A pantograph copper-based slider detection system and method for monorail vehicles

Abstract

The application discloses a pantograph copper-based sliding block detection system and method for a monorail vehicle. The pantograph copper-based sliding block detection system comprises a sliding block identity information obtaining unit, a sliding block image information obtaining unit, a sliding block thickness data measuring unit and a sliding block running state prediction unit. The sliding block identity information obtaining unit receives and outputs sliding block identity information according to a passing signal triggering vehicle number identification and sliding block positioning. The sliding block image information obtaining unit triggers the sliding block image information obtaining unit to capture the sliding block and acquire sliding block image information when the sliding block identity information obtaining unit detects the sliding block. The sliding block thickness data measuring unit detects the sliding block image information to obtain a sliding block contour, processes the sliding block contour through a sliding block thickness measuring algorithm, and generates a copper-based sliding block detection work order according to the sliding block thickness data and the sliding block identity information after obtaining the sliding block thickness data. The sliding block running state prediction unit predicts the sliding block thickness through a feature processing algorithm according to the copper-based sliding block detection work order data to obtain a sliding block running state prediction result.

Description

Technical Field

[0001] This invention relates to the field of pantograph slider detection technology for rail vehicles, and more particularly to a pantograph copper-based slider detection system and method for monorail vehicles. Background Technology

[0002] As a current-carrying device in the power supply system of rail vehicles, the pantograph slider continuously supplies power to the locomotive. However, due to wear and tear from long-term operation, poor contact can occur. If maintenance is not timely, it may pose a safety hazard to the normal operation of the vehicle. Therefore, it is of great significance to conduct regular inspections of the pantograph slider of rail vehicles to ensure that the locomotive's current-collecting device is in normal operating condition.

[0003] Currently, the inspection of pantograph sliders is still mainly done manually. According to current monorail vehicle maintenance procedures, the slider thickness is measured using specialized vernier calipers during the three-day train inspection. This method is inefficient, relies heavily on the experience of maintenance personnel, and is prone to misjudgments. Furthermore, the following problems exist: the inspection device is mounted on the pantograph, making it costly to monitor the pantograph contact status across the entire line; the remaining thickness of the pantograph slider has the greatest impact on the pantograph contact status, therefore strengthening the inspection of the remaining slider thickness is crucial for ensuring the normal condition of the pantographs on trains in operation; the equipment is mounted on steel beams, directly contacting the overhead contact line, which is detrimental to equipment maintenance; and the image acquisition equipment is located behind the overhead contact line, and due to the obstruction of the contact line, the combined image still cannot fully display the true image of the slider and the directly contacting part of the slider. Summary of the Invention

[0004] This application provides a pantograph copper-based slider detection system and method for monorail vehicles, which at least solves the problems of low detection accuracy and efficiency, high detection cost, inconvenient maintenance of detection equipment due to unreasonable installation location, and unreasonable image acquisition equipment installation location design, resulting in the combined image not being able to fully display the true image of the slider and the directly contacting part.

[0005] This invention provides a pantograph copper-based slider detection system for monorail vehicles, comprising:

[0006] Slider identity information acquisition unit: After receiving and triggering vehicle number recognition and slider positioning based on the vehicle passing signal, it outputs slider identity information;

[0007] Slider image information acquisition unit: When the slider identity information acquisition unit detects the slider, it triggers the slider image information acquisition unit to capture the slider and acquire slider image information;

[0008] Slider thickness data measurement unit: detects the slider image information to obtain the slider outline, processes the slider outline through a slider thickness measurement algorithm to obtain slider thickness data, and generates a copper-based slider inspection work order based on the slider thickness data and the slider identity information;

[0009] Slider running status prediction unit: Based on the copper-based slider inspection work order data, the slider thickness is predicted through feature processing algorithms to obtain the slider running status prediction result.

[0010] The aforementioned pantograph copper-based slider detection system, wherein the slider identification information acquisition unit includes:

[0011] The vehicle receiving radar module collects and outputs the vehicle passing signal;

[0012] The image acquisition and control module outputs vehicle number recognition instructions and slider positioning instructions based on the vehicle passing signal;

[0013] The vehicle number recognition module identifies the vehicle number according to the vehicle number recognition instruction to obtain the vehicle number information;

[0014] The slider positioning module positions the slider according to the slider positioning command and outputs trigger sequence data and capture command.

