Non-contact rail abrasion and third rail geometric parameter real-time detection method and system

Abstract

The invention discloses a non-contact track abrasion and third track geometric parameter real-time detection method and system, and the method comprises the steps: collecting the graphic data of a track, and carrying out the preprocessing; converting the preprocessed image data into three-dimensional point cloud data and carrying out coordinate system normalization processing; registering and fusing the point cloud data of the rail head on the unstressed side of the steel rail, and respectively detecting abrasion values of a vertical point position on the stressed side of the steel rail and a horizontal point position on the top surface of the steel rail; performing third rail center point detection and third rail abrasion value calculation according to the third rail contour data; and a third rail pull-out value and a third rail guide height value are calculated according to the relative position relation between the third rail center point and the rail surface of the side steel rail close to the third rail center point. The geometric detection result of the third rail is compensated according to the abrasion detection result, the geometric measurement error of the third rail caused by abrasion of the steel rail is eliminated, and the geometric detection precision of the third rail and the safety of the third rail are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of track geometry detection, and in particular to a non-contact track wear and third rail geometry parameter real-time detection method and system. Background Art

[0002] The third rail, also known as the power supply rail, is a rail installed next to the track line for the sole purpose of supplying power. It works in conjunction with the current supply surface (collector shoe) to provide power support for all equipment on rail transit trains.

[0003] The train draws power from the third rail through the collector shoe. If the position of the third rail relative to the railway rail changes, the train will be unable to draw power. In serious cases, it may cause the train to intrude into the limit, resulting in the possibility of a train collision. Therefore, it is necessary to regularly measure the relative position and wear status of the third rail relative to the railway rail.

[0004] The relative position of the third rail to the railway rail includes the guide height value and the pull-out value. The measurement methods generally include: manual measurement, hand-pushed trolley measurement, and measurement by adding a measuring arm to the train. Among them, manual measurement requires the use of a third rail measuring ruler to measure. During the working time, the monitoring points are manually measured. This method has low measurement efficiency and a long measurement cycle. The measurement method using a hand-pushed trolley to add a measuring arm generally adopts non-contact measurement, that is, the third rail acquisition equipment is used to measure the geometric parameters of the third rail. This method is limited by the manual walking speed and the detection speed of the measuring tool. Under normal circumstances, the maximum speed of this measurement method reaches 5km / h. The method of adding a measuring arm to the train will cause the rail area to sink due to the weight of the train, and the relative relationship between the train wheels and the rails in the curve section will change, which will affect the measurement results.

[0005] When the third rail is designed and installed, the stress-bearing side and top surface of the rail close to the third rail are used as reference. The wear of the rails due to long-term operation will also cause errors in the geometric measurement of the third rail. Therefore, the wear of the rails close to the third rail should be taken into account during the geometric detection of the third rail. Otherwise, there will be large deviations in the geometric detection results of the third rail in areas with greater rail wear. Summary of the invention

[0006] Based on the above background, the object of the present invention is to provide a non-contact rail wear and third rail geometric parameter real-time detection method and system.

[0007] To achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a non-contact rail wear and third rail geometric parameter real-time detection method, comprising:

[0009] Collecting rail head images of the stress-bearing side and the stress-free side of the first rail in the track, rail head images of the stress-bearing side and the stress-free side of the second rail, and images of the contact surface of the third rail, and preprocessing the images;

[0010] Calibrate the acquisition equipment and convert the pre-processed image data into three-dimensional point cloud data; and normalize the coordinate system of all point cloud data according to the rotation and translation matrix obtained by calibration;

[0011] Match and register the rail head point cloud data of the non-stressed side of the first rail and the second rail with the standard rail profile in the template file to obtain the corresponding registration rotation matrix, perform coordinate transformation on the rail head data of the stress-bearing side of the first rail and the second rail according to the obtained registration rotation matrix, and fuse all the registered rail head point cloud data to obtain complete rail head point cloud data;

[0012] The spatial distance between the preset points of the standard rail profile in the template file and the corresponding points of the actual collected rails is calculated based on the fused rail head point cloud data to obtain the wear value of the corresponding points;

[0013] The contact surface of the third rail is fitted linearly to obtain the actual wear plane, and the edge non-contact surface data of the third rail is fitted with features to obtain the center point of the third rail. The wear value of the third rail is calculated based on the distance between the fitted center point of the third rail and the actual wear plane, as well as the theoretical values ​​of the non-contact surface and the contact surface of the third rail.

