Monorail pantograph copper-based slider thickness measurement method, storage medium and system

Abstract

The invention discloses a method, a storage medium and a system for measuring the thickness of a copper-based slider of a monorail vehicle pantograph, relates to the technical field of locomotive inspection and maintenance, and solves the problem of inaccurate measurement of the thickness of a copper-based slider of a pantograph in the prior art. The invention comprises: S1: using a camera module to capture the copper-based slider when receiving a capture signal, and using a laser rangefinder to measure corresponding distance information; S2: using an image processing module to obtain an image captured by the camera module and distance information captured by the laser rangefinder at the same time, and processing them to obtain thickness information of the copper-based slider of the pantograph; the invention combines a two-dimensional image with a laser distance measuring sensor, and uses an algorithm design to calculate the thickness of the copper-based slider of the pantograph, with high accuracy, and has guiding significance for the inspection and maintenance of the copper-based slider of the pantograph.

Description

Technical Field

[0001] The invention relates to the field of locomotive inspection and maintenance, and in particular to a method, storage medium and system for measuring the thickness of a copper-based sliding block of a pantograph of a monorail vehicle. Background Art

[0002] The pantograph slider is a current guide device for connecting the rail vehicle to the power supply system. While it continuously supplies power to the locomotive, it may also cause poor contact due to wear and tear caused by long-term operation. If it is not repaired in time, it may bring safety hazards to the normal operation of the vehicle. Therefore, it is of great significance to regularly and accurately test the thickness of the pantograph slider of the rail vehicle to ensure that the locomotive current collecting device is in normal operation.

[0003] At present, the inspection of pantograph sliders is still mainly done manually. According to the current monorail vehicle maintenance regulations, during the train inspection every three days, a special vernier caliper is used to check the slider thickness. Since the caliper is permanently worn, the scale will be blurred and the appearance will be deformed, which will cause a certain error in the measurement result. Some sliders will be replaced before their service life expires, which is likely to cause a waste of resources. Therefore, it is particularly important to calculate the thickness of the slider.

[0004] Prior art, such as the invention patent with application number "201910921337.9" and the name "Pantograph wear detection method based on improved Canny edge detection algorithm", discloses a detection method for detecting the contact state of the pantograph slide. This method uses an improved Kalman filtering method to smooth the original image, converts the filtered image into a binary image, and draws a relationship graph between the grayscale and the number of rows of each row of the binary image; then the simulated annealing algorithm and the hill climbing method are used to locate the pantograph position and separate it from the background image; then the improved Canny edge detection algorithm is used to obtain the pantograph edge contour map; finally, the minimum pixel difference between the upper and lower edges of the pantograph is calculated, and finally the pantograph wear value is calculated through camera calibration and the obtained minimum pixel difference; there is also an invention patent with application number "202110534974.8" and the name "Method for automatic calibration pixel ratio calculation of contact network geometric parameters". The invention discloses a method for automatically calibrating pixel ratio by calculating geometric parameters of contact network. The method performs feature point recognition, selects multiple fixed feature points for recognition through a recognition device, and calculates the pixel ratio according to the structural parameters given by the pantograph manufacturer or the actual distance of the feature points accurately measured manually; performs deep learning training, collects feature points identified under complex backgrounds and different pantograph models during vehicle operation, performs automatic feature point recognition training, and constructs a recognition model; performs automatic parameter correction, automatically recognizes feature points according to a set period, and calculates the pixel ratio at the same time, performs mean square error correction on the calculated pixel ratio and the previous pixel ratio, and writes the calculated pixel ratio into the system parameter table.

[0005] The existing technology has the following problems:

[0006] 1. The above methods are all applied to the carbon slider pantograph thickness detection system; however, since the carbon slider is mainly used in subway trains and the copper-based slider is mainly used in monorail trains, the carbon slider has a larger contact surface than the copper-based slider and is located in a different position. The copper-based slider is mainly used in monorail trains, is smaller in size than the carbon slider, and is located in a different position from the carbon slider. The position is more hidden than the carbon slider, and is shielded by the skirt. The detection angle and equipment installation position are more difficult. The carbon slider detection method cannot be applied to the copper-based slider, and the slider thickness data cannot be accurately calculated.