[0015] The aforementioned pantograph copper-based slider detection system, wherein the slider identification information acquisition unit further includes:

[0016] Identity information integration module: integrates the vehicle number information and the trigger sequence data to obtain the slider identity information.

[0017] The aforementioned pantograph copper-based slider detection system, wherein the slider image information acquisition unit includes:

[0018] The slider capture module, according to the slider positioning command, detects whether a slider passes through the contact wire position. When the slider positioning module detects that the slider has passed through the contact wire, it outputs the capture command. The slider capture module acquires the slider image information according to the capture command.

[0019] The aforementioned pantograph copper-based slider detection system, wherein the slider thickness data measurement unit includes:

[0020] The image analysis and processing module preprocesses the slider image information using the OpenCV image processing algorithm, and then performs contour detection on the preprocessed slider image information using a deep learning algorithm to obtain the slider contour. The image analysis and processing module processes the slider contour to obtain the number of pixels in the most severely worn area of ​​the slider, and compares the number of pixels in the most severely worn area of ​​the slider with the number of pixels in the unworn area of ​​the slider to obtain the slider thickness data.

[0021] In the aforementioned pantograph copper-based slider detection system, the slider operation status prediction unit extracts numerical statistical features of the slider thickness data in the copper-based slider detection work order through statistical analysis, processes the numerical statistical features through the feature processing algorithm of machine learning, obtains the slider thickness variation law, and then predicts the slider operation status prediction result based on the slider thickness variation law.

[0022] The slider operation status prediction unit obtains the slider operation status prediction result from the copper-based slider inspection work order.

[0023] The present invention also provides a method for detecting a copper-based slider of a pantograph for monorail vehicles, wherein the method is applicable to the detection system for the pantograph copper-based slider described above, and the method for detecting the pantograph copper-based slider includes:

[0024] Steps for obtaining slider identity information: After obtaining vehicle number information based on vehicle passing signal collection, obtain slider identity information based on the vehicle number information and trigger sequence data;

[0025] Steps for obtaining slider image information: Acquire slider image information based on the detection results;

[0026] Slider thickness data measurement steps: The slider image information is detected by an image processing algorithm to obtain the slider outline; the slider outline is processed by a slider thickness measurement algorithm to obtain slider thickness data; and a copper-based slider inspection work order is generated based on the slider thickness data and the slider identity information.

[0027] Slider running status prediction steps: Based on the copper-based slider inspection work order data, the slider thickness is predicted using a feature processing algorithm to obtain the slider running status prediction result.

[0028] A method for detecting a copper-based slider of a pantograph, wherein the step of obtaining the slider image information includes:

[0029] The detection result is obtained by detecting whether a slider has passed through the contact wire location;

[0030] When the detection result indicates that the slider passes through the contact wire, image information of the slider is acquired.

[0031] A method for detecting the copper-based slider of a pantograph, wherein the slider thickness data measurement step includes:

[0032] The slider image information is preprocessed using OpenCV image processing algorithms;

[0033] The slider contour is obtained by performing contour detection on the preprocessed slider image using a deep learning algorithm.

[0034] The slider contour is processed to obtain the number of pixels in the area with the most severe wear. The number of pixels in the area with the most severe wear is compared with the number of pixels in the area without wear to obtain the slider thickness data.

[0035] A method for detecting a pantograph copper-based slider, wherein the slider operating state prediction step includes:

[0036] After extracting the numerical statistical features of the slider thickness data in the copper-based slider detection work order through statistical analysis, the numerical statistical features are processed by the feature processing algorithm of machine learning to obtain the slider thickness variation law. Based on the slider thickness variation law, the slider running state prediction result is obtained.

[0037] The slider operation status prediction unit obtains the slider operation status prediction result from the copper-based slider inspection work order.

