Contact rail detection system, inspection engineering vehicle and detection method

Abstract

The present application relates to straddle type monorail inspection technical field, more specifically, it relates to a contact rail detection system, which can automatically collect the image information of the contact rail, and obtain the installation position and wear degree information of the contact rail according to the image information.The present application also provides a straddle type monorail inspection engineering vehicle, which can travel on the straddle type monorail track, and can obtain the installation position and wear degree information of the contact rail in real time and accurately through the contact rail detection system carried, replacing the traditional manual inspection mode, saving manpower and time, improving the detection efficiency, unifying the detection standard, and making the detection result more reliable.The present application also provides a detection method for the installation position and wear degree of the contact rail, which utilizes structured light detection, and identifies the special feature lines and feature points on the contact rail shape through matching algorithm, so as to obtain the installation position and wear degree information of the contact rail.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of straddle-type monorail inspection, and more particularly to a contact rail detection system applied to a straddle-type monorail, an inspection engineering vehicle and a contact rail detection method. BACKGROUND

[0002] The straddle-type monorail is a track transportation system that supports, stabilizes and guides by a single track, and the vehicle body rides on the track beam to run. It has been widely used in Chongqing. The straddle-type monorail has the characteristics of strong adaptability, low noise, small turning radius and strong climbing ability. The monorail system can better adapt to complex terrain and environment. The width of the bridge pier of the straddle-type monorail is less than 2 meters on average, and compared with other elevated rail transit, the width of the bridge pier is saved by nearly half. The straddle-type monorail can be erected in the green belt on the central or both sides of the urban road, and has the advantages of small occupation, less shielding, flexible route selection and slight traffic interference to the existing urban road.

[0003] The straddle-type monorail train runs on a concrete track beam. The bottom surface of the track beam is fixed on the track foundation, the upper surface is the running surface for the running wheels of the monorail train, and the side surface is the stabilizing surface and the guiding surface. The steering wheels and stabilizing wheels of the monorail train clamp the track beam from both sides of the track beam, stabilize the train on the monorail track beam, and control the direction of the train along the track beam. The contact rail is a device for transmitting electric energy to the electric traction vehicle of the subway and urban rail transit system. On both sides of the track beam of the straddle-type monorail, there is a contact rail, one on each side. The contact rail system mainly consists of a steel-aluminum composite rail (including an aluminum rail body and a stainless steel strip), an expansion joint, an end elbow and related components and an insulation support device, and provides electric energy for the electric locomotive group. The power transmission is realized by the contact between the electric vehicle current collection shoe and the composite rail. According to the current collection mode of the current collection shoe from the contact rail, the installation mode of the contact rail can be divided into three modes: upper contact, lower contact and side contact. The installation mode of the straddle-type monorail is side contact.

[0004] The detection of the installation position and the surface wear degree of the contact rail is a very important link in the inspection and maintenance of the straddle-type monorail track. In order to ensure the safety of the monorail train operation, the installation position and the wear degree of the contact rail need to be detected regularly. At present, the inspection and maintenance of the contact rail on the straddle-type monorail track is mainly completed by manual inspection, but manual inspection requires a lot of time, manpower and financial resources, and the detection accuracy depends heavily on the personal experience of the inspection personnel, and the detection standard cannot be unified. Therefore, manual inspection cannot detect the contact rail regularly, systematically and efficiently, and there are certain safety hazards, which cannot meet the detection needs of the contact rail. SUMMARY

[0005] Therefore, the present application aims to provide a contact rail detection system, which can automatically collect image information of the contact rail, and obtain installation position and wear degree information of the contact rail according to the image information, and has high detection efficiency and more accurate detection results.

[0006] Another object of the present application is to provide a straddle-type monorail inspection engineering vehicle, which can travel on a straddle-type monorail track, and can obtain installation position and wear degree information of the contact rail in real time and accurately through the contact rail detection system carried thereon, thereby replacing the traditional manual inspection mode, saving manpower and time, improving detection efficiency, unifying detection standards, and making the detection results more reliable.

[0007] Another object of the present application is to provide a contact rail installation position detection method, which can obtain installation position information data of the contact rail in real time and efficiently.