[0007] 2. A single sensor is used to predict the slider thickness. Summary of the invention

[0008] In order to solve the above-mentioned problems existing in the prior art, the present invention proposes a method, storage medium and system for measuring the thickness of the copper-based slider of the pantograph of a monorail vehicle, and proposes to solve the problem of inaccurate measurement of the thickness of the copper-based slider of the pantograph in the prior art.

[0009] A method for measuring the thickness of a copper-based slider of a monorail pantograph comprises the following steps:

[0010] S1: Using the camera module to capture the copper-based slider when receiving the capture signal, and using the laser rangefinder to measure the corresponding distance information;

[0011] S2: Use the image processing module to obtain the image captured by the camera module and the distance information collected by the laser rangefinder at the same time, and process them to obtain the thickness information of the copper-based slider of the pantograph.

[0012] Preferably, S2 comprises the following steps:

[0013] S21: Process the distance information according to the distance measurement principle of the laser rangefinder to obtain the physical distance Z from the camera module to the copper-based slider;

[0014] S22: Process the image to obtain the pixel coordinate pair of the thinnest part of the copper-based slider in the image, and then calculate the actual thickness of the thinnest part of the copper-based slider in combination with the physical distance Z obtained in S21.

[0015] Preferably, the S22 comprises the following steps:

[0016] S221: using guided filtering to perform noise reduction on the image;

[0017] S222: Perform superpixel segmentation on the denoised image using the SLIC algorithm;

[0018] S223: performing regional merging on the result of superpixel segmentation in S222 to obtain a mask image of the copper-based slider;

[0019] S224: traverse the mask image to obtain the pixel coordinate pair (u1, v1) and (u2, v2) of the thinnest part of the copper-based slider;

[0020] S225: Restore the pixel coordinate pairs (u1, v1) and (u2, v2) to spatial coordinates in combination with the physical distance z from the camera module to the copper-based slider, and finally calculate the actual thickness of the copper-based slider at its thinnest point. The calculation formula is as follows:

[0021]

[0022]

[0023]

[0024] Where: Z represents the physical distance from the camera module to the copper-based slider; H represents the actual thickness of the copper-based slider at its thinnest point; f represents the camera module parameters.

[0025] Preferably, the laser rangefinder in S1 is a sensor capable of real-time measurement. After being analyzed by a host computer, the capture signal triggers the laser rangefinder sensor to measure distance through serial communication, and at the same time, the camera is controlled to capture images through software triggering.

[0026] Preferably, the camera module in S1 continuously captures multiple images during the process of capturing the copper-based slider, and all the captured images are processed by S221-S223 to obtain corresponding mask images for judgment, and the mask image with the center of the area located at the center of the image is used as the optimal image, and the optimal image is processed by S224-S225 to obtain the true thickness of the copper-based slider at the thinnest point.

[0027] Preferably, the capture signal generation process in S1 is: using a 3D camera to take pictures of the specified position and continuously return the collected point cloud data, and judging whether the slider has entered the specified position based on the point cloud data, if it is judged that the slider has entered the specified position, a corresponding capture signal is generated.

[0028] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the processor executes the steps of a method for measuring the thickness of a copper-based slider of a monorail pantograph.

[0029] A monorail pantograph copper base slider thickness measurement system comprises a camera module, a laser rangefinder and an image processing module; the camera module is used to capture the pantograph copper base block after receiving a capture signal; the laser rangefinder is used to measure corresponding distance information while the camera module is capturing; the image processing module is used to process the image captured by the camera module and calculate the physical distance between the camera module and the pantograph copper base block when capturing according to the distance information, and finally calculate the true thickness of the thinnest part of the copper base block in combination with the processed image and the physical distance.

[0030] The beneficial effects of the present invention include:

[0031] 1. The camera and laser rangefinder are used to detect the thickness of the copper-based slider of the pantograph. The equipment is simple and easy to use. During the specific operation, the capture signal is analyzed by the host computer and then the laser rangefinder sensor is triggered to measure the distance through the serial communication. At the same time, the camera is controlled to capture the image through the software trigger, so that the camera module and the laser rangefinder are triggered at the same time to avoid the image and distance information not corresponding to each other due to the asynchrony between the two, and ensure the synchronization of image information and distance information.

