A dynamic recognition and measurement method and system for the contact point of a large iron flexible pantograph-catenary

Abstract

A dynamic recognition and measurement method and system for the contact point of a large iron flexible pantograph-catenary system, which is implemented by using an overall architecture of two processes. The first process is located at the vehicle-mounted end, where an infrared camera is used to obtain images, and gray-scale matching NCC and Hough line detection are used to identify the pantograph-catenary contact point, and then real-time and rapid analysis is carried out to save the data of possible over-limit problems. The second process is located at the main control device on the ground end, which conducts secondary analysis on the abnormal video to obtain the final abnormal warning information. Among them, the second process is implemented by using object detection in deep learning, and the model parameters of the pantograph and the contact point are obtained by training respectively using the alexnet model framework for forward inference. It is carried out in two steps. First, the pantograph area is identified, and then after longitudinally expanding a part of the area according to the result of the first step, object detection is carried out on the cross-like intersection of the pantograph-catenary contact in the area. The invention has good real-time performance, high accuracy in abnormal detection, strong practicability, and has strong popularization significance.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit, and in particular to a method and system for dynamically identifying and measuring the contact points of the flexible pantograph-catenary system of main railway lines. Background Art

[0002] The pantograph and catenary are the physical components of the pantograph-catenary system of high-speed railways, and are the mechanisms for trains to obtain electrical energy from the catenary. The pantograph-catenary directly affects the safe operation of high-speed electrified railways, and its good service performance is the basic condition for ensuring the reliable and safe operation of high-speed railways; and the identification of the geometric parameters of the pantograph is an important part of judging the safety performance of the pantograph-catenary.

[0003] Currently, the commonly used technical method for detecting pantographs is to combine laser ranging and angular displacement sensor devices, obtain measurement data and perform data preprocessing on it to reduce the interference of external factors, and finally obtain the contact wire height value and the offset value through a conversion equation. However, laser scanning mainly detects and transmits data through signals, and is affected by the low electromagnetic waves carried by the train during use, resulting in errors in some data, which will affect the results of laser radar scanning and the accuracy is poor. Summary of the Invention

[0004] Based on this, it is necessary to provide a method and system for dynamically identifying and measuring the contact points of the flexible pantograph-catenary system of main railway lines in view of the deficiencies in the prior art.

[0005] A method for dynamically identifying and measuring the contact points of the flexible pantograph-catenary system of main railway lines includes the following steps:

[0006] Step S0: Calibrate the infrared camera in the pantograph lifting plane to obtain a calibration file; obtain a mapping matrix composed of three parts: rotation, non-uniform scaling, and translation through the mapping relationship between the actual points and pixel points collected;

[0007]

[0008] Wherein, R: rotation matrix, T: translation vector, Sx, Sy: scaling size;

[0009] Step S1: Use an infrared camera to collect an image of the cooperation between the pantograph and the catenary;

[0010] Step S2: Use NCC gray template matching to obtain the position of the pantograph;

[0011] Step S3: Combine the position of the pantograph to narrow the ROI (region of interest) to the pantograph and the upper region, and then use the Hough transform line extraction to extract the catenary;

[0012] Step S4: Calculate the contact point between the pantograph and the contact network, obtain the accurate position area of ​​the pantograph through the grayscale feature, extract the uppermost contour line of the pantograph and the contact line, solve the intersection point by simultaneously solving the two straight line equations, and obtain the contact point position coordinates;

[0013]

[0014] Step S5: filtering the result points according to the results retained by the previous multiple frames to eliminate abnormal points;

[0015] Step S6: Map the result points and transform them into real coordinates by matrix transformation, and obtain the current height guide value and pull-out value, as shown below;

[0016]

[0017] Among them, (Px, Py): image coordinate point; (Qx, Qy): result coordinate point; x: pull out, y: guide height;

[0018] Step S7: judging whether it is abnormal, if the above-obtained conductance value and pull-out value are abnormal values, saving the video information and transmitting it to the main control device;

[0019] Step S8: the main control device identifies abnormal videos;

[0020] Step S9: the main control device performs pantograph-catenary contact point identification and detection to obtain the contact point coordinates;

[0021] Step S10: Determine whether the contact point is abnormal or not according to the threshold setting.

[0022] Furthermore, the calibration file is in the lifting plane where the pantograph is located, with the center of the pantograph as the 0 point, and a ruler is used to collect plane points for infrared camera calibration.

[0023] Furthermore, in step S5, prediction and filtering are performed according to the distribution characteristics of the installation position of the flexible contact network itself, the rules of the pull-out value and the height conduction value.

[0024] Furthermore, the implementation of the filtering algorithm uses the results of the previous multiple frames of data to form a real-time updated dynamic array, uses the least squares linear fitting method to obtain the regression equation, and judges whether the current frame result is within the movement trend range of the contact point to define the outliers. For outliers, the current trend prediction value is used to replace the outliers.