[0008] Another object of the present application is to provide a contact rail wear detection method, which can obtain wear information data of the contact rail in real time and efficiently.

[0009] In order to achieve the above objects, the present application provides the following technical solutions.

[0010] A contact rail detection system comprises a detection system host and a contact rail information collection device, the contact rail information collection device is used to collect image information of a track beam and a contact rail, and the detection system host obtains installation position information and wear information of the contact rail according to the image information.

[0011] Further, the contact rail information collection device comprises a first contact rail information collection device and a second contact rail information collection device, the image information collected by the first contact rail information collection device is used for the detection system host to obtain the installation position information, and the image information collected by the second contact rail information collection device is used for the detection system host to obtain the wear information.

[0012] Further, the contact rail information collection device has a shell, a face array camera and a linear laser are fixedly arranged in the shell, a window is arranged on the shell, the linear laser projects laser to the surface of the track through the window, and the face array camera collects laser image information projected to the surface of the track through the window.

[0013] Further, the axis line of the face array camera and the linear laser forms an included angle, and the included angle is 23°-39°.

[0014] A straddle-type monorail inspection engineering vehicle, comprising a vehicle body, a chassis of the vehicle body being provided with a walking mechanism, further comprising a contact rail detection system and a suspension side compartment connected with the vehicle body, wherein the detection system host is arranged in the vehicle body, and the contact rail information acquisition device is arranged on the side opposite to the suspension side compartment and the rail.

[0015] A contact rail installation position detection method, which utilizes the contact rail detection system for detection, comprising the following steps:

[0016] The first contact rail information acquisition device transmits the collected rail beam and contact rail image information to the detection system host;

[0017] The detection system host introduces a matrix convolution algorithm into the Steger algorithm to extract the structured light fringe center in the image.

[0018] For the extracted light fringe center, the feature position of the image is analyzed through a matching algorithm to extract the rail beam running surface feature line and the contact rail upper surface feature line.

[0019] The height difference between the rail beam running surface and the contact rail upper surface is calculated to obtain the installation position information of the contact rail.

[0020] Further, the specific method for extracting the rail beam running surface feature line and the contact rail upper surface feature line is as follows: first, according to the geometric shape of the rail beam running surface and the contact rail, a standard parallel line and a trapezoidal structure are designed as a comparison template; second, the structural information entropy between the comparison template and the extracted light fringe center neighborhood is taken as the basis for similarity analysis between the two structures, and the light strip center with the largest similarity is selected as the trapezoidal feature on the light strip curve, so as to identify the rail beam running surface feature line and the contact rail upper surface feature line.

[0021] A contact rail wear detection method, which utilizes the contact rail detection system for detection, comprising the following steps:

[0022] The second contact rail information acquisition device transmits the collected contact rail image information to the detection system host.

[0023] The detection system host introduces a matrix convolution algorithm into the Steger algorithm to extract the structured light fringe center in the image.

[0024] For the extracted light fringe center, the feature position of the image is analyzed through a matching algorithm to extract the contact rail surface feature points p1 and p2 and the feature line between the feature points.

[0025] The height of the contact rail surface protrusion is calculated, and then compared with the initial contact rail surface protrusion height to obtain the contact rail wear information.

[0026] Further, the specific method for extracting the contact rail surface feature points p1 and p2 and the feature line between the feature points is as follows: first, a standard feature point is designed as a comparison template according to the geometric shape features of the contact rail surface; second, the structural information entropy between the comparison template and the extracted light stripe center neighborhood is taken as the basis to analyze the similarity between the structures, and the light stripe center with the maximum similarity is selected as the feature point on the light stripe curve, thereby identifying the contact rail surface feature points p1 and p2 and the feature line between the feature points p1 and p2.

[0027] Further, the specific method for obtaining the contact rail wear information is as follows: after the feature points p1 and p2 and the feature line are identified, the coordinates of the feature points p1 and p2 and the coordinates of the point set on the feature line are obtained, the two-dimensional coordinates are converted into three-dimensional coordinates through a coordinate conversion equation, the points on the feature line are fitted into a spatial straight line equation, the distance from the feature point p1 to the spatial straight line and the distance from the feature point p2 to the spatial straight line are calculated to represent the height value of the contact rail surface protrusion, and then the contact rail wear information is obtained by comparing with the initial contact rail surface protrusion height value.