[0014] The nearest rail is determined according to the point cloud data of the third rail, and the third rail pull-out value and the third rail guide height value are obtained according to the relative position relationship between the center point of the third rail and the surface of the nearest rail, the distance between the center point of the third rail and the actual wear plane, and the wear values ​​of the corresponding points of the rail.

[0015] In a second aspect, the present invention provides a non-contact rail wear and third rail geometric parameter real-time detection system, comprising:

[0016] An image data acquisition module, used to acquire rail head images of the stress-bearing side and the stress-free side of the first rail in the track, rail head images of the stress-bearing side and the stress-free side of the second rail, and an image of the contact surface of the third rail;

[0017] An image data preprocessing module, used for preprocessing the collected images;

[0018] The three-dimensional point cloud conversion module is used to calibrate the image data acquisition module and convert the pre-processed image data into three-dimensional point cloud data; and all point cloud data are normalized in the coordinate system according to the rotation and translation matrix obtained by calibration;

[0019] The rail point cloud data registration and fusion module is used to match and register the rail head point cloud data of the non-stress side of the first rail and the second rail with the standard rail profile in the template file, obtain the corresponding registration rotation matrix, perform coordinate transformation on the rail head data of the stress side of the first rail and the second rail according to the obtained registration rotation matrix, and fuse all the registered rail head point cloud data to obtain complete rail head point cloud data;

[0020] The rail wear value acquisition module is used to calculate the spatial distance between the preset points of the standard rail profile in the template file and the corresponding points of the actual collected rails based on the fused rail head point cloud data, and obtain the wear value of the corresponding points;

[0021] The third rail wear value acquisition module is used to perform linear fitting on the contact surface of the third rail to obtain the actual wear plane, perform feature fitting on the non-contact surface data of the edge of the third rail to obtain the center point of the third rail, and calculate the third rail wear value based on the distance between the fitted third rail center point and the actual wear plane, as well as the theoretical value between the non-contact surface and the contact surface of the third rail;

[0022] The third rail pull-out value and guide height value acquisition module is used to determine the nearest rail based on the third rail point cloud data, and obtain the point wear value of the corresponding rail and the distance between the center point of the third rail and the actual wear plane, and obtain the third rail pull-out value and third rail guide height value based on the relative position relationship between the center point of the third rail and the rail surface.

[0023] The beneficial effects of the present invention are as follows:

[0024] 1) When performing rail wear detection, the present invention uses the outer contour of the rail on the unstressed side to align the rail head area, reducing the influence of the wear surface point cloud on the alignment result and improving the wear detection accuracy.

[0025] 2) When detecting the geometric parameters of the third rail, the present invention divides the surface contour of the third rail into a contact area and a non-contact area. The wear value of the third rail is measured by arc detection of the non-contact area and straight line fitting of the contact surface, which solves the problem of not detecting the wear value of the third rail in the prior art and provides a reference for the service status of the third rail.

[0026] 3) The present invention compensates the third rail geometry detection result according to the wear detection result, realizes the real-time detection of the third rail state under high-speed state, eliminates the third rail geometry measurement error caused by rail wear, improves the third rail geometry detection accuracy, and increases the third rail safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 A flow chart of a non-contact rail wear and third rail geometric parameter real-time detection method provided by an embodiment of the present invention;

[0029] Figure 2 Schematic diagram of a non-contact track wear and third rail geometric parameter real-time detection system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to further understand the present invention, preferred embodiments of the present invention are described below in conjunction with examples. However, it should be understood that these descriptions are only for further illustrating the features and advantages of the present invention, rather than limiting the claims of the present invention.

[0031] Terminology explanation:

[0032] Third rail: also known as the power supply rail, includes contact surface and non-contact surface. The contact surface refers to the part of the third rail that is in direct contact with the train's current collector (such as the collector shoe); the non-contact surface refers to other surfaces except the part that is in contact with the train's current collector. These parts are not directly involved in the transmission of current, but may involve structures such as protection, insulation and fixation.

