A method, system and device for identifying electric derailers and storage medium

Abstract

The application discloses an electric derail device compression and derailment identification method, system, device and storage medium, relates to the field of railway safety technology, and has the technical scheme as follows: the method comprises the following steps: in response to an up-drawing application signal, output information of a wheel sensor and image information about a derail device area are acquired; whether there is a locomotive vehicle in the derail device area is judged according to the output information; when the derail device area is free of the locomotive vehicle, the image information is analyzed and identified to judge whether the electric derail device in the derail device area is compressed and derails; and if the electric derail device does not compress and derail, the electric derail device is allowed to up-draw. Through the method, the locomotive vehicle can be automatically identified and judged, image compression and derailment automatic identification is realized, the accuracy of electric derail device compression and derailment identification is ensured, the up-drawing of the derail device is facilitated, the safety hidden danger is reduced, and the operation safety of the train inspection personnel is ensured.

Description

Technical Field

[0001] This invention relates to the field of railway safety technology, specifically to a method, system, device, and storage medium for identifying the derailment of an electric derailer. Background Technology

[0002] This section is intended to provide background or context for the embodiments set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section.

[0003] Existing electric derailer systems require on-site power requests, necessitating on-site inspectors to travel to the derailer to request its deployment. Due to varying numbers of cars on a train, the distance between the rear of the train and the derailer can be considerable. This on-site requirement for inspectors to travel a significant distance to request power reduces operational efficiency, particularly in 10,000-ton derailment yards.

[0004] Currently, there are two main ways to request power for electric derailers: on-site application and on-duty personnel application. Regardless of the application method, the on-duty personnel need to manually click the confirmation window of the main control software for the derailer to detach. This operation still poses certain safety hazards, especially when the on-duty personnel are fatigued at night and make mistakes. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention proposes a method, system, device, and storage medium for identifying electric derailment devices that can automatically identify and judge locomotives and rolling stock, achieve automated identification of derailment images, ensure the accuracy of electric derailment device identification, facilitate automated control of derailment device detachment, reduce safety hazards, and ensure the safety of train inspection personnel.

[0006] To solve the above-mentioned technical problems, the technical solution adopted by the present invention includes four aspects.

[0007] Firstly, a method for identifying the derailment of an electric derailer is provided, including:

[0008] In response to the derailment request signal, acquire the output information of the wheel sensors and image information about the derailment area;

[0009] Based on the output information, determine whether there are locomotives or vehicles in the derailment zone;

[0010] When there are no locomotives or vehicles in the derailment area, the image information is analyzed and identified to determine whether the electric derailment device in the derailment area has been derailed.

[0011] If the electric derailer is not depressurized, then the electric derailer is allowed to derail.

[0012] In some embodiments, determining whether there are locomotives or vehicles in the derailment zone based on the output information includes:

[0013] The output information is used to identify the direction of travel of the train wheels and the number of wheels passing by.

[0014] The axle counting information within the derailment zone is determined based on the direction of travel of the train wheels and the number of wheels passing through.

[0015] The presence of locomotives or vehicles in the derailment zone is determined based on the axle counting information.

[0016] In some embodiments, determining whether there are locomotives or rolling stock in the derailment zone based on the axle counting information includes:

[0017] When the axle counting information indicates that the number of axles in the derailment zone is zero, it is determined that there are no locomotives or rolling stock in the derailment zone.

[0018] When the axle counting information indicates that the number of axles in the derailer is not zero, it is determined that there are locomotives and vehicles in the derailer zone.

[0019] In some embodiments, when the axle counting information shows that the number of axles in the derailment zone increases over time, it is determined that the locomotives and rolling stock in the derailment zone have entered the derailment zone; when the axle counting information shows that the number of axles in the derailment zone decreases over time, it is determined that the locomotives and rolling stock in the derailment zone have left the derailment zone.

[0020] In some embodiments, analyzing and identifying the image information to determine whether the electric derailer in the derailer area has been derailed includes:

[0021] Preset image templates for the feature locations of the rails;

[0022] The image information is processed to obtain a comparison image for comparison.

