Rail inspection equipment and rail inspection vehicle

Abstract

The embodiment of the invention provides track inspection equipment which comprises an equipment body, and the equipment body is provided with an image acquisition module used for acquiring surface image information and three-dimensional structure information of a steel rail; the main control module is connected with the image acquisition module and is used for processing the steel rail image data acquired by the image acquisition module in real time and giving an alarm according to a processing result; and the network communication module is connected with the main control module and is used for uploading a processing result of the main control module to an upper computer. The surface image information and the three-dimensional structure information of the steel rail are acquired through the image acquisition module, and the main control module processes the steel rail image data of the image acquisition module and gives an alarm according to the processing result; meanwhile, a processing result is uploaded to the upper computer; the image acquisition module covers the steel rails on the two sides of the railway line, defects of the steel rails are detected in real time, the inspection efficiency and accuracy are improved, and the risks of manual false detection and missing detection are reduced.

Description

Technical Field

[0001] The present application relates to the field of track inspection technology, and in particular, to a track inspection device and a track inspection vehicle. Background Art

[0002] The inspection of railway lines is mainly to ensure the safe operation of railways. Traditional inspection methods mainly rely on manual inspection, which is not only time-consuming and labor-intensive, but also has the risk of missed inspections and false inspections. In order to solve these problems, an intelligent inspection and collection device that can improve the efficiency and accuracy of inspections is needed. The inspection equipment for railway lines using graphics and image processing and computer vision technology can automatically and quickly detect the status of the track, shorten the maintenance time, ensure the personal safety of line inspectors, reduce labor input, and achieve cost reduction and efficiency improvement through standardized inspections. It also meets the requirements of speed increase and high-density driving, and also ensures the safe operation of trains after speed increase, which has great economic and social significance.

[0003] At present, the line inspection of each maintenance section of the railway bureau mainly relies on nighttime window period operations, using various types of equipment for measurement and testing and manual inspection. The status of rails and fastener systems mainly relies on manual visual inspection and tapping inspection, which is inefficient and has a certain possibility of underreporting. The inspection results cannot be accurately recorded and cannot be digitized. The manual inspection method can no longer meet the rapid growth needs of railway lines. The efficiency, reliability and accuracy of traditional inspection equipment need to be improved; the impact of the environment, personnel quality, safety protection, etc. should be reduced as much as possible; line environmental data should be introduced, the inspection results should be compared and analyzed and compared with the original line data, fault warning should be given, and perception-based state repair should be realized. Summary of the invention

[0004] The embodiments of the present application provide a track inspection device and a track inspection vehicle to solve the problem that the existing track inspection mainly relies on manual inspection, which is inefficient and lacks reliability.

[0005] In order to achieve the above objectives, this application provides the following technical solutions:

[0006] A track inspection device, comprising a device body, wherein the device body has:

[0007] Image acquisition module, used to collect surface image information and three-dimensional structure information of the rail;

[0008] A main control module, connected to the image acquisition module, for processing the rail image data acquired by the image acquisition module in real time and giving an alarm according to the processing result;

[0009] The network communication module is connected to the main control module and uploads the processing result of the main control module to the host computer.

[0010] Optionally, the image acquisition module includes:

[0011] 2D color camera, used to collect surface image information of rails;

[0012] 3D camera, used to collect three-dimensional structural information of rails;

[0013] The 2D color camera and the 3D camera are connected to the main control module respectively.

[0014] Optionally, there are two 3D cameras, and the two 3D cameras are symmetrically arranged on both sides of a center line of the device body.

[0015] Optionally, the 2D color camera is located at the center of the device body and is used to collect surface image information of the rail.

[0016] Optionally, the main control module includes:

[0017] An analysis and processing unit, used for acquiring the rail image data acquired by the image acquisition module in real time, processing the rail image data according to a traditional image processing algorithm and / or a deep learning image recognition algorithm, and executing preliminary control decisions;

[0018] The edge computing unit is connected to the analysis and processing unit, and is used to receive and process the data of the analysis and processing unit, perform image recognition and defect analysis according to the image algorithm of deep reinforcement learning, and issue an alarm according to the image processing result.

[0019] Optionally, the edge computing unit includes:

[0020] A microprocessor and memory are used to perform graphics data processing and execute control decisions.

[0021] Optionally, it also includes:

[0022] An electrical control module and a power management system, wherein one end of the electrical control module is connected to the power management system, and the other end is respectively connected to the image acquisition module, the main control module and the network communication module.

[0023] Optionally, it also includes:

[0024] The data storage module is connected to the main control module and is used to store the collected rail image data and processing results.

[0025] Optionally, the network communication module includes an Ethernet interface and a wireless communication module, and the Ethernet interface and the wireless communication module are respectively connected to the main control module.

