Experimental platform for simulating track fault detection

Abstract

The present invention relates to an experimental platform for simulating track fault detection, comprising: a simulated track; a track inspection trolley placed on the simulated track; a positioning unit and a gyroscope mounted on the trolley; an image acquisition unit mounted on the bottom of the trolley, comprising a track profile detection module, a rail surface detection module, a fastener detection module, and a sleeper detection module; each module comprising an area array camera, a light source laser with a built-in optical encoding module, a signal controller, and an FPGA for filtering out interference light from ambient light, decoding the optical signal, and digitally converting the optical signal and image information to obtain three-dimensional point cloud data of the object surface; and a host computer connected to the power unit of the trolley, comprising a built-in storage module and a normalization processing module for normalizing the three-dimensional point cloud data and geometric parameter data sent by the gyroscope. The present invention enables detection of rail profile status, rail surface and fastener status, sleeper status, and track geometric parameters with a low false detection rate and high detection accuracy.

Description

Technical Field

[0001] The present invention belongs to the field of rail transportation technology, and relates to rail train detection technology, in particular to an experimental platform for simulating rail fault detection. Background Art

[0002] Urban rail transit plays an increasingly important role in guiding and supporting urban development, meeting public mobility needs, alleviating traffic congestion, and reducing air pollution. At the same time, with the rapid growth of operating mileage and passenger volume, the pressure and challenges of safe operation of urban rail transit are also increasing. The increase in construction mileage and increasingly busy lines are increasing the dynamic forces acting on the wheels and rails of trains. These dynamic forces can cause various hazards, such as track irregularities, surface wear, peeling, block loss, loose and missing fasteners, and damaged sleepers. These hazards can lead to derailments and overturnings of high-speed trains.

[0003] Traditional manual inspection methods are no longer sufficient for such a large number of rail transit lines, and intelligent track inspection systems that replace manual inspections with machines have emerged. However, judging from the existing products on the market, only a few manufacturers have commercialized track inspection system products, and the coverage of these products is limited. One of the reasons for this is that when the track inspection system is actually applied on the line, there is a difference between the on-site conditions and the algorithm processing model preset in the system, resulting in unsatisfactory application results. At the same time, the vehicle-mounted track inspection systems currently used on the market still have the following problems:

[0004] The vehicle body vibrates, affecting the imaging.

[0005] The track surface reflects sunlight and interferes with imaging.

[0006] The use of black and white 2D imaging has poor detection effect and lacks image depth information, resulting in a high false detection rate.

[0007] Systems capable of detecting three-dimensional track information have low applicability when train speeds are high. Summary of the Invention

[0008] In view of the above-mentioned problems of the prior art such as high false detection rate and low detection accuracy, the present invention provides an experimental platform for simulated track fault detection with low false detection rate and high detection accuracy.

[0009] In order to achieve the above objectives, the present invention provides an experimental platform for simulating track fault detection, comprising:

[0010] Simulated tracks;

[0011] Track inspection trolley, placed on the simulated track;

[0012] The positioning unit is installed on the body of the track inspection trolley and is used to locate the position of the track inspection trolley;

[0013] The gyroscope is installed on the track inspection vehicle between the two wheels and rails of the simulated track to detect track geometric parameters;

[0014] The image acquisition unit is installed at the bottom of the track inspection trolley. The image acquisition unit includes a rail profile detection module for acquiring wheel-rail profile images, a rail surface detection module for acquiring wheel-rail surface images, a fastener detection module for acquiring wheel-rail fastener images, and a sleeper detection module for acquiring sleeper images. Each module includes:

[0015] An area array camera is used to obtain images of the object;

[0016] A light source laser is installed at the front end of the area array camera and is used to emit light of a set wavelength when the area array camera acquires an image. The light source laser is equipped with an optical encoding module for encoding the emitted light of the set wavelength;

[0017] The signal controller is used to control the operation of the area array camera and light source laser according to the real-time speed of the track inspection vehicle;