[0038] Compared to related technologies, this invention proposes a pantograph copper-based slider detection system and method for monorail vehicles. The radar receiving module is installed at a fixed angle on the railside. Based on the on-site working distance, a slider positioning camera is installed below the vehicle side. Fixing the slider positioning module to the pier reduces the cost of pantograph contact status detection across the entire line. An automated measurement system for the monorail vehicle pantograph slider is achieved through a trackside visual measurement system, eliminating the need for manual inspection, saving manpower and improving detection efficiency. Slider thickness is detected using slider measurement software, and a slider thickness measurement algorithm based on a combination of OpenCV and deep learning improves detection accuracy and efficiency. A cooperative approach is adopted between the slider positioning module and the image capture module. After the positioning module is fixed to the pier, it continuously acquires images of the contact wire position on the track beam and uploads them to an image processing and analysis server. The server processes the camera images in real time to detect whether a slider has passed at the contact wire position. When a slider is detected, the acquisition control computer calls the slider capture module to capture images of the slider's side, accurately capturing images of the monorail vehicle pantograph slider, avoiding the waste of system resources caused by multiple image captures and processing.

[0039] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0040] The accompanying drawings, which are provided herein to further illustrate this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0041] Figure 1 This is a flowchart of the pantograph copper-based slider detection method according to an embodiment of this application;

[0042] Figure 2 This is a flowchart of the pantograph copper-based slider detection process according to an embodiment of this application;

[0043] Figure 3 This is a schematic diagram of the layout of the vehicle receiving radar module according to an embodiment of this application;

[0044] Figure 4 This is a schematic diagram of the layout of the slider positioning module and the slider capture module according to an embodiment of this application;

[0045] Figure 5 This is a diagram of a copper-based slider detection frame for a monorail vehicle pantograph according to an embodiment of this application.

[0046] Figure 6 This is a schematic diagram of a radar vehicle receiving module according to an embodiment of this application;

[0047] Figure 7 This is a schematic diagram of the OCR character recognition principle according to an embodiment of this application;

[0048] Figure 8 This is a diagram illustrating the recognition effect according to an embodiment of this application;

[0049] Figure 9 This is a field schematic diagram of the pantograph slider in the lowered state according to an embodiment of this application;

[0050] Figure 10 This is a field schematic diagram of the pantograph slider in the raised state according to an embodiment of this application;

[0051] Figure 11 This is a flowchart of the image processing algorithm for the slider positioning module according to an embodiment of this application;

[0052] Figure 12 This is a schematic diagram of the on-site positions of the slider positioning module and the capture module according to an embodiment of this application;

[0053] Figure 13 These are field pantograph slider images according to embodiments of this application;

[0054] Figure 14 This is a flowchart of the slider thickness measurement algorithm according to an embodiment of this application;

[0055] Figure 15 This is a schematic diagram of the on-site measurement results of the pantograph slider according to an embodiment of this application;

[0056] Figure 16 This is a schematic diagram of the slider measurement software interface according to an embodiment of this application;

[0057] Figure 17 This is a schematic diagram of the structure of the copper-based slider detection system for pantographs of monorail vehicles according to the present invention.

[0058] The attached figures are labeled as follows:

[0059] Slider identity information acquisition unit: 51;

[0060] Slider image information acquisition unit: 52;

[0061] Slider thickness data measurement unit: 53;

[0062] Slider running status prediction unit: 54. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0064] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any creative effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the disclosure of this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of this application.

[0065] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0066] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0067] This invention provides a detection system and method for copper-based pantograph sliders on monorail vehicles. It automates the measurement of pantograph sliders through trackside visual measurement, improving detection efficiency. A slider thickness measurement algorithm based on a combination of OpenCV and deep learning enhances detection accuracy. Furthermore, the system employs a cooperative approach between a slider positioning module and an image capture module, enabling accurate image capture of the pantograph slider and avoiding the waste of system resources associated with capturing and processing multiple images.

[0068] The present invention will now be described with reference to specific embodiments.