[0033] There are three current receiving modes of the third rail: upper contact type, lower contact type and side contact type. In this embodiment, the lower contact type is used as an example for schematic illustration, and the lower contact type means that the rail head of the third rail faces downward.

[0034] Embodiment 1:

[0035] The embodiment of the present invention provides a non-contact rail wear and third rail geometric parameter real-time detection method, see Figure 1 , the method comprises the following steps:

[0036] S1: collecting rail head images of the first rail on the track at the stress side and the non-stress side, rail head images of the second rail on the track at the stress side and the non-stress side, and an image of the contact surface of the third rail;

[0037] S2: preprocessing the collected image information;

[0038] S3: Calibrate the camera and convert the preprocessed image data into three-dimensional point cloud data. Apply the calibration parameters to normalize the coordinate system of all point cloud data to obtain three-dimensional point cloud data of the first rail, the rail head of the second rail, and the rail surface of the third rail in the same coordinate system;

[0039] S4: performing point cloud registration and fusion on the rail head point cloud data, and detecting the wear values ​​of the preset points of the rail respectively;

[0040] S5: performing third rail center point detection and wear surface fitting according to the third rail point cloud data, and calculating the third rail wear value;

[0041] S6: Determine the position area of ​​the third rail relative to the steel rail according to the point cloud data of the third rail, and calculate the third rail pull-out value and the third rail guide height value according to the relative relationship between the center point of the third rail and the surface of the adjacent steel rail.

[0042] Specifically:

[0043] S1: Collect the profile data of the contact surfaces of the first rail, the second rail, and the third rail of the running track.

[0044] In this embodiment, the image acquisition device includes six line scan camera acquisition modules and a mileage encoder, wherein all line scan cameras are triggered simultaneously by the mileage encoder, and when the encoder change value reaches the set threshold, the camera is triggered to collect the rail surface and the third rail surface profile of the same vertical area under the current mileage state, and the data collection of the rail and third rail profile is completed. The setting of the threshold needs to be adjusted according to the specific application scenario and environmental conditions, and the optimal threshold setting is determined through experiments according to the actual track environment and camera performance.

[0045] The specific implementation steps and principles of this process are as follows:

[0046] The four line scan camera acquisition modules in the middle are divided into two groups, each with two line scan camera modules, installed on the same plane. Because the camera on one side can only scan part of the rail head area, in order to ensure that the complete rail head data can be collected, two line scan camera modules are set in each group; the two camera acquisition modules at the edge position respectively collect data on the surface profile of the third rail on both sides of the rail. It should be noted that for the convenience of subsequent description, the six cameras in the morning are numbered from left to right as: Camera 1, Camera 2, Camera 3, Camera 4, Camera 5 and Camera 6.

[0047] The third rail is set beside the rail, usually one rail. Based on the direction of travel of the rail transit train, the third rail is located on the right side of the rail in some cases and on the left side of the rail in some cases, providing power support for all equipment on the rail transit train. However, the specific number of third rails needs to be determined according to the design and application scenarios of the railway system. Therefore, in order to improve the versatility of the detection equipment, two camera acquisition modules are symmetrically arranged on the left and right to collect data on the surface profile of the third rail on both sides of the rail. However, in this embodiment, only the third rail on one side of the guide rail is used for schematic illustration, and it is not intended to limit the scope of protection of the present invention.

[0048] S2: Preprocess the collected image information.

[0049] Preprocess the collected images to provide high-quality image data for subsequent image analysis. Image preprocessing includes image filtering, edge detection, and contour extraction.

[0050] Image filtering includes Gaussian filtering, median filtering, and bilateral filtering. Gaussian filtering uses a Gaussian function as a convolution kernel to smooth the image to remove noise and retain edge information; median filtering removes noise by replacing each pixel value with the median of its neighborhood; bilateral filtering reduces noise while maintaining edge sharpness and is suitable for smoothing that retains details.

[0051] Edge detection generally uses the Canny multi-stage edge detection algorithm, which includes Gaussian filtering, gradient calculation, non-maximum suppression and double thresholding to detect edges in images; it also includes Sobel edge detection that uses the Sobel operator to calculate image gradients, and Laplacian edge detection that uses the Laplacian operator to calculate the second-order derivative of the image.

[0052] Silhouette extraction connects the edges into contours according to the findContours function and findContours function provided in OpenCV. It can accurately extract the contour information of the object, that is, the silhouette map, from the image, providing a basis for subsequent image analysis and understanding.