[0018] FPGA, used to filter out interference light from the ambient light in the image acquired by the array camera based on light coding, perform optical decoding on the filtered light signal, and digitally convert the light signal and image information to obtain three-dimensional point cloud data of the surface of the object being photographed;

[0019] The host computer is connected to the power unit of the track inspection trolley to control the movement of the track inspection trolley. The host computer is equipped with:

[0020] The normalization processing module is used to normalize the three-dimensional point cloud data sent by the FPGA and the track geometry parameter data sent by the gyroscope through a normalization algorithm to eliminate the jitter caused by the vibration of the vehicle body;

[0021] The storage module is used to store the data processed by the normalization processing module and the position information of the track inspection vehicle.

[0022] Preferably, the simulated track includes a bracket, a wheel rail mounted on the bracket, and a sleeper arranged below the wheel rail.

[0023] Preferably, the total length of the simulated track is at least 8m, providing a travel distance of at least 5m for the track inspection trolley, and the wheel rails are standard 50 rails, with a spacing of 1435mm between the two wheel rails.

[0024] Furthermore, the brackets at both ends of the wheel rail are provided with limit pieces to prevent the track inspection trolley from running out of bounds.

[0025] Preferably, the rail surface detection module is installed at the bottom of the track inspection trolley, directly above the top surface of the wheel-rail of the simulated track; the track profile detection module is installed at both sides of the bottom of the track inspection trolley, corresponding to the wheel-rail position of the simulated track, and located on both sides of the rail surface detection module; the fastener detection module is installed at the bottom of the track inspection trolley, directly above the top surface of the wheel-rail of the simulated track, and is integrated with the rail surface detection module in a module box; the sleeper detection module is installed at the bottom of the track inspection trolley, between the two wheel-rails of the simulated track.

[0026] Preferably, the track profile detection module on each side includes two track profile detection modules, and the two track profile detection modules on the same side are installed at an angle of 68°.

[0027] Preferably, the FPGA is equipped with:

[0028] A split camera memory module is used to filter out interference light from ambient light in images acquired by the array camera based on light coding;

[0029] An optical decoding module, used for optically decoding the image after filtering out interference light;

[0030] The digital conversion processing module is used to perform digital conversion processing on the image after optical decoding to obtain three-dimensional point cloud data of the surface of the object being photographed.

[0031] Furthermore, it also includes a transverse connecting piece, and the image acquisition unit is installed on the bottom of the track inspection trolley through the transverse connecting piece.

[0032] Preferably, the track inspection vehicle comprises:

[0033] vehicle body;

[0034] The driving wheel is located below the front end of the vehicle body and is connected to the power device on the vehicle body through a chain;

[0035] A driven wheel is provided below the rear end of the vehicle body, and the driven wheel is a standard wheel pair;

[0036] Wheel encoder, installed on the output shaft of the power unit or the driving wheel output shaft or the driven wheel output shaft, is used to collect the real-time speed of the track inspection trolley;

[0037] The power supply / IO trigger device is located at the upper rear end of the vehicle body and is connected to the image acquisition unit, the host computer and the wheel codec respectively. It is used to power the image acquisition unit and, after receiving the acquisition command sent by the host computer, convert the real-time vehicle speed provided by the wheel encoder into pulse information corresponding to each module and send it to the signal controller. The signal controller controls the operation of the area array camera and light source laser of the corresponding module according to the pulse information corresponding to different modules.

[0038] Furthermore, it also includes a wire trough provided on one side of the simulation track, and the cables connecting the image acquisition unit, the positioning unit, the gyroscope and the power supply / IO trigger device with the host computer are placed in the wire trough.

[0039] Compared with the prior art, the advantages and positive effects of the present invention are:

[0040] (1) The experimental platform of the present invention can simulate various track faults and realize fault detection of rail profile status, rail surface status, fastener status, sleeper status and track geometric parameters under the condition of the maximum train operating speed of 80km / h, with low false detection rate and high detection accuracy.