[0032] 2. By combining the 2D image with the laser ranging sensor and using an algorithm to calculate the thickness of the pantograph copper-based slider, the accuracy is high and it has guiding significance for the maintenance of the pantograph copper-based slider. In the specific calculation process, the optimal image corresponding to the most reliable distance information is selected according to the position of the copper-based slider in the image to calculate the true thickness of the copper-based slider at the thinnest point, so as to ensure the accuracy of the measurement to the greatest extent possible.

[0033] 3. The present invention can be combined with the measurement system in the prior art to realize the automated measurement of the copper-based slider of the pantograph of a monorail vehicle, thereby freeing up manpower and improving the detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a flow chart of the method for measuring the thickness of the copper-based slider of the monorail pantograph involved in Example 1.

[0035] Figure 2 This is a schematic diagram of the principle of obtaining distance by the oblique laser ranging sensor involved in Example 1.

[0036] Figure 3 This is a 2D image of the pantograph copper-based slider after guided filtering processing involved in Example 1.

[0037] Figure 4 This is a 2D image of the pantograph copper-based slider after superpixel segmentation processing involved in Example 1.

[0038] Figure 5 This is a mask diagram of the copper-based slider of the pantograph involved in Example 1.

[0039] Figure 6 This is a comparison chart of the measurement error results of the present application and the prior art involved in Example 1. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0041] Example 1

[0042] The following is combined with Figure 1 The specific embodiments of the present invention are described in detail;

[0043] The method for measuring the thickness of the copper-based slider of the monorail pantograph comprises the following steps:

[0044] S1: Using the camera module to capture the copper-based slider when receiving the capture signal, and using the laser rangefinder to measure the corresponding distance information;

[0045] The capture signal generation process is as follows: using a 3D camera to take pictures of a designated position and continuously returning the collected point cloud data, and judging whether the slider has entered the designated position according to the point cloud data, and if it is judged that the slider has entered the designated position, a capture signal is generated accordingly;

[0046] After being analyzed by the host computer, the capture signal is sent to the laser sensor via RS485 communication as a trigger instruction to trigger the laser ranging sensor to measure the distance. At the same time, the camera is controlled to capture the image through the gigabit network through a soft trigger instruction, so that the camera module and the laser rangefinder are triggered at the same time, avoiding the inconsistency between the two and the inability to correspond to the image and distance information.

[0047] S2: Use the image processing module to obtain the image captured by the camera module and the distance information collected by the laser rangefinder at the same time, and process them to obtain the thickness information of the copper-based slider of the pantograph.

[0048] S21: Process the distance information according to the distance measurement principle of the laser rangefinder to obtain the physical distance Z from the camera module to the copper-based slider; Specifically: Since the camera module is installed on the track side in the direction of the oncoming vehicle, if it collects the image and distance data of the copper-based slider of the monorail pantograph, it needs to have a certain elevation angle. Therefore, the laser distance measurement sensor of this embodiment adopts an oblique laser distance measurement sensor. The principle of the oblique laser distance measurement sensor to obtain the distance is as follows: Figure 2 As shown. Figure 2 Knowing that ΔABO~ΔBDF, then Let DF be X, EF be x, which represents the imaging distance of the light spot reflected to the CCD. At this time:

[0049] DE=Xx

[0050] For ΔBDF, X = f·cotα; so DE = fcotα-x. Based on the similarity of the triangles, solve AO.

[0051]

[0052] AO is the distance information measured in S1. Based on AO, OC, the physical distance Z from the camera module to the copper-based slider, can be inferred.

[0053] S22: Process the image to obtain the pixel coordinate pair of the thinnest part of the copper-based slider in the image, and then calculate the real thickness of the thinnest part of the copper-based slider in combination with the physical distance Z obtained in S21; specifically: the camera module takes ten consecutive shots when capturing, and the interval between the ten consecutive shots is 50ms. While shooting, the laser sensor is triggered to measure the distance through RS485 communication; after the ten consecutive captured images are processed by steps S221-S223, the mask image of each image is determined, and the mask image in which the center of the copper-based slider area is closest to the center of the image is selected as the optimal image, and combined with its corresponding physical distance Z, the real thickness of the thinnest part of the copper-based slider is obtained through steps S224-S225; the purpose of selecting the optimal image is to ensure that the distance information during calculation is the distance from the oblique laser ranging sensor to the center of the copper-based slider, so as to ensure the accuracy of the physical distance Z corresponding to the image, and finally obtain the most accurate real thickness of the thinnest part of the copper-based slider as much as possible;

[0054] S221: Use guided filtering to reduce noise for all. The processing effect is as follows: Figure 3 As shown; the calculation formula is as follows:

[0055]

[0056] Where q, I, p represent the output image, guide image and input image respectively, i, j represent the index of the pixel in the image respectively; the specific workflow is as follows:

[0057] Input: input image p; guide image I; search radius r; regularization coefficient ε.