[0023] The comparison image is compared with the image template to determine the similarity between the comparison image and the image template;

[0024] The similarity is compared with a preset threshold. When the similarity is greater than the preset threshold, the comparison is considered successful, and it is determined that the electric derailer has not been derailed.

[0025] In some embodiments, comparing the similarity with a preset threshold includes:

[0026] The color mode of the current image is determined based on the comparison image; the color mode includes color mode and black and white mode.

[0027] When the comparison image is in color mode, the preset threshold is 97%, that is, when the similarity is greater than 97%, the comparison is determined to be successful, and it is determined that the electric derailer has not been derailed.

[0028] When the comparison image is in black and white mode, the preset threshold is 98%. That is, when the similarity is greater than 98%, the comparison is considered successful, and it is determined that the electric derailer has not been derailed.

[0029] In some embodiments, processing the image information to obtain a comparison image for comparison includes:

[0030] The image information is subjected to grayscale conversion, sharpening, filtering, contrast enhancement, edge detection, and binarization to obtain a comparison image.

[0031] In some embodiments, the grayscale processing employs a weighted average method; the sharpening processing uses a high-pass filter to process image information; the filtering processing employs median filtering; the contrast enhancement processing classifies the value of each pixel according to a set threshold and increases the image contrast by reducing the number of layers; the edge detection processing includes: defining an edge as the boundary of a region in the image where the grayscale changes drastically; using local image differentiation techniques to obtain an edge detection operator; and constructing an edge detection operator from a small neighborhood of pixels in the original image to perform edge detection; the binarization processing employs local adaptive binarization to set a reasonable threshold.

[0032] In some embodiments, the derailment area extends from 15m inside the derailment to 3m outside the derailment; and the top edge of the derailment area is located at the edge of the adjacent track sleeper, and the bottom edge is located at the edge of the track sleeper.

[0033] Secondly, an electric derailer derailment detection system is provided, comprising:

[0034] The acquisition module is used to acquire the output information of the wheel sensors and image information about the derailer area in response to the upper derailment application signal;

[0035] The automatic locomotive and rolling stock determination module is used to determine whether there are locomotives or rolling stock in the derailment zone based on the output information.

[0036] The derailment identification module is used to analyze and identify the image information when the locomotive and rolling stock determination module determines that there are no locomotives or rolling stock in the derailment area, and to determine whether the electric derailer in the derailer area has been derailed.

[0037] The electric derailer service module is used to allow the electric derailer to detach when the requested derailer has not been derailed.

[0038] Thirdly, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the aforementioned identification method.

[0039] Fourthly, a computer-readable storage medium is provided, wherein when the computer program is executed by a processor, it implements the steps of the identification method as described above.

[0040] Compared with the prior art, one or more embodiments of the above solutions may have the following advantages or beneficial effects:

[0041] This application provides a method, system, device, and storage medium for identifying electric derailment devices that have been derailed. The identification method includes: responding to a derailment request signal, acquiring output information from wheel sensors and image information about the derailment device area; determining whether there are locomotives or vehicles in the derailment device area based on the output information; when there are no locomotives or vehicles in the derailment device area, analyzing and identifying the image information to determine whether the electric derailment device in the derailment device area has been derailed; if the electric derailment device has not been derailed, then allowing the electric derailment device to detach. This identification method can automatically identify and determine locomotives and vehicles, achieve automated image derailment identification, ensure the accuracy of electric derailment device derailment identification, facilitate automated control of derailment device detachment, reduce safety hazards, and ensure the safety of train inspection personnel. Attached Figure Description

[0042] The present application will be described in more detail below based on embodiments and with reference to the accompanying drawings;

[0043] Figure 1 This is an exemplary flowchart of the electric derailer derailment identification method in an embodiment of the present invention;

[0044] Figure 2 In the embodiments of the present invention, corresponding to Figure 1 An exemplary flowchart of step S2 shown;

[0045] Figure 3 In the embodiments of the present invention, corresponding to Figure 2 An exemplary flowchart of step S23 shown;

[0046] Figure 4 In the embodiments of the present invention, corresponding to Figure 1 An exemplary flowchart of step S3 shown;

[0047] Figure 5 In the embodiments of the present invention, corresponding to Figure 4 An exemplary flowchart of step S34 shown;

[0048] Figure 6 This is a schematic block diagram of the electric derailment device derailment identification system in an embodiment of the present invention;

[0049] Figure 7 This is a schematic block diagram illustrating the connection relationship between the wheel sensor, wheel detector, camera, and pressure-removal recognition system in an embodiment of the present invention.