[0041] (2) The experimental platform of the present invention adopts an image acquisition unit using an array camera and a light source laser equipped with an optical coding module. It automatically filters out ambient light interference through laser triangulation and optical coding and decoding technology to obtain a three-dimensional image of the track object. The data is converted into three-dimensional point cloud data. The converted three-dimensional point cloud data not only has the two-dimensional information of the image, but also has the depth of field information of the distance between the acquired object and the camera, thereby improving the accuracy of fault location and identification.

[0042] (3) The experimental platform of the present invention uses normalization processing to eliminate the jitter caused by the vibration of the vehicle body. It is necessary to install vibration compensation to directly output high-precision detection information.

[0043] (4) The experimental platform of the present invention uses a high-speed array camera with a frame rate of 25K combined with FPGA front-end processing to achieve the detection requirement of 80km / h.

[0044] (5) The present invention uses an RFID antenna as a positioning device for the rail, which can accurately locate the fault based on the detection results of the experimental platform in combination with the wheel encoder. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a schematic diagram of the structure of an experimental platform for simulating track fault detection according to an embodiment of the present invention;

[0046] Figure 2-3 This is a schematic structural diagram of the simulated track according to an embodiment of the present invention;

[0047] Figure 4 This is a schematic structural diagram of the track inspection vehicle according to an embodiment of the present invention;

[0048] Figure 5-6 This is a schematic diagram of the structure of the track inspection trolley with the back cover opened according to an embodiment of the present invention;

[0049] Figure 7 for Figure 6 Enlarged view of part A;

[0050] Figure 8-9This is a schematic diagram of the installation of the image acquisition unit according to an embodiment of the present invention;

[0051] Figure 10 This is a control principle block diagram of the experimental platform for simulating track fault detection according to the present invention;

[0052] Figure 11 This is a structural block diagram of each module described in the present invention;

[0053] Figure 12 Schematic diagram of the field of view and depth of field of the area array camera in the track profile detection module of the present invention;

[0054] Figure 13 Schematic diagram of the field of view and depth of field of the area array camera in the rail surface inspection module of the present invention;

[0055] Figure 14 Schematic diagram of the field of view and depth of field of the area array camera in the fastener detection module of the present invention;

[0056] Figure 15 Schematic diagram of the field of view and depth of field of the area array camera in the sleeper detection module of the present invention.

[0057] In the figure, 1. Simulated track, 101. Bracket, 102. Wheel rail, 103. Sleeper, 2. Track inspection trolley, 201. Car body, 202. Power unit, 203. Driving wheel, 204. Driven wheel, 205. Wheel encoder, 206. Power supply / IO trigger device, 207. Back cover, 3. Positioning unit, 4. Gyroscope, 5. Image acquisition unit, 6. Track profile detection module, 7. Rail surface detection module, 8. Fastener detection module, 9. Sleeper detection module, 10. Area array camera, 11. Light source laser, 1101. Optical encoding module, 12. Signal controller, 13. FPGA, 1301. Split camera memory module, 1302. Optical decoding module, 1303. Digital conversion processing module, 14. Host computer, 1401. Normalization processing module, 1402. Storage module, 15. Limiting piece, 16. Horizontal connecting piece, 17. Wire duct, 18. Anti-collision alarm. DETAILED DESCRIPTION

[0058] The present invention is described in detail below by way of exemplary embodiments, but it should be understood that elements, structures, and features of one embodiment may be beneficially combined in other embodiments without further description.