[0053] S3: Convert the image data of the rail and the third rail obtained after preprocessing into three-dimensional point cloud data, and normalize the coordinates of the three-dimensional point cloud data. Including,

[0054] S301: Calibrate the camera to obtain the rotation and translation matrix Rt of the camera;

[0055] The calibration of the camera includes the determination of the internal and external parameters of the camera. Among them, the internal parameters include focal length, principal point, distortion coefficient, etc., which constitute the camera internal parameter matrix, and the external parameters include rotation and translation matrix parameters, etc. Using the internal and external parameters of the camera, combined with the depth information of each pixel point image in the two-dimensional image, the coordinates of the two-dimensional image can be reversely projected into the three-dimensional space to obtain the corresponding three-dimensional point cloud data. Among them, the depth information of each pixel point of the two-dimensional image is the depth in the three-dimensional space (that is, the distance from the camera), which can usually be obtained through structured light method, depth sensor, stereo vision and other methods; the rotation and translation matrix describes the position and direction of the camera relative to the world coordinate system, and converts the three-dimensional coordinates of the image from the camera coordinate system to the world coordinate system to obtain the final three-dimensional point cloud data.

[0056] In this embodiment, the four line scan camera acquisition modules that collect rail profile area data in the middle position are calibrated to obtain the rotation and translation matrix Rt of the four cameras; the rotation and translation matrix Rt is saved through the configuration file; the third rail data acquisition camera is calibrated to obtain the corresponding rotation and translation matrix, and the rotation and translation matrix parameters are saved in the configuration file. After calibration, if the camera installation position is not changed, there is no need to calibrate again.

[0057] It should be noted that camera calibration and corresponding conversion of image data into three-dimensional point cloud data belong to the prior art, and ordinary technicians in this field can implement it in combination with existing knowledge, so the specific process will not be repeated here.

[0058] S302: converting the rail image data into three-dimensional point cloud data and normalizing the coordinate system;

[0059] After converting the rail image data collected by the line scan camera acquisition module into three-dimensional point cloud data, the rotation and translation matrix Rt of the corresponding camera is read according to the camera number to normalize the coordinate system. The coordinate systems of the two cameras in each group are converted to the same coordinate system for fusion to obtain complete rail head point cloud data.

[0060] S303: converting the third track image data into three-dimensional point cloud data; and normalizing the coordinate system;

[0061] After converting the third-rail image data collected by the line scan camera acquisition module into three-dimensional point cloud data each time, the rotation and translation matrix Rt of the corresponding camera is read according to the camera number to perform coordinate system normalization processing, that is, the third-rail point cloud data is converted to the same coordinate system as the rail point cloud data through the rotation and translation matrix.

[0062] S4: performing point cloud registration and fusion according to the rail head point cloud data obtained in step S3, and detecting the wear values ​​of preset points of the rail respectively.

[0063] In this embodiment, the preset point of the rail is the horizontal point of the top surface, that is, the point where the horizontal tangent line is tangent to the rail head, which is recorded as the 0° point; the point where the vertical tangent line is tangent to the force-bearing side of the rail head is recorded as the 90° point; in order to simplify the description, the subsequent expressions directly refer to the 0° point and the 90° point of the rail. The specific process is as follows:

[0064] S401: Based on the rail head point cloud data Pts2 and Pts5 collected by camera 2 and camera 5, the collected rail profile is registered with the standard rail profile in the template file using the ICP (Iterative Closest Point) registration algorithm to obtain the registration rotation matrix Rt2', Rt5' and the registered point cloud set Pts2', Pts5';

[0065] S402: Apply the registration rotation matrices Rt2' and Rt5' to coordinate transformation of the point cloud data Pts3 and Pts4 of camera 3 and camera 4, respectively, to obtain new point cloud sets Pts3' and Pts4';

[0066] S403: After obtaining a new point cloud set, Pts2' and Pts3', Pts4' and Pts5' are merged respectively to obtain new point cloud data Pts23 and Pts45. The new point cloud data is the point cloud data of the first rail head and the second rail head.