[0026] The present application also provides a track inspection vehicle, comprising the track inspection equipment described in any one of the above embodiments.

[0027] A track inspection device provided in an embodiment of the present application includes a device body, which has: an image acquisition module, which is used to acquire surface image information and three-dimensional structure information of a rail; a main control module, which is connected to the image acquisition module and is used to process the rail image data acquired by the image acquisition module in real time and issue an alarm based on the processing result; and a network communication module, which is connected to the main control module and uploads the processing result of the main control module to a host computer.

[0028] Compared with the prior art, the track inspection equipment and track inspection vehicle provided in the embodiments of the present application have the following technical effects:

[0029] In the present application, the surface image information and three-dimensional structure information of the rails are collected through the image acquisition module, the main control module processes the above-mentioned rail image data of the image acquisition module, and issues an alarm based on the processing result; at the same time, the processing result is uploaded to the host computer; the image acquisition module covers the rails on both sides of the railway line, detects the defects of the rails in real time, improves the inspection efficiency and accuracy, and reduces the risk of human misdetection and missed detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0031] Figure 1 A schematic diagram of the appearance structure of a track inspection device provided in an embodiment of the present application;

[0032] Figure 2 A schematic diagram of the internal structure of a track inspection device provided in an embodiment of the present application.

[0033] The following are marked in the accompanying drawings:

[0034] Track inspection equipment 100;

[0035] Device body 1, 3D camera 11, 2D color camera 12, electrical control module 13, network communication module 14, edge computing unit 15. DETAILED DESCRIPTION

[0036] The embodiment of the invention discloses a track inspection device and a track inspection vehicle, so as to solve the problem that the existing track inspection mainly relies on manual inspection, has low efficiency and insufficient reliability.

[0037] In order to make the technical solutions and advantages in the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than an exhaustive list of all the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0038] See also Figure 1-2 , Figure 1 A schematic diagram of the appearance and structure of a track inspection device 100 provided in an embodiment of the present application; Figure 2 A schematic diagram of the internal structure of a track inspection device 100 provided in an embodiment of the present application.

[0039] In a specific embodiment, the track inspection device 100 provided in the present application includes a device body 1, and the device body 1 has an image acquisition module, a main control module, a network communication module 14, an electrical control module 13, a data storage module and a power management system; wherein, the image acquisition module is used to collect surface image information and three-dimensional structural information of the rail, and the image acquisition module includes a 2D color camera 12 and a 3D camera 11, which are respectively connected to the main control module, and the 2D color camera 12 is used to collect surface image information of the rail and directly observe the surface condition of the rail; its resolution is not less than 1920x1080 to ensure image clarity. The frame rate is above 30fps to achieve stable image acquisition of fast-moving vehicles or detection equipment. An industrial-grade camera is used with dust-proof and shock-proof design to adapt to different environmental conditions. The 3D camera 11 is used to collect the three-dimensional structural information of the rail to accurately measure the shape parameters of the rail. It is based on structured light or laser scanning technology with high accuracy and an error below the sub-millimeter level. Capturing the three-dimensional structural information of the track surface can be used to identify problems such as wear and depression of the track; and it has a high dynamic range (HDR) and can work stably under different lighting conditions. The camera can adapt to the working environment under different lighting conditions, improve image quality, and reduce detection errors caused by sudden changes in light. Specifically, there are two 3D cameras 11, and the two 3D cameras 11 are symmetrically arranged on both sides of the center line of the device body 1; the 2D color camera 12 is located at the center of the device body 1 and is used to collect surface image information of the rail.

[0040] In this specific embodiment, the main control module includes an analysis and processing unit and an edge computing unit 15, and the edge computing unit 15 is connected to the analysis and processing unit; the analysis and processing unit collects the rail image data collected by the image acquisition module in real time, processes the rail image data according to the traditional image processing algorithm and / or the deep learning image recognition algorithm, and executes the preliminary control decision; the specific preliminary control decision is that the analysis and processing unit controls the sensors on the equipment, such as temperature and humidity sensors, to collect data. The analysis and processing unit integrates the data analysis algorithm, processes the collected rail image data, and automatically detects various defects of the rail, such as marking potential defect areas, recording abnormal data, etc. The preliminary decision results can be used for instant feedback, such as immediately alarming when serious defects are detected. The specific algorithm can include a traditional image processing algorithm and an image recognition algorithm based on deep learning, a parallel computing framework based on CPU / GPU, such as TensorFlow Lite, OpenCV, optimizes the processing speed, provides edge machine learning capabilities, can train and reason models on the device side, and improves autonomous analysis capabilities. It can be understood that the above algorithms and software parts can be set according to the technical development in this field, and the improvement of this application lies in the connection relationship between the modules. Preferably, the analysis and processing unit may be specifically a PLC controller.