[0069] Example 1

[0070] This embodiment also provides a pantograph copper-based slider detection system and method for monorail vehicles. Please refer to... Figures 1 to 2 , Figure 1 This is a flowchart of the pantograph copper-based slider detection method according to an embodiment of this application; Figure 2 This is a flowchart illustrating the detection process of the copper-based slider of the pantograph for monorail vehicles according to an embodiment of this application. Figures 1 to 2 As shown, the pantograph copper-based slider detection method includes:

[0071] Step S1 for obtaining slider identity information: After obtaining the vehicle number information based on the vehicle passing signal, obtain the slider identity information based on the vehicle number information and the trigger sequence data;

[0072] Step S2: Obtain slider image information based on the detection results;

[0073] S3: The slider thickness data measurement step is as follows: The slider image information is detected by the image processing algorithm to obtain the slider outline, the slider outline is processed by the slider thickness measurement algorithm to obtain the slider thickness data, and a copper-based slider inspection work order is generated based on the slider thickness data and the slider identity information.

[0074] S4: Based on the copper-based slider inspection work order data, the slider thickness is predicted using a feature processing algorithm to obtain the slider operation status prediction result.

[0075] In this embodiment, step S2, which obtains slider image information, includes:

[0076] The detection results are obtained by detecting whether a slider has passed through the contact wire location;

[0077] When the detection result indicates that the slider has passed through the contact wire, the slider image information is collected.

[0078] In this embodiment, the slider thickness data measurement step S3 includes:

[0079] The slider image information is preprocessed using OpenCV image processing algorithms;

[0080] The contour of the slider is obtained by performing contour detection on the preprocessed slider image using a deep learning algorithm.

[0081] The slider contour is processed to obtain the number of pixels in the area with the most severe wear. The number of pixels in the area with the most severe wear is compared with the number of pixels in the unworn area of ​​the slider to obtain the slider thickness data.

[0082] In this embodiment, the slider running state prediction step S4 includes:

[0083] After extracting the numerical statistical features of the slider thickness data in the copper-based slider detection work order through statistical analysis, the numerical statistical features are processed by machine learning feature processing algorithms to obtain the slider thickness variation law. Based on the slider thickness variation law, the slider running status prediction result is obtained.

[0084] The slider running status prediction unit obtains the slider running status prediction results in the copper-based slider inspection work order.

[0085] Example 2

[0086] This embodiment also provides a pantograph copper-based slider detection system for monorail vehicles. Figure 3 This is a schematic diagram of the layout of the vehicle receiving radar module according to an embodiment of this application; Figure 4 This is a schematic diagram of the layout of the slider positioning module and the slider capture module according to an embodiment of this application; Figure 5 This is a diagram of a copper-based slider detection frame for a monorail vehicle pantograph according to an embodiment of this application. Figure 6 This is a schematic diagram of a radar vehicle receiving module according to an embodiment of this application; Figure 7 This is a schematic diagram of the OCR character recognition principle according to an embodiment of this application; Figure 8 This is a diagram illustrating the recognition effect according to an embodiment of this application; Figure 9 This is a field schematic diagram of the pantograph slider in the lowered state according to an embodiment of this application; Figure 10 This is a field schematic diagram of the pantograph slider in the raised state according to an embodiment of this application; Figure 11 This is a flowchart of the image processing algorithm for the slider positioning module according to an embodiment of this application; Figure 12 This is a schematic diagram of the on-site positions of the slider positioning module and the capture module according to an embodiment of this application; Figure 13 These are field pantograph slider images according to embodiments of this application; Figure 14 This is a flowchart of the slider thickness measurement algorithm according to an embodiment of this application; Figure 15 This is a schematic diagram of the on-site measurement results of the pantograph slider according to an embodiment of this application; Figure 16 This is a schematic diagram of the slider measurement software interface according to an embodiment of this application; Figure 17 This is a schematic diagram of the copper-based slider detection system for pantographs on monorail vehicles according to the present invention. Figures 3 to 17 As shown, the pantograph copper-based slider detection system of the invention is applicable to the above-mentioned pantograph copper-based slider detection method. The pantograph copper-based slider detection system includes:

[0087] Slider identity information acquisition unit 51: After receiving and triggering vehicle number recognition and slider positioning based on the vehicle passing signal, it outputs slider identity information;