[0067] S404: Calculate the spatial distance between the 0° point and the 90° point of the standard rail profile in the template file and the corresponding position of the actual collected rail based on the fused rail head point cloud data. This distance is the wear value of the 0° point and the 90° point. Specifically,

[0068] According to the spatial coordinates of the measurement points at 0° and 90° in the template file, the 10 point cloud data closest to the 0° (x, y, z) and 90° (x, y, z) points in the template file are extracted in the point cloud sets Pts23 and Pts45 respectively to obtain two new point cloud sets Pts_0 and Pts_90; according to the two sets of point cloud data Pts_0 and Pts_90, two straight lines L_0 and L_90 are fitted respectively by the least squares method; and the vertical distances from 0° (x, y, z) and 90° (x, y, z) to the straight lines L_0 and L_90 in the point template file are taken as the wear values ​​of the points to obtain the wear values ​​w_0 and w_90.

[0069] S5: Detect the third rail center point and calculate the third rail wear value based on the third rail point cloud data. Including:

[0070] S501: Detect the non-contact surface of the third rail to obtain the coordinates of the center point of the third rail;

[0071] The non-contact surface of the third rail has different features in different models, that is, different feature detections can be performed accordingly, such as arc feature detection, straight line feature detection, etc. In this embodiment, the arc feature presented in the edge area of ​​the third rail is circle-fitted to obtain the coordinates of the center point of the third rail.

[0072] A circle is fitted according to the arc features presented in the edge area of ​​the third rail. Methods for circle fitting include the least square method, the RANSAC (Random Sample Consensus) algorithm, etc. In this embodiment, the RANSAC algorithm is specifically used to fit the contour point cloud of the third rail to obtain two fitted circle equations C_l, C_r and the center point coordinates of the two fitted circles (c_l_cent(x, y, z), c_r_cent(x, y, z)).

[0073] According to the coordinates of the fitting circle center, the coordinates of the center point of the third rail are obtained, t_cent (x', y', z'), where x' = t_cent ((c_l_cent.x + c_r_cent.x) * 0.5, y' = (c_l_cent.y + c_r_cent.y) * 0.5, z' = (c_l_cent.z + c_r_cent.z) * 0.5).

[0074] S502: performing a linear detection on the contact surface of the third rail, locating the actual wear plane of the third rail, and calculating the wear value of the third rail according to the theoretical value and the actual detection difference between the positions of the arc center points on both sides of the third rail surface and the third rail surface;

[0075] According to the point cloud data of the third rail profile, the RANSAC algorithm is used to perform straight line detection on the third rail contact surface to obtain the corresponding rail contact surface point cloud set Pts_plane and straight line equation L, and locate the actual wear plane of the third rail.

[0076] The height difference between the center point of the arc detection and the wear surface is subtracted from the theoretical value between the non-contact surface and the contact surface of the third rail to obtain the third rail wear value railcost = Ht-Hw, where Hw is the distance between the center of the fitting circle and the straight line equation; Ht is the theoretical design value between the center points of the arcs on both sides of the third rail and the contact surface of the third rail under the corresponding model of the third rail.

[0077] S6: judging the position of the third rail relative to the steel rail according to the third rail point cloud data, and calculating the third rail pull-out value and the third rail guide height value according to the relative relationship between the third rail center point and the steel rail surface; including:

[0078] S601: Determine the position area of ​​the third rail relative to the steel rail, and extract the wear value of the nearest steel rail;

[0079] After the point cloud of the third rail profile is normalized, the y-coordinate value of the point cloud data collected from the third rail is used to determine which side of the rail the third rail is located near, that is, to determine whether the third rail is located near the first rail or the second rail; and the wear values ​​of the corresponding rail 0° point and 90° point detected in step S4 are extracted based on the judgment result.

[0080] S602: Calculate the third rail pull-out value and the third rail guide height value;

[0081] The third rail pull-out value refers to the lateral distance between the center point C of the third rail in the same cross section and the wear measurement point of the adjacent rail at 90°; that is, the Y-axis coordinate difference of the two points in the coordinate system of this embodiment;

[0082] The third rail guide height value refers to the vertical distance between the center point C of the third rail in the same cross section and the 0° point rail wear measurement point of the adjacent rail, that is, the Z-axis coordinate difference between the two points in the coordinate system of this embodiment.