[0041] In another embodiment, the edge computing unit 15 includes a microprocessor and a memory for performing image data processing and executing control decisions; the microprocessor can be specifically an embedded computing unit, such as an ARM processor with a GPU or a low-power industrial-grade computing device, equipped with a high-performance CPU and GPU for advanced image recognition and defect analysis; so as to be able to process image and sensor data in real time, avoid processing delays due to data transmission delays, and improve inspection efficiency. By utilizing the GPU of the microprocessor, the parallel processing capability is greatly improved, and image recognition and defect analysis operations can be completed quickly; the processing speed is improved; the processing results are fed back in real time to ensure immediate alarm and processing of faults. The edge computing unit 15 uses a deep reinforcement learning (DRL) algorithm to perform advanced analysis of the image, identify and classify various defects of the rail, such as cracks, wear, corrosion, etc.; according to the output of the deep reinforcement learning algorithm, the defects are analyzed in detail to assess the severity and scope of the defects; according to the defect analysis results, the edge computing unit 15 can trigger an alarm in real time to notify relevant personnel to conduct inspections and repairs; record alarm information, including time, location, defect type and severity, and generate reports for subsequent analysis and management.

[0042] Optionally, one end of the electrical control module 13 is connected to the power management system, and the other end is connected to the image acquisition module, the main control module, the data storage module and the network communication module 14 respectively; the power distribution of the equipment is managed; the electrical control module 13 adopts a modular design to facilitate maintenance and upgrading.

[0043] In one embodiment, the data storage module is connected to the main control module to store the collected rail image data and processing results. It uses an industrial-grade solid-state hard drive (SSD) to meet the needs of large-capacity data storage, with a capacity of 1TB or more, so as to store long-term and large amounts of inspection data. It has a built-in double-write mechanism and RAID technology to back up data in real time to ensure data security and system reliability. The data storage unit has a self-repair function to further improve the system's fault tolerance and ensure data security and integrity.

[0044] The network communication module 14 includes an Ethernet interface and a wireless communication module, which are respectively connected to the main control module for data transmission and remote control; the Ethernet interface adopts an industrial Ethernet interface, such as Gigabit Ethernet, to ensure the stability of large data transmission; no communication module is required to support 4G / 5G networks, to achieve remote data transmission, and to support dual-mode communication to improve communication reliability. At the same time, the network communication module 14 uses advanced encryption algorithms such as AES-256 for data encryption transmission to ensure that data is not stolen or tampered with during transmission; the communication link adopts a two-way authentication mechanism to prevent unauthorized access and communication hijacking. Using lightweight protocols such as MQTT or CoAP is suitable for the data transmission needs of IoT devices, with low bandwidth occupancy and low latency.

[0045] In a specific embodiment, the device housing is designed with an industrial-grade protective shell that is shockproof, dustproof, and moisture-proof to ensure that the device can operate stably in various harsh environments. The internal components of the device housing are fixed by shock-absorbing materials, and the device housing is made of impact-resistant materials to ensure that it will not be damaged when operating in a bumpy environment. The device housing meets the IP67 or higher protection level to prevent dust and moisture from entering the interior of the device; ensure that the device can operate stably in various harsh environments (such as high temperature, low temperature, vibration, and humidity). The functional modules are connected through standard interfaces. Users can replace or upgrade each module according to specific needs, such as cameras, computing units, communication modules, etc., to adapt to different application scenarios and performance requirements; the device supports the access of multiple sensors and peripherals, such as temperature sensors, ultrasonic sensors, etc., which expands the functional range of the equipment and improves the comprehensiveness of the inspection process.

[0046] At the same time, the system is equipped with a graphical user interface (GUI) for easy operation. Users can monitor the device status and inspection data in real time through a local display or wireless terminal (such as a tablet computer or mobile phone), which is convenient for operation and management. The network communication module 14 supports remote maintenance and firmware update functions. Technicians can check, debug and update the software of the device through remote connection, reducing maintenance costs and time.

[0047] The above-mentioned equipment has many original features such as high integration, high performance, strong environmental adaptability, safety and reliability, intelligent analysis, and multi-functional expansion. It can significantly improve the efficiency and accuracy of railway line inspections and provide strong guarantees for safe railway operations.

[0048] The specific operation steps of the track inspection device 100 include:

[0049] 1. Device installation and initialization:

[0050] a. Installation:

[0051] The track inspection device 100 is securely mounted in the carriage of a large track inspection vehicle, or mounted on a small mobile inspection device.

[0052] Make sure that the 2D color camera 12 and the 3D camera 11 can cover both the left and right sides of the track.

[0053] Connect the electrical control module 13 and the power management system to the power supply of the vehicle or mobile device.

[0054] b. Initialization:

[0055] Start the edge computing unit 15 and perform a system self-check to ensure that all sensors and computing units are working properly.