[0058] Output: Output image q.

[0059] 1:meanI=f mean (I)

[0060] meanp=f mean (p)

[0061] corrI=f mean (I.*I)

[0062] corrIp=f mean (I.*p)

[0063] 2:varI=corrI-meanI.*meanI

[0064] covIp=corrIp-meanI.*meanp

[0065] 3:a=covIp. / (varI+ε)

[0066] b=meanp-a.*meanI

[0067] 4:mean a =f mean (a)

[0068] mean b =f mean (b)

[0069] 5:q=mean a .*I+mean b

[0070] * Among them, f mean (·) is mean filtering.

[0071] S222: Use the SLIC algorithm to perform superpixel segmentation on the denoised image. The processing effect is as follows: Figure 4 As shown in the figure, the SLIC algorithm converts the color image into a 5-dimensional feature vector in CIELAB color space and XY coordinates, then constructs a distance metric for the 5-dimensional feature vector and performs local clustering of image pixels. The algorithm can generate compact and approximately uniform superpixels, and has a high comprehensive evaluation in terms of computing speed, object contour preservation, and superpixel shape, which meets the segmentation requirements of the copper-based slider of the pantograph; specifically:

[0072] a. Initialize seed points (cluster centers): Distribute seed points evenly in the image according to the set number of superpixels.

[0073] b. Reselect the seed point in the n*n neighborhood of the seed point (generally n=3). The specific method is: calculate the gradient values ​​of all pixels in the neighborhood and move the seed point to the place with the smallest gradient in the neighborhood.

[0074] c. Assign a class label to each pixel in the neighborhood around each seed point (i.e., which cluster center it belongs to).

[0075] d. Distance measurement. Including color distance and spatial distance. For each searched pixel, calculate the distance between it and the seed point. The distance calculation method is as follows:

[0076]

[0077]

[0078]

[0079] Among them, dc represents the color distance, ds represents the spatial distance, and Ns is the maximum spatial distance within the class, which is defined as Ns=S=sqrt(N / K).

[0080] e. Iterative optimization, the number of iterations is set to 10.

[0081] f. Enhance connectivity.

[0082] S223: The result of superpixel segmentation in S222 is subjected to regional merging to obtain a mask image of the copper-based slider, such as Figure 5 As shown;

[0083] S224: traverse the mask image to obtain the pixel coordinate pair (u1, v1) and (u2, v2) of the thinnest part of the copper-based slider;

[0084] S225: Restore the pixel coordinate pairs (u1, v1) and (u2, v2) to spatial coordinates in combination with the physical distance z from the camera module to the copper-based slider, and finally calculate the actual thickness of the copper-based slider at its thinnest point. The calculation formula is as follows:

[0085]

[0086]

[0087]

[0088] Where: Z represents the physical distance from the camera module to the copper-based slider; H represents the actual thickness of the copper-based slider at its thinnest point; f represents the camera module parameters.

[0089] After comparative tests and test results, Figure 6As shown, it can be seen that there are 90 data with an absolute value of the difference between the measurement result of the present application and the manual measurement result within 0.5 mm, among which the absolute value of the difference between the 20 arcing data and the manual measurement is within 0.5 mm; there are 77 data with an absolute value of the difference between the measurement result of the prior art and the manual measurement result within 0.5 mm, among which the absolute value of the difference between the 20 arcing data and the manual measurement is within 0.5 mm only 10. It can be concluded that the measurement result of the present embodiment is better than the measurement result of the prior art.

[0090] Note: The prior art refers to the copper-based slider thickness detection method mentioned in the pantograph copper-based slider detection system and method for monorail vehicles disclosed in Patent No. CN115371572A.

[0091] Example 2

[0092] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor executes the steps of a method for measuring the thickness of a copper-based slider of a monorail pantograph.