[0025] Furthermore, in steps S8 and S9, a deep learning method is used to identify and detect the pantograph.

[0026] A dynamic recognition and measurement system for the contact point of the large - iron flexible pantograph - catenary, which includes an on - vehicle detection system and a ground analysis system. The on - vehicle detection system includes an image acquisition module, an image processing module, a calculation and analysis module, a judgment module, a data storage module, and a data transmission module; the ground analysis system includes a deep learning module, a data determination module, and a database; the image acquisition module acquires images, and the image processing module performs gray - scale matching NCC and Hough line detection on the images to identify the pantograph - catenary contact points; the calculation and analysis module calculates the contact points between the pantograph and the catenary, filters the structures retained in multiple frames, and performs mapping transformation to obtain the current sag value and the stagger value; the judgment module compares and analyzes the analysis value with the standard value, and stores the data information in the data storage module; while the abnormal data information is sent to the ground analysis system through the data transmission module for secondary analysis; the ground analysis system stores the received information in the database, and performs identification and detection through the deep learning module, and the data determination module compares and analyzes the data information after detection and issues an alarm for confirmed abnormalities.

[0027] Further, the image acquisition module is an infrared camera, and the infrared camera is arranged on the top of the vehicle.

[0028] In summary, the recognition and measurement method of the present invention is implemented by adopting the overall architecture of two processes. The first process is located at the on - vehicle end. An infrared camera is used to acquire images, and gray - scale matching NCC and Hough line detection are used to identify the pantograph - catenary contact points, and then real - time and rapid analysis is carried out to save the possible over - limit problem data. The second process is located at the main control device at the ground end, which performs secondary analysis on the abnormal video to obtain the final abnormal alarm information. Among them, the second process is implemented by using object detection in deep learning. The model parameters of the pantograph and the contact point are obtained by training respectively using the alexnet model framework for forward inference. It is carried out in two steps. The first step is to identify the pantograph area, and the second step is to perform object detection on the cross - like intersection of the pantograph - catenary contact in the area after longitudinally expanding a partial area according to the result of the first step. This method can ensure its real - time performance by combining the rapid response of conventional image algorithms, and adopts the combination of two processes. The strategy of combining deep learning at the main control device is used for secondary analysis to ensure the accuracy of abnormal detection. It has strong practicability and has strong promotion significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is one of the schematic diagrams of the calibration file in step S0 of a method for dynamically recognizing and measuring the contact point of the large - iron flexible pantograph - catenary according to the present invention;

[0030] Figure 2 It is one of the schematic diagrams of the NCC matching result in step S2;

[0031] Figure 3 It is one of the schematic diagrams of the result after shrinking the ROI in S3;

[0032] Figure 4 One of the schematic diagrams of the Hough line extraction result in S3;

[0033] Figure 5 One of the diagrams related to the algorithm processing result in S6;

[0034] Figure 6 One of the schematic diagrams of the pantograph recognition result in S8;

[0035] Figure 7 One of the schematic diagrams of the cross recognition result of the contact point type in S9. Detailed implementation manner

[0036] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0037] As Figure 1 shown, it is a dynamic recognition and measurement method for the contact point of the large-iron flexible pantograph-catenary provided by the present invention, which specifically includes the following steps:

[0038] Step S0: Calibrate the infrared camera in the pantograph lifting plane to obtain a calibration file (as Figure 1 shown, which is one of the calibration files, and this table represents the mapping conversion relationship between the points on the image and the actual plane points, and the values are determined according to the actual situation); the calibration file is to calibrate the infrared camera by collecting plane points with a scale in the pantograph lifting plane with the center of the pantograph as the 0 point, and obtain a mapping matrix composed of three parts: rotation, non-uniform scaling, and translation through the mapping relationship between the collected actual points and pixel points.

[0039]

[0040] Among them, R: rotation matrix, T: translation vector, Sx, Sy: scaling size.

[0041] Step S1: Collect the cooperative image of the pantograph and the catenary; in this embodiment, an infrared camera is set on the train roof, and the infrared camera is used to obtain the image of the pantograph and the catenary. The infrared camera can avoid complex background interference to a certain extent by imaging with temperature, and due to the current transmission between the catenary and the pantograph, the thermal effect of the current will cause the temperature to rise, making the characteristics of the pantograph and the catenary more obvious to a certain extent.

[0042] Step S2: Use NCC gray template matching to obtain the position of the pantograph (as Figure 2 shown); NCC gray matching can avoid the influence of light and ensure the adaptability of the matching algorithm.