[0083] The specific calculation process is as follows:

[0084] The coordinate difference between the center point coordinate and the wear point of the rail close to one side is calculated to obtain the initial pull value and lead height value of the third rail.

[0085] According to the rail wear values ​​w_0 and w_90 obtained in step S4, and the distance HW between the center point of the third rail and the actual wear plane obtained in step S5, the initial pull value pullvalue and the lead height value leadhight of the third rail are compensated and calculated to obtain the specific third rail geometry detection result:

[0086] Pull value pullvalue'=pullvalue+w_90,

[0087] Lead high value leadhight'=leadhight+w_0+HW.

[0088] In this embodiment, the rail close to the third rail is used as the detection reference, the 90° point wear detection result of the rail is used as the compensation value of the third rail pull-out detection result, and the 0° point wear detection result of the rail is used as the compensation value of the third rail guide height detection result. This method solves the problem of measurement errors of the third rail guide height value and pull-out value caused by rail wear. At the same time, the difference between the distance between the arc area of ​​the third rail edge and the wear surface of the third rail and the design value of the third rail model is used as the third rail wear detection result, which provides a reference for the service status of the third rail.

[0089] Embodiment 2:

[0090] See also Figure 2This embodiment provides a non-contact rail wear and third rail geometric parameter real-time detection system, including:

[0091] An image data acquisition module is used to acquire an image of a rail head on a stress-bearing side of a first rail, an image of a rail head on a stress-free side of a first rail, an image of a rail head on a stress-bearing side of a second rail, an image of a rail head on a stress-free side of a second rail, and an image of a contact surface of a third rail;

[0092] An image data preprocessing module, used for preprocessing the collected images;

[0093] The three-dimensional point cloud conversion module is used to calibrate the image data acquisition module and convert the pre-processed image data into three-dimensional point cloud data; and all point cloud data are normalized in the coordinate system according to the rotation and translation matrix obtained by calibration;

[0094] The rail point cloud data registration and fusion module is used to match and register the rail head point cloud data of the non-stress side of the first rail and the second rail with the standard rail profile in the template file, obtain the corresponding registration rotation matrix, perform coordinate transformation on the rail head data of the stress side of the first rail and the second rail according to the obtained registration rotation matrix, and fuse all the registered rail head point cloud data to obtain complete rail head point cloud data;

[0095] The rail wear value acquisition module is used to calculate the spatial distance between the preset point position of the standard rail profile in the template file and the corresponding position of the actual collected rail based on the fused rail head point cloud data, and obtain the wear value of the corresponding point position;

[0096] The third rail wear value acquisition module is used to perform linear fitting on the contact surface of the third rail to obtain the actual wear plane, perform feature fitting on the non-contact surface data of the edge of the third rail to obtain the center point of the third rail, and calculate the third rail wear value based on the distance between the fitted third rail center point and the actual wear plane, as well as the theoretical value between the non-contact surface and the contact surface of the third rail;

[0097] The third rail pull-out value and guide height value acquisition module is used to determine the nearest rail based on the third rail point cloud data, and obtain the point wear value of the corresponding rail and the distance between the center point of the third rail and the actual wear plane, and calculate the third rail pull-out value and the third rail guide height value based on the relative position relationship between the center point of the third rail and the rail surface.

[0098] The above embodiments are only used to help understand the method and core idea of ​​the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made to the present invention without departing from the principles of the present invention, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

[0099] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0100] It should be noted that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the steps as sequential processes, many of the steps can be implemented in parallel, concurrently or simultaneously. In addition, the order of the steps can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