[0088] Slider image information acquisition unit 52: When the slider identity information acquisition unit detects the slider, it triggers the slider image information acquisition unit to capture the slider and acquire slider image information;

[0089] Slider thickness data measurement unit 53: detects slider image information to obtain slider contour, processes slider contour through slider thickness measurement algorithm to obtain slider thickness data, and generates copper-based slider inspection work order based on slider thickness data and slider identity information;

[0090] Slider running status prediction unit 54: Based on the copper-based slider inspection work order data, the slider thickness is predicted through feature processing algorithm to obtain the slider running status prediction result.

[0091] In this embodiment, the slider identity information acquisition unit 51 includes:

[0092] The vehicle receiving radar module collects and outputs vehicle passing signals;

[0093] The image acquisition and control module outputs vehicle number recognition instructions and slider positioning instructions based on the vehicle passing signal;

[0094] The vehicle number recognition module identifies the vehicle number and obtains the vehicle number information according to the vehicle number recognition command;

[0095] The slider positioning module positions the slider according to the slider positioning command and outputs trigger sequence data and capture command;

[0096] Identity information integration module: integrates the vehicle number information and the trigger sequence data to obtain the slider identity information.

[0097] In practice, the pantograph copper-based slider detection system mainly consists of trackside equipment and machine room equipment;

[0098] The trackside equipment includes: a train arrival radar module, an image car number module, a slider positioning module, and a slider capture module. The train arrival radar module is used to determine the arrival and departure of the train, the image car number module is used to detect the train number, and the slider positioning module is used to detect the slider position and trigger the slider capture module to acquire a high-definition image of the slider.

[0099] The equipment in the computer room includes: an image acquisition and control system and an image analysis and processing system. The image acquisition and control system is responsible for collecting and processing all sensor signals and capturing and controlling the slider image. It includes one acquisition and control computer, one switch, one power supply box, one KVM, one remote PDU, and one UPS. The image processing and analysis system is used to process high-definition images of the slider and automatically analyze and identify the slider wear curve. It includes one data storage and recognition server.

[0100] The working principle of the radar vehicle receiving module in this invention is as follows:

[0101] After the radar vehicle receiving module is installed at a fixed angle on the side of the rail, it continuously detects whether there is an object at the designated location. When an object is detected, the receiving radar module collects the vehicle passing signal. Specifically, when a monorail vehicle enters the depot, the radar vehicle receiving module fixed at the front end first determines the arrival of the monorail vehicle. When the radar is continuously triggered for a period of time, it is considered that a monorail vehicle has passed. The radar vehicle receiving module will send the vehicle passing signal to the acquisition control computer, i.e., the image acquisition control system, and control the capture module and slider positioning module of the entire system to turn on or off.

[0102] The vehicle receiving radar module is powered by DC24V. The speed measurement error for objects with speeds ranging from 5km / h to 120km / h is no higher than 1%. It refreshes data at a rate of no less than 10 times per second and can operate normally within a temperature range of -20℃ to +60℃.

[0103] The working principle of the vehicle license plate recognition module in this invention is as follows:

[0104] The image acquisition and control system sends a vehicle number recognition command to the vehicle number recognition module based on the vehicle passing signal. The vehicle number recognition module then identifies the vehicle number and obtains the vehicle number information based on the vehicle number recognition command.

[0105] In detail, when the vehicle passing signal sent by the vehicle receiving radar module is transmitted to the image acquisition industrial control computer (i.e., the image acquisition control system and image processing and analysis server) through serial communication, the image processing and analysis server sends processing instructions to the vehicle number recognition module to trigger the camera to work, continuously capturing images of the monorail vehicle passing by. At the same time, the OCR character recognition algorithm is used to process and analyze the captured images of the monorail vehicle passing by, identify the number of the monorail vehicle and record it.

[0106] The module integrates a high-brightness strobe fill light, enabling shooting in dark environments at night. The license plate recognition device is powered by DC24V and uses an industrial camera to capture license plate images, achieving a recognition rate of ≥99%. The module has an IP66 waterproof and dustproof rating and can operate normally within a temperature range of -40℃ to +70℃.