[0050] Figure 8 This is a schematic block diagram of an electronic device provided in an embodiment of the present invention;

[0051] Figure 9 This is a schematic diagram of a computer-readable storage medium provided in an embodiment of the invention.

[0052] In the accompanying drawings, the same parts are referred to by the same reference numerals, and the drawings are not drawn to scale. Detailed Implementation

[0053] The present disclosure will be further described below with reference to the embodiments shown in the accompanying drawings.

[0054] This application discloses a method for identifying the derailment of an electric derailer, such as... Figure 1 As shown, the identification method includes: in response to a derailment request signal, acquiring output information from wheel sensors and image information about the derailer area; determining whether there are locomotives or vehicles in the derailer area based on the output information; when there are no locomotives or vehicles in the derailer area, analyzing and identifying the image information to determine whether the electric derailer in the derailer area has been derailed; if the electric derailer has not been derailed, then the electric derailer is allowed to detach. This identification method can automatically identify and judge locomotives and vehicles, achieve automated image derailment identification, ensure the accuracy of electric derailer derailment identification, facilitate automated control of derailer detachment, reduce safety hazards, and ensure the safety of train inspection personnel.

[0055] Some embodiments of this disclosure also provide products corresponding to the above-described electric derailer derailment identification system, electronic devices, storage media, and computer programs.

[0056] This disclosure provides at least one embodiment of an electric derailer detonation identification method. This identification method can be implemented in software, hardware, firmware, or any combination thereof. It is loaded and executed by a processor in a device such as a mobile phone, tablet computer, laptop computer, desktop computer, or network server, thereby achieving automatic identification and judgment of locomotives and vehicles, realizing automated image detonation identification, ensuring the accuracy of electric derailer detonation identification, facilitating automated control of derailer detachment, reducing safety hazards, and ensuring the safety of train inspection personnel.

[0057] The following is for reference. Figure 1 As shown, at least one embodiment of the electric derailer derailment identification method provided in this disclosure will be described, the identification method including steps S1 to S5.

[0058] S1. In response to the upper derailment request signal, acquire the output information of the wheel sensor and the image information about the derailment area.

[0059] In some embodiments, wheel sensors and cameras are installed on each track in the inspection area. The wheel sensors are used to collect vehicle wheel information and output it in a high / low voltage mode. The cameras are used to collect image information of the derailment area and send it to the electric derailment derailment identification system for identification.

[0060] In some embodiments, the derailment area extends from 15m inside the derailment to 3m outside the derailment; and the top edge of the derailment area is located at the edge of the adjacent track sleeper, and the bottom edge is located at the edge of the track sleeper, that is, the derailment area is a diamond-shaped area. When the camera collects image information, it only collects images within the derailment area to facilitate accurate image recognition and reduce unnecessary recognition range, thereby improving recognition efficiency.

[0061] In some embodiments, in order to achieve accurate identification of locomotives and vehicles parked in the derailment area, ensure the reliability of image information transmission, and avoid errors in judgment due to image abnormalities caused by interference, the acquired images must be clear and accurate. It is necessary to select a camera with high sensitivity, high signal-to-noise ratio, low illumination, low distortion, and high definition. In practical applications, Hikvision network HD camera (iDS-2ZCN2507N) can be selected to meet the requirements.

[0062] In some embodiments, the wheel sensors are low-speed active wheel sensors. When the train enters the inspection yard, the speed is low, especially when the train is about to enter the entire work area, the speed gradually decreases to zero. During this process, when the wheels pass the wheel sensors set near the derailment device, the speed changes continuously and the train may stop and then start again. There may even be repeated situations where the wheels move forward and backward. Therefore, low-speed wheel sensors are needed to accurately identify the number and direction of low-speed or zero-speed wheels in order to accurately determine vehicle information.