Claims

1. A non-contact rail wear and third rail geometric parameter real-time detection method, characterized in that: include, Collecting rail head images of the stress-bearing side and the stress-free side of the first rail in the track, rail head images of the stress-bearing side and the stress-free side of the second rail, and images of the contact surface of the third rail, and preprocessing the images; Calibrate the acquisition equipment and convert the pre-processed image data into three-dimensional point cloud data; and normalize the coordinate system of all point cloud data according to the rotation and translation matrix obtained by calibration; Match and register the rail head point cloud data of the non-stressed side of the first rail and the second rail with the standard rail profile in the template file to obtain the corresponding registration rotation matrix, perform coordinate transformation on the rail head data of the stress-bearing side of the first rail and the second rail according to the obtained registration rotation matrix, and fuse all the registered rail head point cloud data to obtain complete rail head point cloud data; The spatial distance between the preset points of the standard rail profile in the template file and the corresponding points of the actual collected rails is calculated based on the fused rail head point cloud data to obtain the wear value of the corresponding points; The contact surface of the third rail is fitted linearly to obtain the actual wear plane, and the edge non-contact surface data of the third rail is fitted with features to obtain the center point of the third rail. The wear value of the third rail is calculated based on the distance between the fitted center point of the third rail and the actual wear plane, as well as the theoretical values ​​of the non-contact surface and the contact surface of the third rail. The nearest rail is determined according to the point cloud data of the third rail, and the third rail pull-out value and the third rail guide height value are obtained according to the relative position relationship between the center point of the third rail and the surface of the nearest rail, the distance between the center point of the third rail and the actual wear plane, and the wear values ​​of the corresponding points of the rail.

2. The non-contact rail wear and third rail geometric parameter real-time detection method according to claim 1 is characterized in that: The equipment for collecting rail head images of the stressed side and the unstressed side of the first rail in the track, rail head images of the stressed side and the unstressed side of the second rail, and the image of the contact surface of the third rail includes six line scan cameras arranged in the same facade area, and the line scan cameras are triggered simultaneously by the mileage encoder; the six line scan cameras in the same facade area are numbered as camera 1, camera 2, camera 3, camera 4, camera 5 and camera 6 in sequence, wherein camera 1 and / or camera 6 are used to obtain contact surface data of the third rail, camera 2 is used to obtain the rail head image of the unstressed side of the first rail, camera 3 is used to obtain the rail head image of the stressed side of the first rail, camera 4 is used to obtain the rail head image of the stressed side of the second rail, and camera 5 is used to obtain the rail head image of the unstressed side of the second rail.

3. The non-contact rail wear and third rail geometric parameter real-time detection method according to claim 1 is characterized in that: The image preprocessing includes image filtering, edge detection and / or silhouette extraction.

4. The non-contact rail wear and third rail geometric parameter real-time detection method according to claim 2 is characterized in that: The acquisition device is calibrated, and the pre-processed image data is converted into three-dimensional point cloud data; and all point cloud data are normalized in the coordinate system according to the rotation and translation matrix obtained by calibration, including: Calibrate each camera, obtain the rotation and translation matrix corresponding to each camera and store it; The rail image data is converted into three-dimensional point cloud data, the rotation and translation matrices of the corresponding cameras are read according to the camera numbers, and the rail head data of the stress-bearing side and the stress-free side of the rail are converted into the same coordinate system according to the corresponding rotation and translation matrices and fused to obtain the complete rail head point cloud data; The third rail image data is converted into three-dimensional point cloud data, the corresponding rotation and translation matrix is ​​read according to the camera number, and the third rail point cloud data is converted into the same coordinate system as the rail point cloud data through the corresponding rotation and translation matrix for normalization.

5. The non-contact rail wear and third rail geometric parameter real-time detection method according to claim 1 is characterized in that: The method for matching and registering the rail head point cloud data of the unstressed side of the first rail and the second rail with the standard rail profile in the template file is an iterative closest point ICP registration algorithm.

6. The non-contact rail wear and third rail geometric parameter real-time detection method according to any one of claims 1 to 5, characterized in that: The method of calculating the spatial distance between the preset point position of the standard rail profile in the template file and the corresponding point position of the actual collected rail according to the fused rail head point cloud data to obtain the wear value of the corresponding point position includes: According to the spatial coordinates of the preset measurement points in the template file, a number of point cloud data closest to the preset points in the template file are extracted from the preset measurement point rail point cloud data to obtain a point cloud set corresponding to each preset point; wherein the preset measurement points are the tangent point where the horizontal tangent line is tangent to the rail head, recorded as the 0° point; and the tangent point where the vertical tangent line is tangent to the stress side of the rail head, recorded as the 90° point; Perform straight line fitting according to the point cloud set corresponding to each preset point; According to the preset vertical distance from the measurement point to the corresponding fitting straight line in the template file, the wear value of the point is taken as the wear value of the point. The wear value of the 0° point is w_0, and the wear value of the 90° point is w_90.