[0059] In the description of the present invention, it should be noted that the terms "upper," "lower," "left," "right," "top," "bottom," "front," and "back" and the like, indicating positions or relationships, are based on the positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0060] Example: See Figure 1-11 This embodiment provides an experimental platform for simulating track fault detection, including:

[0061] Simulation track 1;

[0062] Track inspection trolley 2 is placed on the simulated track 2;

[0063] The positioning unit 3 is installed on the body 201 of the track inspection vehicle 2 and is used to locate the position of the track inspection vehicle 2;

[0064] The gyroscope 4 is mounted on the vehicle body 201 of the track inspection vehicle 2 between the two wheel rails 102 of the simulated track 1 and is used to detect track geometric parameters;

[0065] The image acquisition unit 5 is installed at the bottom of the track inspection trolley 1. The image acquisition unit includes a track profile detection module 6 for acquiring wheel-rail profile images, a rail surface detection module 7 for acquiring wheel-rail surface images, a fastener detection module 8 for acquiring wheel-rail fastener images, and a sleeper detection module 9 for acquiring sleeper images. Each module includes:

[0066] An area array camera 10 is used to acquire an image of a photographed object;

[0067] The light source laser 11 is installed at the front end of the area array camera 10 and is used to emit light of a set wavelength when the area array camera 10 acquires an image. The light source laser 11 is equipped with an optical encoding module 1101 for encoding the emitted light of the set wavelength;

[0068] The signal controller 12 is used to control the operation of the area array camera 10 and the light source laser 11 according to the real-time speed of the track inspection vehicle;

[0069] FPGA 13 is used to filter out interference light from the ambient light in the image acquired by the array camera 10 according to the optical coding, perform optical decoding on the filtered light signal, and perform digital conversion processing on the light signal and image information to obtain three-dimensional point cloud data of the surface of the object being photographed;

[0070] The host computer 14 is connected to the power unit 202 of the track inspection trolley 2 to control the movement of the track inspection trolley 2; the host computer is equipped with:

[0071] Normalization processing module 1401 is used to normalize the three-dimensional point cloud data sent by FPGA 13 and the track geometry parameter data sent by gyroscope 4 (including basic information data such as lateral acceleration, vertical acceleration, three-axis inclination, and rotational angular velocity) through a normalization algorithm to eliminate jitter caused by vehicle body vibration;

[0072] The storage module 1402 is used to store the data processed by the normalization processing module 1401 and the position information of the track inspection vehicle 2.

[0073] The present invention uses a combination of an area array camera and a light source laser. The area array camera acquires two-dimensional image information, and a line laser is used for fill-in light to present a segmented line on the imaging target surface of the area array camera. The imaging position of the segmented line on the camera target surface will be different depending on the distance between the surface of the object being photographed and the camera lens. The segmented line collected once is analyzed by FPGA to obtain the depth coordinate information of the collected object surface. The FPGA converts the two-dimensional information and the depth coordinate information into three-dimensional point cloud data, so that the detection result not only has the two-dimensional information of the image, but also has the depth of field information of the distance between the collected object and the camera, thereby improving the accuracy of fault location and identification. It should be noted that when performing fill-in light, the light of the set wavelength emitted by the light source laser is first encoded by the optical coding module to facilitate the subsequent filtering of interference light in the ambient light. The wavelength of the light emitted by the light source laser can be set according to actual needs.

[0074] Specifically, see Figure 2-3 The simulated track includes a bracket 101, a wheel rail 102 installed on the bracket 101, and a sleeper 103 arranged below the wheel rail 102.

[0075] In this embodiment, the total length of the simulated track is 8m, providing a travel distance of 5m for the track inspection trolley. The wheel rail is a standard 50-gauge track, and the spacing between the two wheel rails is 1435mm. It should be noted that the total length of the simulated track is not limited to 8m and can be designed according to the actual site requirements, but it should not be less than 8m, and can also be 9m, 10m, etc. It should also be noted that under laboratory conditions, the simulated track can provide a travel distance of at least 5m for the track inspection trolley. Within the travel range, most common track faults can be designed, such as: scratches and peeling of rail surfaces; loose, missing, or buried fasteners; wear of sleepers, etc.

[0076] In one embodiment, see Figure 1 The brackets 101 at both ends of the wheel rail 102 are provided with limit members 15 to prevent the track inspection trolley from running beyond the boundary. Specifically, the limit member is a limit rod, which prevents the track inspection trolley from running beyond the range of the simulated track through the blocking effect of the limit rod.