[0063] In some embodiments, a set of two low-speed active wheel sensors is installed on the rails at both ends of each track in the inspection yard, on the inner and outer sides of the derailment devices (23 meters on the inner side and 6 meters on the outer side). Each track requires eight low-speed active wheel sensors. The wheel sensors are mounted using clamps to avoid drilling holes in the rails. They are used to monitor the passing of locomotive and rolling stock wheels and output the collected wheel information in high and low voltage levels. The standard installation dimensions for the wheel sensors are: a center-to-center distance of 190±5mm between a set of wheel sensors; a vertical distance of 38-40mm between the top plane of the wheel sensor and the rail plane; and a horizontal distance of 4mm between the wheel sensor and the inner edge of the rail, based on the dimensions specified by the calibration block, to ensure accurate collection of vehicle wheel information.

[0064] S2. Determine whether there are locomotives or vehicles in the derailment zone based on the output information.

[0065] In some embodiments, step S2, such as Figure 2 As shown, it includes:

[0066] S21. Identify the direction of travel of the train wheels and the number of wheels passing by based on the output information;

[0067] S22. Determine the axle counting information in the derailment zone based on the direction of travel of the train wheels and the number of wheels passing through;

[0068] S23. Determine whether there are locomotives or vehicles in the derailment area based on the axle counting information.

[0069] In some embodiments, the wheel sensor is connected to a wheel detector. The wheel sensor outputs the collected wheel information to the wheel detector in a high-low level manner. The wheel detector determines the direction of wheel travel and the number of wheels passing by based on the timing logic relationship of the received high-low level, and determines the axle counting information in the derailment zone.

[0070] In some embodiments, the step involves determining whether there are locomotives or rolling stock within the derailment zone based on the axle counting information, such as... Figure 3 As shown, it includes:

[0071] S231. When the axle counting information indicates that the number of axles in the derailment zone is zero, it is determined that there are no locomotives or rolling stock in the derailment zone.

[0072] S232. When the axle counting information indicates that the number of axles in the derailer is not zero, determine that there are locomotives and vehicles in the derailer zone.

[0073] In some embodiments, when the axle counting information shows that the number of axles in the derailment zone increases over time, it is determined that locomotives and rolling stock in the derailment zone have entered the derailment zone; when the axle counting information shows that the number of axles in the derailment zone decreases over time, it is determined that locomotives and rolling stock in the derailment zone have exited the derailment zone. The occupancy status of the derailment zone is automatically analyzed and determined based on axle counting technology. The number of axles increases when locomotives and rolling stock enter the derailment zone and decreases when they exit. When the number of axles in the derailment zone is zero, it means that the wheels have been cleared and there are no locomotives or rolling stock in the derailment zone; otherwise, it is determined that there are locomotives or rolling stock in the derailment zone, thus facilitating automated determination of whether there are locomotives or rolling stock in the derailment zone.

[0074] S3. When there are no locomotives or vehicles in the derailer area, the image information is analyzed and identified to determine whether the electric derailer in the derailer area has been derailed.

[0075] In some embodiments, when the derailer is in the area of ​​a locomotive or vehicle, the derailment request signal is invalidated to prevent the derailer from derailing, thereby avoiding incorrect derailment insertion and ensuring operational safety.

[0076] In some embodiments, step S3, such as Figure 4 As shown, it includes:

[0077] S31. Preset an image template for the feature location of the rail;

[0078] S32. Process the image information to obtain a comparison image for comparison;

[0079] S33. Compare the comparison image with the image template to determine the similarity between the comparison image and the image template;

[0080] S34. Compare the similarity with a preset threshold. When the similarity is greater than the preset threshold, the comparison is successful, and it is determined that the electric derailer has not been derailed.

[0081] In some embodiments, the parameter information in the image template includes the setting of rail feature positions, so that when the device is compared with the comparison image, it can determine whether the rail has been derailed by identifying the rail features. That is, when no complete rail features are found in the comparison image, it is determined that the electric derailer has not been derailed by locomotives or vehicles.