[0107] The OCR character recognition algorithm uses the CRNN algorithm, whose network structure consists of three layers: a convolutional layer, a recurrent layer, and a transcription layer. The convolutional layer uses a CNN network to extract feature sequences from the video stream captured by the camera. The recurrent layer uses an RNN network to predict the distribution of true values ​​from the feature sequences obtained from the convolutional layer. The transcription layer uses a CTC network to transform the label distribution obtained from the recurrent layer into the final recognition result through deduplication and integration operations.

[0108] The working principle of the slider positioning module in this invention is as follows:

[0109] The slider is positioned according to the slider positioning command, and trigger sequence data and capture command are output. The vehicle number information and the trigger sequence data are integrated to obtain the slider identity information. Specifically, according to the on-site working distance, the positioning module is fixed to the pier, and the slider positioning camera is installed on the side below the vehicle. After the acquisition control computer, i.e., the image acquisition control system, receives the monorail vehicle passing signal sent by the receiving radar module, it starts the camera and slider positioning detection program of the slider positioning module. Then, it continuously acquires images of the contact wire position on the track beam and uploads them to the image processing and analysis server. The server processes the camera images in real time to detect whether a slider has passed at the contact wire position. During train operation, only the pantograph slider will contact the contact wire on the track beam. The acquisition control computer then calls the slider capture module to capture the side image of the slider. According to the trigger sequence number of the slider positioning module triggered by the image acquisition control system and the vehicle number information, the slider identity information, i.e., the storage location of the slider image in the local folder and the slider naming number, is defined.

[0110] like Figure 9 and Figure 10 The figures show the pantograph slider in its lowered and raised states, respectively. The areas marked in the figure represent the contact wire and the slider, respectively. The distances of the two cameras from the sliders on both sides are approximately 2.3m and 3m, respectively.

[0111] In this embodiment, the slider image information acquisition unit 52 includes:

[0112] The slider capture module and slider positioning module detect whether a slider has passed through the contact wire position according to the slider positioning command. When the slider positioning module detects that the slider has passed through the contact wire, it outputs a capture command. The slider capture module then acquires the slider image information according to the capture command.

[0113] In practice, the image captured by the camera needs to be analyzed during the slider positioning process. If the presence of a slider is detected in the current frame by the image features, the camera is triggered to capture the image and obtain a side view of the slider. Specifically, the image data is filtered by a radius filter, and the slider features are found by the changes in fixed point features. The slider is then judged to have been reached based on the fixed point threshold. When the result indicates that the slider has been reached, the slider capture module is triggered to capture the slider image. At this time, all four sliders on both sides of the train will be captured and saved to the image processing server before the monorail train leaves the detection area.

[0114] The slider capture module consists of four modules, each composed of a camera and a light source, with two modules on each side of the train.

[0115] In this embodiment, the slider thickness data measurement unit 53 includes:

[0116] The image analysis and processing module preprocesses the slider image information using the OpenCV image processing algorithm, and then performs contour detection on the preprocessed slider image information using a deep learning algorithm to obtain the slider contour. The image analysis and processing module processes the slider contour to obtain the number of pixels in the most severely worn area of ​​the slider, and compares the number of pixels in the most severely worn area of ​​the slider with the number of pixels in the unworn area of ​​the slider to obtain the slider thickness data.

[0117] In practice, the slider capture module captures the slider image and uploads it to the image processing and analysis server. The processing system then calls the corresponding image processing algorithm to preprocess the image data, improve the detectability of useful information, and maximize the simplification of the data.

[0118] The preprocessed slider image is subjected to contour detection using a deep learning algorithm to obtain the slider contour. The slider contour is then processed to obtain the number of pixels in the most severely worn area. This number is compared with the number of pixels in the unworn area to obtain the slider thickness data. Based on the slider thickness data and the slider's identification information, a copper-based slider inspection work order is generated. Specifically, after the slider capture module transmits the slider image information to the image analysis and processing system, the slider image processing and thickness detection algorithms begin running. The flowchart of the slider thickness measurement algorithm is shown below. Figure 14 As shown, the operation steps of the slider thickness measurement algorithm are as follows:

[0119] Step 1: Preprocess the image using OpenCV. Specifically, filter the image, convert the filtered image to grayscale, sharpen the grayscale image, extract edges from the sharpened image, obtain straight lines using Hough transform, determine the approximate position of the slider based on the obtained results, and crop the slider image from the image.