[0093] Example 3

[0094] A monorail pantograph copper base slider thickness measurement system comprises a camera module, a laser rangefinder and an image processing module; the camera module is used to capture the pantograph copper base block after receiving a capture signal; the laser rangefinder is used to measure corresponding distance information while the camera module is capturing; the image processing module is used to process the image captured by the camera module and calculate the physical distance between the camera module and the pantograph copper base block when capturing according to the distance information, and finally calculate the true thickness of the thinnest part of the copper base block in combination with the processed image and the physical distance.

[0095] The above-mentioned embodiments only express the specific implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the protection scope of the present application. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the technical solution concept of the present application, and these all belong to the protection scope of the present application.

Claims

1. A method for measuring the thickness of a copper-based slider of a monorail pantograph, characterized in that: The following steps are involved: S1: Using the camera module to capture the copper-based slider when receiving the capture signal, and using the laser rangefinder to measure the corresponding distance information; The laser rangefinder is a sensor that can measure in real time. After being analyzed by the host computer, the captured signal triggers the laser rangefinder sensor to measure the distance through serial communication, and at the same time, the camera is triggered to capture the image through software triggering; The camera module is installed on the rail side in the direction of the oncoming vehicle. The laser rangefinder uses an oblique laser rangefinder sensor. According to the similarity of triangles, the physical distance Z from the camera module to the copper-based slider is obtained based on the corresponding distance information measured by the laser rangefinder. S2: using the image processing module to obtain the image captured by the camera module and the distance information collected by the laser rangefinder at the same time, and process them to obtain the thickness information of the copper-based slider of the pantograph; S21: Process the distance information according to the distance measurement principle of the laser rangefinder to obtain the physical distance Z from the camera module to the copper-based slider; S22: Process the image to obtain the pixel coordinate pair of the thinnest part of the copper-based slider in the image, and then calculate the actual thickness of the thinnest part of the copper-based slider in combination with the physical distance Z obtained in S21; The S22 comprises the following steps: S221: using guided filtering to perform noise reduction on the image; S222: Perform superpixel segmentation on the denoised image using the SLIC algorithm; S223: performing regional merging on the result of superpixel segmentation in S222 to obtain a mask image of the copper-based slider; S224: traverse the mask image to obtain the pixel coordinate pair (u1, v1) and (u2, v2) of the thinnest part of the copper-based slider; S225: Restore the pixel coordinate pairs (u1, v1) and (u2, v2) to spatial coordinates in combination with the physical distance z from the camera module to the copper-based slider, and finally calculate the actual thickness of the copper-based slider at its thinnest point. The calculation formula is as follows: Where: Z represents the physical distance from the camera module to the copper-based slider; H represents the actual thickness of the copper-based slider at its thinnest point; f represents the camera module parameters.

2. The method for measuring the thickness of the copper-based slider of the monorail pantograph according to claim 1 is characterized in that: The camera module in S1 continuously captures multiple images during the process of capturing the copper-based slider, and all the captured images are processed by S221-S223 to obtain the corresponding mask images for judgment, and the mask image with the center of the area located at the center of the image is used as the optimal image, and the optimal image is processed by S224-S225 to obtain the actual thickness of the copper-based slider at the thinnest point.

3. The method for measuring the thickness of the copper-based slider of the monorail pantograph according to claim 1 is characterized in that: The capture signal generation process in S1 is: using a 3D camera to take pictures of the specified position and continuously return the collected point cloud data, and judging whether the slider has entered the specified position based on the point cloud data, if it is judged that the slider has entered the specified position, a corresponding capture signal is generated.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 3.

5. Monorail pantograph copper-based slider thickness measurement system, characterized in that: A method for measuring the thickness of a copper-based slider of a monorail pantograph used to implement any one of claims 1 to 3, comprising a camera module, a laser rangefinder and an image processing module; the camera module is used to capture a copper-based block of the pantograph after receiving a capture signal; the laser rangefinder is used to measure corresponding distance information while the camera module is capturing; the image processing module is used to process the image captured by the camera module and calculate the physical distance between the camera module and the copper-based block of the pantograph when capturing based on the distance information, and finally calculate the actual thickness of the copper-based block at the thinnest part in combination with the processed image and the physical distance.

Images