[0082] In some embodiments, step S33 specifically includes performing grayscale processing, sharpening processing, filtering processing, contrast enhancement processing, edge detection processing, and binarization processing on the image information to obtain a comparison image.

[0083] The grayscale processing adopts a weighted average method. The grayscale processing process specifically includes: determining the three grayscale components of the color image from the obtained image information: (a) R component grayscale image; (b) G component grayscale image; (c) B component grayscale image, and averaging the three components with different weights according to their importance and other indicators.

[0084] Since the human eye is most sensitive to green and least sensitive to blue, a reasonable grayscale image can be obtained by weighting the RGB components according to the following formula.

[0085] f(i,j)=0.30R(i,j)+0.59G(i,j)+0.11B(i,j);

[0086] Sharpening processes include: using a high-pass filter to make the image clearer, thus achieving sharpening;

[0087] Filtering: Median filtering is used to replace the value of the center point of the image or sequence with the median value of the field. It has the advantages of simple operation, fast speed and good noise removal effect.

[0088] Contrast enhancement processing: Classify the value of each pixel according to a set threshold, reduce the number of levels to achieve the effect of increasing contrast;

[0089] Edge detection processing: Defines an edge as the boundary of a region in an image where the gray level changes drastically; uses local image differentiation techniques to obtain edge detection operators; and constructs an edge detection operator from a small neighborhood of a pixel in the original image to detect edges.

[0090] Binarization processing: Local adaptive binarization is adopted to make the threshold setting more reasonable. The threshold of this method is calculated by setting a parametric equation based on various local features such as the average value E of the pixels in the window, the squared difference P between pixels, and the root mean square value Q between pixels.

[0091] In some embodiments, step S34, such as Figure 5 As shown, it includes:

[0092] S341. Determine the color mode of the current image based on the comparison image; the color mode includes color mode and black and white mode;

[0093] S342. When the comparison image is in color mode, the preset threshold is 97%, that is, when the similarity is greater than 97%, the comparison is determined to be successful, and it is determined that the electric derailer has not been derailed.

[0094] S343. When the comparison image is in black and white mode, the preset threshold is 98%, that is, when the similarity is greater than 98%, the comparison is determined to be successful, and it is determined that the electric derailer has not been derailed.

[0095] In some embodiments, when comparing the similarity between a comparison image and an image template to determine whether the electric derailer has been derailed, at least two comparison images are compared. Only when two or more comparison images are successfully compared is it determined that the electric derailer has not been derailed.

[0096] S4. If the electric derailer is not pressed off, the electric derailer is allowed to derail.

[0097] S5. If the electric derailer is derailed, the image on that track will be identified as derailed and requires further manual confirmation.

[0098] In some embodiments, this identification method is applied to an identification system. When it is determined that the electric derailer has detached, the system displays the image to the operator, indicating that the detachment is detected and requires further manual confirmation. Furthermore, if rain, snow, or other interference causes a misidentification of detachment, the operator can manually confirm the image by zooming in on the screen. If it is confirmed that the detachment is not detected, the operator can allow the derailer to detach by entering a password.

[0099] At least some embodiments of this disclosure also provide an electric derailer derailment detection system, such as Figure 6 As shown, it includes:

[0100] Acquisition module 11 is used to acquire the output information of the wheel sensor and image information about the derailer area in response to the upper derailment application signal;

[0101] The automatic locomotive and rolling stock determination module 12 is used to determine whether there are locomotives or rolling stock in the derailment zone based on the output information.

[0102] The derailment identification module 13 is used to analyze and identify the image information when the locomotive and rolling stock determination module determines that there are no locomotives or rolling stock in the derailment area, and to determine whether the electric derailer in the derailer area has been derailed.

[0103] Electric derailer service module 14 is used to allow the electric derailer to detach when the electric derailer to be detached has not been pressed off.

[0104] In some embodiments, such as Figure 6 and Figure 7 As shown, the electric derailer crushing and derailment identification system includes a control host 15 and a video host 16; the acquisition module 11, the locomotive and rolling stock automatic judgment module 12, the crushing and derailment identification module 13, and the electric derailer service module 14 are all located on the control host 15; the video host 16 is used to display the identification image and the identification result.