[0077] Specifically, see Figure 4-7 and Figure 10 , the track inspection trolley comprises:

[0078] Car body 201;

[0079] The driving wheel 203 is provided below the front end of the vehicle body 201 and is connected to the power device 202 provided on the vehicle body 201 via a chain;

[0080] Driven wheels 204 are provided below the rear end of the vehicle body and are standard wheel sets;

[0081] The wheel encoder 205 is installed on the output shaft of the driven wheel 204 and is used to collect the real-time speed of the track inspection vehicle;

[0082] The power supply / IO trigger device 206 is located at the upper rear end of the vehicle body and is respectively connected to the image acquisition unit, the host computer and the wheel codec. It is used to power the image acquisition unit and, after receiving the acquisition command sent by the host computer, convert the real-time vehicle speed provided by the wheel encoder into pulse information corresponding to each module and send it to the signal controller. The signal controller controls the operation of the area array camera and light source laser of the corresponding module according to the pulse information corresponding to different modules.

[0083] Taking the collection of track profile as an example, the working principle of the power supply / IO trigger device during the detection process is explained. After receiving the track profile collection command sent by the host computer, the power supply / IO trigger device converts the real-time vehicle speed provided by the wheel encoder into a pulse information for the track profile detection module and sends it to the signal controller. The signal controller controls the operation of the area array camera and light source laser in the module according to the pulse information corresponding to the track profile detection module.

[0084] It should be noted that the wheel encoder is not limited to being installed on the output shaft of the driven wheel, and can be installed on the output shaft of the power unit or the output shaft of the driving wheel, and the specific installation is based on actual needs.

[0085] It should also be noted that the track inspection trolley uses a standard wheel pair, and a power device (such as a motor, etc.) is used as the power source to drive the active wheel of the track inspection trolley to rotate. The contact between the driven wheel and the rail is used to simulate the wheel-rail contact scene on the track train line. The matching simulated track uses 50-gauge standard rails. The simulated wheel-rail movement is more realistic. When performing fault identification, the actual wheel-rail contact situation can be fully considered. The collected data is the track status data under real line conditions (excluding environmental factors).

[0086] Specifically, see Figure 6-9The rail surface detection module 7 is installed at the bottom of the track inspection trolley, just above the top surface of the wheel rail of the simulated track; the rail profile detection module is installed on both sides of the bottom of the track inspection trolley, corresponding to the position of the wheel rail of the simulated track, and is located on both sides of the rail surface detection module; the fastener detection module is installed at the bottom of the track inspection trolley, just above the top surface of the wheel rail of the simulated track, and is integrated with the rail surface detection module in a module box; the sleeper detection module is installed at the bottom of the track inspection trolley, between the two wheel rails of the simulated track. For the field of view and depth of field of each module camera, please refer to Figure 12-15 ,In the figure, the unit of field of view and depth of field parameters is: mm.

[0087] In one embodiment, see Figure 9 Each side of the track profile detection module includes two track profile detection modules, which are installed at a 68° angle. The 68° angle between the two track profile detection modules is to accurately collect side information of the rail head.

[0088] In one embodiment, see Figure 8 、 9 The experimental platform also includes a transverse connector 16. The track profile detection module 6, rail surface detection module 7, fastener detection module 8, and sleeper detection module 9 are mounted on the bottom of the track inspection vehicle via the transverse connector 16, located between the driving and driven wheels. It should be noted that the design of the transverse connector is adapted to the design dimensions of the track inspection vehicle. Specifically, in this embodiment, the transverse connector is a crossbeam.

[0089] Specifically, see Figure 10 、 11 , the FPGA 13 is provided with:

[0090] The split camera memory module 1301 is used to filter out interference light from the ambient light in the image acquired by the area array camera according to the light coding;

[0091] An optical decoding module 1302 is used to optically decode the image after filtering out interference light;

[0092] The digital conversion processing module 1303 is used to perform digital conversion processing on the image after optical decoding to obtain three-dimensional point cloud data of the surface of the object being photographed.