[0043] Step S3: Reduce the ROI (target area) to the pantograph and the area above it (such as Figure 3 As shown in the figure), and then use the Hough transform line to extract the contact network (as shown in the figure). Figure 4 As shown). Hough detection is performed after grayscale matching detection, which can ensure that only the area above the pantograph is detected to avoid background interference. For multi-line situations, the contact network position will not change suddenly and has a zigzag feature, so that an effective contact network working branch (the part in contact with the pantograph) can be obtained.

[0044] Step S4: Calculate the contact point between the pantograph and the contact network, obtain the accurate position area of ​​the pantograph through the grayscale feature, extract the top contour line of the pantograph and the contact line, solve the intersection point by solving the two straight line equations, and obtain the contact point position coordinates; where Y1: contact network straight line equation. Y2: pantograph top straight line equation.

[0045]

[0046] Step S5: filter the result points according to the results retained by the previous multiple frames to eliminate abnormal points; the filtering process is based on the flexible contact network itself to ensure the uniform wear of the carbon slide plate installation position distribution characteristics, the pull-out value presents a "Z" shape, and the guide height value presents a small range of wave-shaped law, to predict and filter; the implementation of the filtering algorithm uses the results of the first 40 frames of data to form a real-time update dynamic array, and uses the least squares linear fitting method to obtain the regression equation. The current frame result is judged whether it is within the range of the movement trend of the contact point to define the abnormal value, and the current trend prediction value is used to replace the abnormal value. It can be understood that in other embodiments, more or less than 40 frames of data can also be used according to actual needs; here, the specific number is not limited.

[0047] Step S6: Mapping transformation is performed on the result point of step S5, and matrix transformation is performed to obtain the actual coordinates, and the current guide height value and pull-out value are obtained, as shown below;

[0048]

[0049] Among them, (Px, Py): image coordinate point; (Qx, Qy): result coordinate point; x: pull out, y: guide height.

[0050] Step S7: Determine whether it is abnormal. If the above-obtained conductance value and pull-out value are abnormal values, save the video information and transmit it to the main control device; the main control device can be a computer, a human-computer interaction machine, etc.;

[0051] Step S8: Identify and detect abnormal videos (such as Figure 5As shown in the figure, a control system is provided on the main control device, and the control system identifies the pantograph and catenary in the abnormal video based on deep learning;

[0052] Step S9: Perform pantograph-catenary contact point identification and detection to obtain contact point coordinates; in this embodiment, deep learning-based cross identification is used to identify the contact point, as Figure 6 shown in the figure, where the small rectangle indicates the identification position.

[0053] Step S10: Determine whether the contact point exceeds the limit according to the threshold setting; compare and analyze the obtained contact point coordinates with the standard coordinate range in the database to determine whether the contact point exceeds the limit abnormally.

[0054] In addition, the present invention also discloses a dynamic identification and measurement system for flexible pantograph-catenary contact points of large railways, and this system works using the above-mentioned dynamic identification and measurement method for flexible pantograph-catenary contact points of large railways. A dynamic identification and measurement system for flexible pantograph-catenary contact points of large railways includes a vehicle-mounted detection system and a ground analysis system. The vehicle-mounted detection system includes an image acquisition module, an image processing module, a calculation and analysis module, a judgment module, a data storage module, and a data transmission module; the ground analysis system includes a deep learning module, a data determination module, and a database; the image acquisition module acquires images, and the image processing module performs gray-scale matching NCC and Hough line detection on the images to identify the pantograph-catenary contact points; the calculation and analysis module calculates the contact points of the pantograph and the catenary, filters the structures retained in multiple frames, and performs mapping transformation to obtain the current lead height value and pull-out value; the judgment module compares and analyzes the analysis value with the standard value and stores the data information in the data storage module; and the abnormal data information is sent to the ground analysis system through the data transmission module for secondary analysis; the ground analysis system stores the received information in the database, performs identification and detection through the deep learning module, and the data determination module compares and analyzes the detected data information and issues an alarm for confirmed abnormalities.

[0055] Further, the image acquisition module is an infrared camera, and the infrared camera is arranged on the top of the vehicle.

[0056] In summary, the identification and measurement method of the present invention is implemented by adopting an overall architecture of two processes. The first process is located at the vehicle-mounted end, where an infrared camera is used to acquire images, and gray-scale matching NCC and Hough line detection are used to identify the pantograph-catenary contact point, and then real-time and rapid analysis is carried out to save the data of possible over-limit problems. The second process is located at the main control device on the ground end, which performs secondary analysis on the abnormal video to obtain the final abnormal warning information. Among them, the second process is implemented by using object detection in deep learning, and the model parameters of the pantograph and the contact point are obtained by training respectively using the alexnet model framework for forward inference. It is carried out in two steps. The first step is to identify the pantograph area, and the second step is to perform object detection on the cross-shaped intersection of the pantograph-catenary contact in the area after longitudinally expanding a part of the area according to the result of the first step. This method can ensure its real-time performance by combining the fast response of conventional image algorithms. By combining the two processes and adopting the strategy of combining deep learning at the main control device for secondary analysis, the accuracy of abnormal detection is guaranteed. It has strong practicability and has strong popularization significance.

