
| 焦志阳: "基于图像处理的受电弓实时状态检测研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, no. 2022, 15 May 2022 (2022-05-15), pages 033 - 515 * |
| 莫小凡等: "基于铁路5C装置的受电弓滑板缺陷智能检测技术", 《中国铁路》, no. 2022, 15 February 2022 (2022-02-15), pages 148 - 155 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104101600B (en) | Cross Section of CC Billet testing of small cracks method | |
| CN106683076B (en) | The method of train wheel tread damage detection based on textural characteristics cluster | |
| CN108596872B (en) | Steel rail disease detection method based on Gabor wavelet and SVM | |
| CN109300125B (en) | Method for extracting pantograph slide plate image of urban rail train in complex environment | |
| CN106052575A (en) | Pantograph carbon slide plate wear online detection method based on train high speed running | |
| CN110047070B (en) | Method and system for identifying rail wear degree | |
| CN109059775B (en) | Steel rail abrasion detection method with image edge extraction step | |
| CN109269403B (en) | Contact net lead abrasion measuring method and device based on machine vision | |
| CN108177660B (en) | Steel rail abrasion detection method with laser image processing step | |
| CN108921164B (en) | Contact net locator gradient detection method based on three-dimensional point cloud segmentation | |
| CN110232682B (en) | Image-based track foreign matter detection method | |
| CN107633266B (en) | Electric locomotive contact net pantograph electric arc detection method | |
| CN104198497A (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| CN109269416B (en) | Contact net lead abrasion measuring method and device | |
| CN111968079B (en) | Three-dimensional pavement crack extraction method based on local extremum of section and segmentation sparsity | |
| CN110717900A (en) | Pantograph abrasion detection method based on improved Canny edge detection algorithm | |
| CN110186934B (en) | Axle box rubber pad crack detection method and detection device | |
| CN111127381B (en) | Non-parallel detection method for pantograph slide plate | |
| CN108759671B (en) | Dynamic detection method for contact line abrasion | |
| CN117876368A (en) | Method and system for detecting abrasion and crack of carbon slide plate of contact rail collector shoe | |
| CN109614868A (en) | Automobile tire decorative pattern graph line identifying system | |
| CN112288717A (en) | Method for detecting foreign matters on side part of motor train unit train | |
| CN116681912A (en) | Rail gauge detection method and device for railway turnout | |
| CN116071726A (en) | Road inspection system and method based on edge calculation | |
| CN114463258A (en) | Locomotive brake pad abrasion detection method based on deep learning technology |
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 |