[0093] The split camera memory module processes the image captured by the camera target surface into a digital signal, thereby obtaining the signal's unit beam charge. It then identifies and separates interfering light from the ambient light based on the stored optical code, and then filters out the interfering light using a filtering algorithm. The optical decoding module optically decodes the image after filtering out the interfering light, and the digital conversion processing module digitally converts the decoded image to produce 3D point cloud data of the object's surface. This 3D point cloud data includes not only the 2D image data but also the depth of field data of the object's distance from the area array camera, enabling high-precision fault location and identification.

[0094] In one embodiment, see Figure 1 The experimental platform also includes a wire trough 17 on one side of the simulation track. The cables connecting the image acquisition unit, positioning unit, gyroscope, power supply / IO trigger device and the host computer are placed in the wire trough 17. Data transmission is carried out in a wired manner, which is more stable.

[0095] Specifically, in this embodiment, the positioning unit adopts an RFID antenna, the host computer adopts an industrial computer, the power supply / IO trigger device adopts an existing power supply / IO trigger on the market, and the area array camera adopts an existing 25K high-speed day-blind area array camera on the market.

[0096] When the above-mentioned experimental platform of this embodiment performs simulated track fault detection, the detection platform starts working, and the host computer sends an acquisition instruction to the power supply / IO trigger. After receiving the acquisition instruction, the power supply / IO trigger sends corresponding pulse information to each module according to the real-time vehicle speed information provided by the wheel encoder. Each detection module starts to collect data and sends it to the host computer for storage. During storage, the data is input into the storage module in the form of a queue for recognition and the recognition results are stored.

[0097] The above-mentioned experimental platform of the embodiment of the present invention can simulate various track faults and realize fault detection of rail profile status, rail surface status, fastener status, sleeper status and track geometric parameters under the condition of the maximum train operating speed of 80km / h. It has a low false detection rate and high detection accuracy, providing more training samples for the engineering application of the track inspection system.

[0098] Finally, it should be noted that the experimental platform of the present invention can replace the simulated track with a real track for fault detection of the real track. Figure 1 and Figure 4 The upper surface of the track inspection trolley is also provided with an anti-collision alarm, which is electrically connected to the power supply / IO trigger. The power supply / IO trigger supplies power to the anti-collision alarm. When the track inspection trolley encounters an obstacle while walking, the anti-collision alarm will sound an alarm.

[0099] The above embodiments are used to explain the present invention rather than to limit the present invention. Any modifications and changes made to the present invention within the spirit of the present invention and the protection scope of the claims shall fall within the protection scope of the present invention.

Claims

1. An experimental platform for simulating track fault detection, characterized in that: include: Simulated tracks; Track inspection trolley, placed on the simulated track; The positioning unit is installed on the body of the track inspection trolley and is used to locate the position of the track inspection trolley; The gyroscope is installed on the track inspection vehicle between the two wheels and rails of the simulated track to detect track geometric parameters; The image acquisition unit is installed at the bottom of the track inspection trolley, and includes a rail profile detection module for acquiring wheel-rail profile images, a rail surface detection module for acquiring wheel-rail surface images, a fastener detection module for acquiring wheel-rail fastener images, and a sleeper detection module for acquiring sleeper images; each module includes an area array camera, a light source laser, a signal controller, and an FPGA; the area array camera is used to acquire images of the object being photographed; the light source laser is installed at the front end of the area array camera and is used to emit light of a set wavelength when the area array camera acquires an image, and the light source laser is equipped with an optical coding module for encoding the emitted light of the set wavelength; the signal The controller is used to control the operation of the area array camera and the light source laser according to the real-time speed of the track inspection vehicle. The FPGA is used to filter out interference light in the ambient light from the image acquired by the area array camera according to the optical coding, optically decode the filtered light signal, and digitally convert the light signal and image information to obtain three-dimensional point cloud data of the surface of the object being photographed. The FPGA is equipped with a split camera memory module, an optical decoding module, and a digital conversion processing module. The split camera memory module is used to filter out interference light in the ambient light from the image acquired by the area array camera according to the optical coding. The optical decoding module is used to optically decode the image after the interference light is filtered out. The digital conversion processing module is used to perform digital conversion processing on the image after optical decoding to obtain three-dimensional point cloud data of the surface of the object; The host computer is connected to the power unit of the track inspection trolley to control the movement of the track inspection trolley; the host computer is equipped with a normalization processing module and a storage module; The normalization processing module is used to normalize the three-dimensional point cloud data sent by the FPGA and the track geometric parameter data sent by the gyroscope through a normalization algorithm to eliminate the jitter caused by the vibration of the vehicle body; the storage module is used to store the data processed by the normalization processing module and the position information of the track inspection vehicle.