[0105] Furthermore, wheel sensors 17 and cameras 18 are installed on each track in the inspection area. Wheel sensors 17 collect vehicle wheel information and output it in high and low voltage levels. Cameras 18 collect image information from the derailment area and send it to the electric derailment identification system for recognition. Wheel sensors 17 are connected to wheel detectors 19. Both wheel detectors 19 and cameras 18 are communicatively connected to the derailment identification system. Specifically, wheel detectors 19 and cameras 18 are connected to the communication cabinet 20 via a field communication CAN bus, and then converted by a communication conversion device (fiber optic switch) to connect to the fiber optic network. Finally, the collected output information and image information are transmitted to the derailment identification system for recognition.

[0106] In some embodiments, the depressurization identification system is installed in the on-site train inspection duty room to facilitate monitoring by duty personnel and to take appropriate action based on the identification results.

[0107] At least some embodiments of this disclosure also provide an electronic device, such as Figure 8 As shown, the electronic device includes a memory 21 and a processor 22. The memory 21 stores a computer program that, when executed by the processor, performs the steps of the identification method provided in any embodiment of this disclosure.

[0108] In some embodiments, processor 22 is used to perform all or part of the steps in the identification method as described in any embodiment of this disclosure. Memory 21 is used to store various types of data, which may include, for example, instructions for any application or method in an electronic device, as well as application-related data.

[0109] The processor 22 may be implemented as an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field-programmable gate array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, and is used to execute the identification method in Embodiment 1 above.

[0110] The memory 21 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0111] At least some embodiments of this disclosure also provide a computer-readable storage medium, such as Figure 9 As shown, the readable storage medium stores a computer program 31, which, when executed by a processor, implements the steps of the identification method provided in any embodiment of this disclosure.

[0112] In some embodiments, the storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0113] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0114] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0115] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0116] This invention also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the identification method provided in any embodiment of this disclosure.

[0117] In summary, the electric derailer derailment identification method, system, equipment, and storage medium provided in this application can automatically identify whether there are locomotives or rolling stock in the derailer area. When locomotives or rolling stock are present, the derailer is not allowed to derail, ensuring construction safety. When there are no locomotives or rolling stock, image recognition technology is further used to determine the occupancy status of the derailer area, to determine whether derailment has occurred, and to allow the derailer to derail if it has not occurred. This achieves automated identification of derailment, ensures the accuracy of electric derailer derailment identification, reduces safety hazards, and protects the safety of train inspection personnel.

[0118] The various embodiments in this disclosure are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0119] The scope of protection of this disclosure is not limited to the embodiments described above. Obviously, those skilled in the art can make various modifications and variations to this disclosure without departing from its scope and spirit. If such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, then the intent of this disclosure also includes such modifications and variations.

Claims

1. A method for identifying the derailment of an electric derailer, characterized in that, include: In response to the derailment request signal, acquire the output information of the wheel sensors and image information about the derailment area; Based on the output information, determine whether there are locomotives or vehicles in the derailment zone; When there are no locomotives or vehicles in the derailment area, the image information is analyzed and identified to determine whether the electric derailment device in the derailment area has been derailed. If the electric derailer is not derailed, then the electric derailer is allowed to derail. The top edge of the derailment area is located at the edge of the adjacent track sleeper, and the bottom edge is located at the edge of the track sleeper, that is, the derailment area is a diamond-shaped area; The step of analyzing and identifying the image information to determine whether the electric derailer in the derailer area has been derailed includes: Preset image templates for the feature locations of the rails; The image information is processed to obtain a comparison image for comparison. The comparison image is compared with the image template to determine the similarity between the comparison image and the image template; The similarity is compared with a preset threshold. When the similarity is greater than the preset threshold, the comparison is considered successful, and it is determined that the electric derailer has not been derailed.