[0120] Step 2: Segment the image using deep learning-based slider segmentation and obtain the minimum bounding rectangle of the segmented region, i.e., the slider outline;

[0121] Step 3: Search for the thinnest part of the slider along the direction perpendicular to the long side of the rectangle to obtain the number of pixels in the area with the most severe wear. Compare the number of pixels in the area with the number of pixels in the unworn area of ​​the slider to obtain the actual wear value of the slider, i.e., the slider thickness data.

[0122] Because the monorail and the slider need to be in constant contact during train operation, the wear of the slider is uneven. Therefore, the solution uses the minimum thickness value of the middle area of ​​the slider as the measured thickness value of the slider.

[0123] In this embodiment, the slider running state prediction unit 54 extracts the numerical statistical features of the slider thickness data in the copper-based slider detection work order through statistical analysis, processes the numerical statistical features through a machine learning feature processing algorithm, obtains the slider thickness change pattern, and then predicts the slider running state prediction result based on the slider thickness change pattern.

[0124] The slider running status prediction unit obtains the slider running status prediction results in the copper-based slider inspection work order.

[0125] In practice, after the copper-based slider inspection work order is generated, the slider data is stored in the image processing and analysis system. Effective statistical analysis is used to extract effective numerical statistical features from the slider thickness data. Various feature processing algorithms based on machine learning are used to mine and analyze the slider thickness data to find the pattern of slider thickness change, realize the prediction of slider thickness change trend, provide timely early warning of slider thickness wear, and finally describe it in the copper-based slider inspection work order.

[0126] The final slider measurement results are as follows Figure 15 As shown, accurate measurements can be obtained at the thinnest point of the slider.

[0127] Measurement software interface as follows Figure 16 As shown, the measurement software belongs to Figure 2 The system integrates a vehicle receiving radar module, a vehicle number recognition module, a slider positioning module, a slider capture module, and an image analysis and processing system. The slider capture module captures slider images and displays them in the upper left corner of the interface. At the same time, it transmits the slider image information to the image processing and analysis system and displays the final result in the lower right corner.

[0128] In summary, this invention provides a pantograph copper-based slider detection system and method for monorail vehicles. Based on vision technology, it directly measures the remaining thickness of the pantograph slider on monorail vehicles, providing the most direct and effective maintenance basis for train maintenance. This invention uses vision technology to directly acquire real images of the pantograph slider, obtaining its true remaining thickness. Furthermore, this invention is a trackside detection system; a single system can detect the remaining thickness of the pantograph sliders of all returning trains on the current line. The equipment is located on the ground beside the track, far from the overhead contact line, resulting in minimal electromagnetic interference and convenient maintenance.

[0129] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the scope of the appended claims.

Claims

1. A pantograph copper-based slider detection system for monorail vehicles, characterized in that, The pantograph copper-based slider detection system includes: Slider identity information acquisition unit: After receiving and triggering vehicle number recognition and slider positioning based on the vehicle passing signal, it outputs slider identity information; Slider image information acquisition unit: When the slider identity information acquisition unit detects the slider, it triggers the slider image information acquisition unit to capture the slider and acquire slider image information; Slider thickness data measurement unit: detects the slider image information to obtain the slider outline, processes the slider outline through a slider thickness measurement algorithm to obtain slider thickness data, and generates a copper-based slider inspection work order based on the slider thickness data and the slider identity information; Slider running status prediction unit: Based on the copper-based slider inspection work order data, the slider thickness is predicted through feature processing algorithms to obtain the slider running status prediction result; The slider identity information acquisition unit includes: The vehicle receiving radar module collects and outputs the vehicle passing signal; The image acquisition and control module outputs vehicle number recognition instructions and slider positioning instructions based on the vehicle passing signal; The vehicle number recognition module identifies the vehicle number and obtains the vehicle number information according to the vehicle number recognition instruction; The slider positioning module positions the slider according to the slider positioning command and outputs trigger sequence data and capture command; Identity information integration module: integrates the vehicle number information and the trigger sequence data to obtain the slider identity information; The slider image information acquisition unit includes: The slider capture module, according to the slider positioning module, detects whether a slider passes through the contact wire position according to the slider positioning command. When the slider positioning module detects that the slider has passed through the contact wire, it outputs the capture command. The slider capture module acquires the slider image information according to the capture command.