2. The experimental platform for simulating track fault detection according to claim 1, characterized in that: The simulated track comprises a bracket, a wheel rail installed on the bracket, and a sleeper arranged below the wheel rail.

3. The experimental platform for simulating track fault detection according to claim 2, characterized in that: The total length of the simulated track is at least 8m, providing a travel distance of at least 5m for the track inspection trolley. The wheel rail is a standard 50 rail, and the spacing between the two wheel rails is 1435mm.

4. The experimental platform for simulating track fault detection according to claim 2, characterized in that: The brackets at both ends of the wheel rail are provided with limit pieces to prevent the track inspection trolley from running out of bounds.

5. The experimental platform for simulating track fault detection according to claim 1, characterized in that: The rail surface detection module is installed at the bottom of the track inspection trolley, just above the top surface of the wheel rail of the simulated track; The track profile detection module is installed on both sides of the bottom of the track inspection trolley, corresponding to the wheel-rail position of the simulated track, and is located on both sides of the rail surface detection module; the fastener detection module is installed on the bottom of the track inspection trolley, located just above the top surface of the wheel-rail of the simulated track, and is integrated with the rail surface detection module in a module box; The sleeper detection module is installed at the bottom of the track inspection trolley and is located between the two wheel rails of the simulated track.

6. The experimental platform for simulating track fault detection according to claim 5, characterized in that: The track profile detection module on each side includes two track profile detection modules, and the two track profile detection modules on the same side are installed at an angle of 68°.

7. The experimental platform for simulating track fault detection according to any one of claims 1 to 6, characterized in that: It also includes a transverse connecting piece, and the image acquisition unit is installed on the bottom of the track inspection trolley through the transverse connecting piece.

8. The experimental platform for simulating track fault detection according to claim 7, characterized in that: The track inspection trolley comprises: vehicle body; The driving wheel is located below the front end of the vehicle body and is connected to the power device on the vehicle body through a chain; A driven wheel is provided below the rear end of the vehicle body, and the driven wheel is a standard wheel pair; Wheel encoder, installed on the output shaft of the power unit or the driving wheel output shaft or the driven wheel output shaft, is used to collect the real-time speed of the track inspection trolley; The power supply / IO trigger device is located at the upper rear end of the vehicle body and is connected to the image acquisition unit, the host computer and the wheel codec respectively. It is used to power the image acquisition unit and, after receiving the acquisition command sent by the host computer, convert the real-time vehicle speed provided by the wheel encoder into pulse information corresponding to each module and send it to the signal controller. The signal controller controls the operation of the area array camera and light source laser of the corresponding module according to the pulse information corresponding to different modules.

9. The experimental platform for simulating track fault detection according to claim 8, characterized in that: It also includes a wire trough located on one side of the simulation track, in which the cables connecting the image acquisition unit and the host computer, the cables connecting the positioning unit and the host computer, the cables connecting the gyroscope and the host computer, the cables connecting the power device and the host computer, and the cables connecting the power supply / IO trigger device and the host computer are all placed.

Images