[0057] The above-described embodiments merely represent one implementation manner of the present invention, and the description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the appended claims.

Claims

1. A method for dynamic identification and measurement of the contact point of a large iron flexible bow-net, characterized in that: The method comprises the following steps: providing a measurement system, wherein the measurement system comprises a vehicle-mounted detection system and a ground analysis system, wherein the vehicle-mounted detection system comprises an image acquisition module, an image processing module, a calculation and analysis module, a judgment module, a data storage module, and a data transmission module, wherein the image processing module comprises an infrared camera; the ground analysis system comprises a deep learning module, a data judgment module, and a database, and the ground analysis system is arranged on a main control device; Step S0, calibrate the infrared camera on the pantograph lifting plane to obtain a calibration file; the calibration file is in the lifting plane where the pantograph is located, with the pantograph center as the 0 point, and use a ruler to collect plane points for infrared camera calibration, and obtain a mapping matrix consisting of three parts: rotation, non-uniform scaling and translation through the mapping relationship between the actual points collected and the pixel points; Among them, R: rotation matrix, T: translation vector, Sx, Sy: scaling size; Step S1: using an infrared camera to collect images of the coordination between the pantograph and the contact network; Step S2: the image processing module performs grayscale matching on the image and uses NCC grayscale template matching to obtain the pantograph position; Step S3: Reduce the ROI to the pantograph and the area above it in combination with the pantograph position, and then use Hough transform to extract the contact network; Step S4: Calculate the contact point between the pantograph and the contact network, obtain the accurate position area of ​​the pantograph through the grayscale feature, extract the uppermost contour line of the pantograph and the contact line, solve the intersection point by simultaneously solving the two straight line equations, and obtain the contact point position coordinates; Step S5: filtering the result points according to the results retained by the previous multiple frames to eliminate abnormal points; Step S6: Map the result points and transform them into real coordinates by matrix transformation, and obtain the current height guide value and pull-out value, as shown below; Among them, (Px, Py): image coordinate point; (Qx, Qy): result coordinate point; x: pull out, y: guide height; Step S7: Determine whether it is abnormal, if the above-obtained high value, pull-out value is an abnormal value, the video information is saved and transmitted to the main control device; Step S8: the main control device identifies the abnormal video; the main control device is provided with a control system, which identifies the pantograph and the contact network in the abnormal video based on deep learning; Step S9: the main control device performs pantograph-catenary contact point identification and detection, uses a deep learning cross-type method to identify the contact point, and obtains the contact point coordinates; Step S10: Determine whether the contact point is abnormal or not according to the threshold setting.

2. A method for dynamic identification and measurement of large iron flexible bow-net contact points as claimed in claim 1, characterized in that: In step S5, prediction and filtering are performed based on the distribution characteristics of the installation position of the flexible contact network itself, the rules of the pull-out value and the height conduction value.

3. A method for dynamic identification and measurement of large iron flexible bow-net contact points as claimed in claim 2, characterized in that: The implementation of the filtering algorithm uses the results of the previous multiple frames of data to form a real-time updated dynamic array, uses the least squares linear fitting method to obtain the regression equation, and judges whether the current frame result is within the movement trend range of the contact point to define the outliers. For outliers, the current trend prediction value is used to replace the outliers.

4. A system for dynamic identification and measurement of a large iron flexible bow-net contact point, used to implement a method for dynamic identification and measurement of a large iron flexible bow-net contact point as claimed in any one of claims 1 to 3, characterized in that: It includes an on-board detection system and a ground analysis system. The on-board detection system includes an image acquisition module, an image processing module, a calculation and analysis module, a judgment module, a data storage module, and a data transmission module; the ground analysis system includes a deep learning module, a data judgment module, and a database; the image acquisition module acquires images, and the image processing module performs grayscale matching NCC and Hough line detection on the images to identify the contact points between the pantograph and the contact network; the calculation and analysis module calculates the contact points between the pantograph and the contact network, and performs filtering and mapping transformation on the structures retained in multiple frames to obtain the current conduction height value and the pull-out value; the judgment module compares and analyzes the analysis value with the standard value, and stores the data information in the data storage module; The abnormal data information is sent to the ground analysis system through the data transmission module for secondary analysis; the ground analysis system stores the received information in the database, and performs identification and detection through the deep learning module, and the data judgment module compares and analyzes the data information after detection and issues an alarm for confirmed abnormalities.

5. A dynamic identification and measurement system for large iron flexible bow-net contact points as claimed in claim 4, characterized in that: The image acquisition module is an infrared camera, and the infrared camera is arranged on the top of the vehicle.

Images