7. The non-contact rail wear and third rail geometric parameter real-time detection method according to claim 6 is characterized in that: The method of performing linear fitting on the contact surface of the third rail to obtain the actual wear plane and performing feature fitting on the non-contact surface data of the edge of the third rail to obtain the center point of the third rail includes: Perform linear detection on the contact surface of the third rail to obtain the corresponding linear equation L and locate the actual wear plane of the third rail; According to the arc features presented in the edge area of ​​the third rail, a circle fitting is performed to obtain two fitting circle equations C_l, C_r and the coordinates of the centers of the two fitting circles (c_l_cent(x, y, z), c_r_cent(x, y, z)); According to the coordinates of the center of the fitting circle, the coordinates of the center point of the third rail are obtained, t_cent (x', y', z'), where x' = t_cent ((c_l_cent.x + c_r_cent.x) * 0.5, y' = (c_l_cent.y + c_r_cent.y) * 0.5, z' = (c_l_cent.z + c_r_cent.z) * 0.5).

8. The non-contact rail wear and third rail geometric parameter real-time detection method according to claim 7 is characterized in that: The calculation of the wear value of the third rail according to the distance between the fitted third rail center point and the actual wear plane and the theoretical value of the third rail non-contact surface and the contact surface includes: The third rail wear value railcost = Ht-Hw, Where Hw is the distance between the center of the fitting circle and the straight line equation; Ht is the theoretical design value between the center points of the arcs on both sides of the third rail and the contact surface of the third rail under the corresponding model of the third rail.

9. The non-contact rail wear and third rail geometric parameter real-time detection method according to claim 8, characterized in that: The method of determining the nearest rail according to the point cloud data of the third rail, and obtaining the third rail pull-out value and the third rail guide height value according to the relative position relationship between the center point of the third rail and the surface of the nearest rail, the distance between the center point of the third rail and the actual wear plane, and the wear value of the corresponding point of the rail includes: The coordinate difference between the coordinates of the center point of the third rail and the 0° wear point and the 90° wear point in the template file close to one side of the rail is calculated to obtain the initial pull value and lead height value of the third rail. According to the wear values ​​of the rail at 0° and 90° points, and the distance HW between the center point of the third rail and the actual wear plane, the initial pull value pullvalue and lead height value leadhight of the third rail are compensated and calculated to obtain the specific third rail geometry detection results: Pull value pullvalue'=pullvalue+w_90, Lead high value leadhight'=leadhight+w_0+HW.

10. A non-contact rail wear and third rail geometric parameter real-time detection system, characterized in that: include, An image data acquisition module, used to acquire rail head images of the stress-bearing side and the stress-free side of the first rail in the track, rail head images of the stress-bearing side and the stress-free side of the second rail, and an image of the contact surface of the third rail; An image data preprocessing module, used for preprocessing the collected images; The three-dimensional point cloud conversion module is used to calibrate the image data acquisition module and convert the pre-processed image data into three-dimensional point cloud data; and all point cloud data are normalized in the coordinate system according to the rotation and translation matrix obtained by calibration; The rail point cloud data registration and fusion module is used to match and register the rail head point cloud data of the non-stress side of the first rail and the second rail with the standard rail profile in the template file, obtain the corresponding registration rotation matrix, perform coordinate transformation on the rail head data of the stress side of the first rail and the second rail according to the obtained registration rotation matrix, and fuse all the registered rail head point cloud data to obtain complete rail head point cloud data; The rail wear value acquisition module is used to calculate the spatial distance between the preset points of the standard rail profile in the template file and the corresponding points of the actual collected rails based on the fused rail head point cloud data, and obtain the wear value of the corresponding points; The third rail wear value acquisition module is used to perform linear fitting on the contact surface of the third rail to obtain the actual wear plane, perform feature fitting on the non-contact surface data of the edge of the third rail to obtain the center point of the third rail, and calculate the third rail wear value based on the distance between the fitted third rail center point and the actual wear plane, as well as the theoretical value between the non-contact surface and the contact surface of the third rail; The third rail pull-out value and guide height value acquisition module is used to determine the nearest rail based on the third rail point cloud data, and obtain the point wear value of the corresponding rail and the distance between the center point of the third rail and the actual wear plane, and obtain the third rail pull-out value and third rail guide height value based on the relative position relationship between the center point of the third rail and the rail surface.

Images