[0028] The contact rail detection system provided by the application comprises a detection system host and a contact rail information acquisition device, the track beam and contact rail image information acquired by the contact rail information acquisition device is processed and analyzed by the detection system host, and thus the installation position and wear degree information of the contact rail are obtained.

[0029] The contact rail detection system provided by the application can replace the traditional manual inspection mode, has higher detection efficiency, more unified detection standard, and more accurate and smaller error detection results.

[0030] The contact rail detection system provided by the application can replace the traditional manual inspection mode, has higher detection efficiency, more unified detection standard, and more accurate and smaller error detection results. BRIEF DESCRIPTION OF DRAWINGS

[0031] In order to make the technical solutions in the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only aim at the embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative effort on the basis of the provided drawings.

[0032] Figure 1 Fig. 1 is a schematic diagram of a contact rail detection system of the present application;

[0033] Figure 2 Fig. 2 is a schematic diagram of an external structure of a contact rail information acquisition device in an embodiment of the present application;

[0034] Figure 2 Fig. 3 is a schematic diagram of an internal structure of a contact rail information acquisition device in an embodiment of the present application;

[0035] Figure 3 Fig. 4 is a schematic diagram of an overall appearance of a straddle-type monorail inspection engineering vehicle of the present application;

[0036] Figure 4 Fig. 5 is a schematic diagram of a contact rail cross section;

[0037] Figure 5 Fig. 6 is a schematic diagram of a structure of a suspension side compartment and a relative side of a track;

[0038] Figure 6 Fig. 7 is a schematic diagram of an image acquired by a first contact rail information acquisition device of the present application;

[0039] Figure 7 Fig. 8 is a schematic diagram of an image acquired by a second contact rail information acquisition device of the present application;

[0040] Figure 8 Fig. 9 is a schematic diagram of a vehicle body chassis structure of a straddle-type monorail inspection engineering vehicle;

[0041] Figure 9 Fig. 10 is a flowchart of a contact rail installation position detection method;

[0042] Figure 10 Fig. 11 is a schematic diagram of a calibration plate of the present application;

[0043] Figure 11 Fig. 12 is a flowchart of a contact rail wear degree information detection method.

[0044] In the drawings, the following notations are used:

[0045] 100-contact rail detection system, 110-detection system host, 120-contact rail information acquisition device, 121-first contact rail information acquisition device, 122-second contact rail information acquisition device, 130-housing, 131-area array camera, 132-linear laser, 133-window, 200-inspection engineering vehicle, 210-vehicle body, 211-speed measuring wheel, 220-hanging side compartment, 310-track beam, 311-traveling surface, 320-contact rail, 321-aluminum rail body, 322-stainless steel belt. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0047] Please refer to Figures 1-11 , Figure 1 It is a schematic diagram of the contact rail detection system of the present application. Figure 2 A is a schematic diagram of the external structure of the contact rail information acquisition device in an embodiment of the present application. Figure 2 B is a schematic diagram of the internal structure of the contact rail information acquisition device in an embodiment of the present application. Figure 3 It is a schematic diagram of the overall appearance of the straddle-type monorail inspection engineering vehicle of the present application. Figure 4 It is a schematic diagram of the cross section of the contact rail. Figure 5 It is a schematic diagram of the structure of the hanging side compartment relative to one side of the track. Figure 6 It is a schematic diagram of the image acquired by the first contact rail information acquisition device of the present application. Figure 7 It is a schematic diagram of the image acquired by the second contact rail information acquisition device of the present application. Figure 8 It is a schematic diagram of the vehicle body chassis structure of the straddle-type monorail inspection engineering vehicle. Figure 9 It is a flowchart of the contact rail installation position detection method. Figure 10 It is a schematic diagram of the calibration plate of the present application. Figure 11 It is a flowchart of the contact rail wear degree information detection method.