2. The electric derailment device derailment identification method according to claim 1, characterized in that, The step of determining whether there are locomotives or vehicles in the derailment zone based on the output information includes: The output information is used to identify the direction of travel of the train wheels and the number of wheels passing by. The axle counting information within the derailment zone is determined based on the direction of travel of the train wheels and the number of wheels passing through. The presence of locomotives or vehicles in the derailment zone is determined based on the axle counting information.

3. The electric derailment device derailment identification method according to claim 2, characterized in that, The step of determining whether there are locomotives or rolling stock in the derailment zone based on the axle counting information includes: When the axle counting information indicates that the number of axles in the derailment zone is zero, it is determined that there are no locomotives or rolling stock in the derailment zone. When the axle counting information indicates that the number of axles in the derailer is not zero, it is determined that there are locomotives and vehicles in the derailer zone.

4. The electric derailment device derailment identification method according to claim 3, characterized in that, When the axle counting information shows that the number of axles in the derailment zone increases over time, it is determined that the locomotives and rolling stock in the derailment zone have entered the derailment zone; when the axle counting information shows that the number of axles in the derailment zone decreases over time, it is determined that the locomotives and rolling stock in the derailment zone have left the derailment zone.

5. The electric derailment device derailment identification method according to claim 1, characterized in that, The step of comparing the similarity with a preset threshold includes: The color mode of the current image is determined based on the comparison image; the color mode includes color mode and black and white mode. When the comparison image is in color mode, the preset threshold is 97%, that is, when the similarity is greater than 97%, the comparison is determined to be successful, and it is determined that the electric derailer has not been derailed. When the comparison image is in black and white mode, the preset threshold is 98%. That is, when the similarity is greater than 98%, the comparison is considered successful, and it is determined that the electric derailer has not been derailed.

6. The electric derailment device derailment identification method according to claim 1, characterized in that, The process of processing the image information to obtain a comparison image for comparison includes: The image information is subjected to grayscale conversion, sharpening, filtering, contrast enhancement, edge detection, and binarization to obtain a comparison image.

7. The electric derailment device derailment identification method according to claim 6, characterized in that, The grayscale processing uses a weighted average method; the sharpening processing uses a high-pass filter to process the image information; the filtering processing uses median filtering; the contrast enhancement processing classifies the value of each pixel according to a set threshold and increases the image contrast by reducing the number of layers; the edge detection processing includes: defining the edge as the boundary of a region in the image where the grayscale changes drastically; using local image differentiation technology to obtain an edge detection operator; and constructing an edge detection operator from a small neighborhood of pixels in the original image to perform edge detection; the binarization processing uses local adaptive binarization to set a reasonable threshold.

8. The electric derailment device derailment identification method according to claim 1, characterized in that, The derailment zone is defined as the area from 15m inside the derailment to 3m outside the derailment.

9. An electric derailleur press-off recognition system, characterized by, include: The acquisition module is used to acquire the output information of the wheel sensors and image information about the derailer area in response to the upper derailment application signal; The automatic locomotive and rolling stock determination module is used to determine whether there are locomotives or rolling stock in the derailment zone based on the output information. The derailment identification module is used to analyze and identify the image information when the locomotive and rolling stock automatic judgment module determines that there are no locomotives or rolling stock in the derailment area, and to determine whether the electric derailer in the derailer area has been derailed. The electric derailer service module is used to allow the electric derailer to detach when the requested derailer has not been pressed off. The top edge of the derailment area is located at the edge of the adjacent track sleeper, and the bottom edge is located at the edge of the track sleeper, that is, the derailment area is a diamond-shaped area; The step of analyzing and identifying the image information to determine whether the electric derailer in the derailer area has been derailed includes: Preset image templates for the feature locations of the rails; The image information is processed to obtain a comparison image for comparison. The comparison image is compared with the image template to determine the similarity between the comparison image and the image template; The similarity is compared with a preset threshold. When the similarity is greater than the preset threshold, the comparison is considered successful, and it is determined that the electric derailer has not been derailed.

10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the identification method according to any one of claims 1 to 8.

11. A computer readable storage medium, on which a computer program is stored, characterized in that, When the computer program is executed by a processor, it implements the steps of the identification method as described in any one of claims 1 to 8.

Images