[0056] According to the track inspection task, configure the communication parameters of the network communication module 14 to ensure smooth data transmission.

[0057] Load pre-trained data analysis algorithms into the analysis processing unit.

[0058] 2. Data collection and processing:

[0059] a.2D color camera 12 data acquisition:

[0060] The 2D color camera 12 collects color images of the track surface in real time, and the image has high resolution and can clearly reflect the track surface status.

[0061] The collected data is transmitted to the edge computing unit 15 via wires for preliminary processing to remove interference and noise.

[0062] b. 3D camera 11 data acquisition:

[0063] The 3D camera 11 uses structured light, laser scanning and other technologies to obtain the three-dimensional structural information of the track in real time, including the shape, contour and size parameters of the track.

[0064] The collected three-dimensional data is transmitted to the edge computing unit 15 via wires for preliminary processing to generate a three-dimensional model of the track.

[0065] c.Data fusion and storage:

[0066] The edge computing unit 15 fuses the 2D image data and the 3D structure data to form a full-scale, multi-angle track data set.

[0067] · Storage unit The large-capacity storage device saves the data that has been preliminarily processed and integrated to ensure that the data will not be lost.

[0068] d. Real-time analysis and identification:

[0069] The analysis and processing unit uses pre-loaded efficient algorithms to analyze the collected data in real time and identify various defects of the track, such as cracks, deformation, wear, etc.

[0070] Through artificial intelligence and machine learning technologies, the analysis and processing unit can automatically label and classify defect types and assess the severity of defects.

[0071] 3. Data transmission and report generation:

[0072] a. Data transmission:

[0073] The network communication module 14 transmits the processed data to the remote control center via wireless (such as 4G / 5G network) or wired (such as Ethernet).

[0074] Ensure timely and reliable data transmission to avoid data loss or delay.

[0075] b. Report Generation:

[0076] After receiving the data, the server in the remote control center will further analyze and summarize the data.

[0077] Generate detailed inspection reports, including track defect location, type, severity and other information.

[0078] Inspection reports can be presented in a variety of formats, such as text, charts, 3D models, etc., and can also be generated in PDF and other document formats as needed.

[0079] 4. Maintenance and upgrade:

[0080] a. Regular maintenance:

[0081] Regularly inspect and maintain the track inspection device 100 to ensure that components such as the camera, edge computing unit 15, electrical control module 13, and network communication module 14 are working properly.

[0082] Clean the camera lens.

[0083] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0084] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A track inspection device, characterized in that: The device comprises a device body, wherein the device body has: Image acquisition module, used to collect surface image information and three-dimensional structure information of the rail; A main control module, connected to the image acquisition module, for processing the rail image data acquired by the image acquisition module in real time and giving an alarm according to the processing result; The network communication module is connected to the main control module and uploads the processing result of the main control module to the host computer.

2. The track inspection equipment according to claim 1, characterized in that: The image acquisition module comprises: 2D color camera, used to collect surface image information of rails; 3D camera, used to collect three-dimensional structural information of rails; The 2D color camera and the 3D camera are connected to the main control module respectively.

3. The track inspection equipment according to claim 2, characterized in that: The number of the 3D cameras is two, and the two 3D cameras are symmetrically arranged on both sides of the center line of the device body.

4. The track inspection equipment according to claim 2, characterized in that: The 2D color camera is located at the center of the device body and is used to collect surface image information of the rail.

5. The track inspection equipment according to claim 1, characterized in that: The main control module comprises: An analysis and processing unit, used for acquiring the rail image data acquired by the image acquisition module in real time, processing the rail image data according to a traditional image processing algorithm and / or a deep learning image recognition algorithm, and executing preliminary control decisions; The edge computing unit is connected to the analysis and processing unit, and is used to receive and process the data of the analysis and processing unit, perform image recognition and defect analysis according to the image algorithm of deep reinforcement learning, and issue an alarm according to the image processing result.

6. The track inspection equipment according to claim 5, characterized in that: The edge computing unit comprises: A microprocessor and memory are used to perform graphics data processing and execute control decisions.

7. The track inspection equipment according to claim 1, characterized in that: Also includes: An electrical control module and a power management system, wherein one end of the electrical control module is connected to the power management system, and the other end is respectively connected to the image acquisition module, the main control module and the network communication module.

8. The track inspection equipment according to claim 1, characterized in that: Also includes: The data storage module is connected to the main control module and is used to store the collected rail image data and processing results.

9. The track inspection equipment according to claim 1, characterized in that: The network communication module includes an Ethernet interface and a wireless communication module, and the Ethernet interface and the wireless communication module are respectively connected to the main control module.

10. A track inspection vehicle, characterized in that: The invention comprises the track inspection equipment as described in any one of claims 1 to 9.

Images