2. The pantograph copper-based slider detection system according to claim 1, characterized in that, The slider thickness data measurement unit includes: The image analysis and processing module preprocesses the slider image information using the OpenCV image processing algorithm, and then performs contour detection on the preprocessed slider image information using a deep learning algorithm to obtain the slider contour. The image analysis and processing module processes the slider contour to obtain the number of pixels in the most severely worn area of ​​the slider, and compares the number of pixels in the most severely worn area of ​​the slider with the number of pixels in the unworn area of ​​the slider to obtain the slider thickness data.

3. The pantograph copper-based slider detection system according to claim 1, characterized in that, The slider running status prediction unit extracts the numerical statistical features of the slider thickness data in the copper-based slider detection work order through statistical analysis, processes the numerical statistical features through the feature processing algorithm of machine learning, obtains the slider thickness change law, and then predicts the slider running status prediction result based on the slider thickness change law. The slider operation status prediction unit obtains the slider operation status prediction result from the copper-based slider inspection work order.

4. A method for detecting the copper-based slider of a pantograph for monorail vehicles, applied to the pantograph copper-based slider detection system for monorail vehicles as described in any one of claims 1-3, characterized in that, The pantograph copper-based slider detection method includes: Steps for obtaining slider identity information: After obtaining vehicle number information based on vehicle passing signal collection, obtain slider identity information based on the vehicle number information and trigger sequence data; Steps for obtaining slider image information: Acquire slider image information based on the detection results; Slider thickness data measurement steps: The slider image information is detected by an image processing algorithm to obtain the slider outline; the slider outline is processed by a slider thickness measurement algorithm to obtain slider thickness data; and a copper-based slider inspection work order is generated based on the slider thickness data and the slider identity information. Slider running status prediction steps: Based on the copper-based slider inspection work order data, the slider thickness is predicted through feature processing algorithms to obtain the slider running status prediction results; The step of obtaining the slider image information includes: The detection result is obtained by detecting whether a slider has passed through the contact wire location; When the detection result indicates that the slider passes through the contact wire, image information of the slider is acquired; The step of obtaining the slider's identity information includes: Collect and output the vehicle passage signal; Based on the vehicle passage signal, output vehicle number identification command and slider positioning command; The vehicle number is identified according to the vehicle number recognition instruction to obtain vehicle number information; The slider is positioned according to the slider positioning command, and trigger sequence data and capture command are output; The slider's identity information is obtained by integrating the vehicle number information and the trigger sequence data.

5. The pantograph copper-based slider detection method according to claim 4, characterized in that, The slider thickness data measurement steps include: The slider image information is preprocessed using OpenCV image processing algorithms; The slider contour is obtained by performing contour detection on the preprocessed slider image using a deep learning algorithm. The slider contour is processed to obtain the number of pixels in the area with the most severe wear. The number of pixels in the area with the most severe wear is compared with the number of pixels in the area without wear to obtain the slider thickness data.

6. The pantograph copper-based slider detection method according to claim 4, characterized in that, The slider operation state prediction step includes: After extracting the numerical statistical features of the slider thickness data in the copper-based slider detection work order through statistical analysis, the numerical statistical features are processed by the feature processing algorithm of machine learning to obtain the slider thickness variation law. Based on the slider thickness variation law, the slider running state prediction result is obtained. The slider operation status prediction unit obtains the slider operation status prediction result from the copper-based slider inspection work order.

Images