[0048] As Figure 1 shown, a contact rail detection system 100 includes a detection system host 110 and a contact rail information acquisition device 120. The contact rail information acquisition device 120 is used to acquire image information of a track beam and a contact rail, and the detection system host 110 acquires installation position information and wear information of the contact rail according to the image information.

[0049] The number of the contact rail information acquisition device 120 is not limited here. One contact rail information acquisition device 120 can be used to acquire complete image information of the rail beam and the contact rail surface for subsequent analysis. In order to obtain more detailed image information, a plurality of contact rail information acquisition devices 120 can also be installed to acquire image information at different positions on the rail respectively, so as to obtain better image information. In this way, the detection system host 110 can obtain more accurate detection results.

[0050] In an embodiment of the present application, the contact rail information acquisition device 120 includes a first contact rail information acquisition device 121 and a second contact rail information acquisition device 122. The image information acquired by the first contact rail information acquisition device 121 is used by the detection system host 110 to obtain the installation position information, and the image information acquired by the second contact rail information acquisition device 122 is used by the detection system host 110 to obtain the wear information. In order to obtain more comprehensive image information, two contact rail information acquisition devices are used to acquire images in this embodiment, but the focus of the acquisition between the two is not consistent. The first contact rail information acquisition device 121 is mainly used to acquire overall image information of the running surface 311 of the rail beam 310 and the upper surface of the contact rail 320, which is used for subsequent analysis of the installation position data of the contact rail 320, i.e. for calculating the height difference between the running surface 311 of the rail beam 310 and the upper surface of the contact rail 320. The second contact rail information acquisition device 122 is mainly used to acquire image information of the outer surface of the contact rail 320, which is used for subsequent analysis of the wear data of the contact rail 320, i.e. for calculating the height of the protrusion of the outer surface of the contact rail 320.

[0051] Preferably, as shown in Figure 2 A and 2B, the contact rail information acquisition device 120 has a housing 130, a face array camera 131 and a linear laser 132 are fixedly arranged inside the housing 130, a window 133 is arranged on the housing of the housing 130, the linear laser 132 projects laser to the rail surface through the window 133, and the face array camera 131 acquires the laser image information projected to the rail surface through the window 133.

[0052] The installation position and wear degree information of the contact rail 320 are acquired by using the area array camera 131 and the linear laser 132 to adopt the structured light measurement method. The linear laser 132 projects linear laser on the surface of the rail to form a measurement light strip, and the area array camera 131 collects the corresponding measurement light strip image information. The detection system host 110 identifies, extracts and calculates the acquired measurement light strip image information, so as to acquire the height difference between the running surface 311 of the rail beam 310 and the upper surface of the contact rail 320, thereby determining the installation position of the contact rail 320, and also acquiring the protrusion height data of the current contact rail 320 surface, comparing with the original protrusion height of the contact rail 320 surface, thereby determining the wear degree of the contact rail 320.

[0053] The shell 130 is a sealed structure, which can effectively prevent the influence of external floating dust and other factors on the internal area array camera 131 and linear laser 132, improve the detection precision and prolong the service life. The window 133 can be a large window, or can be set as two small windows for the area array camera 131 and the linear laser 132 to be used separately. The shell 130 can be made of metal material to increase the structural strength, and a hole is opened on the shell, and then an optical lens is sealed and arranged at the hole to form the window 133.

[0054] After the area array camera 131 and the linear laser 132 are fixed, the axes of the two are at a certain included angle with each other, which can be set according to the application scene, the shooting distance and other factors. In the embodiment, the included angle between the area array camera 131 and the linear laser 132 can be in the range of 23° to 39°.

[0055] As shown in Figure 3 The present application also provides a straddle-type monorail inspection engineering vehicle 200, which can be roughly divided into upper and lower parts. The upper part is a vehicle body 210, and the lower part is a suspended side compartment 220 connected to the vehicle body 210. The vehicle body 210 is internally provided with a driver's cabin, a control room and the like. The driver's cabin is used for the driver to control the operation of the vehicle, and the control room is provided with the detection system host 110. The maintenance personnel directly controls the entire process of contact rail detection in the control room and views various data information in the contact rail detection process. The engineering vehicle chassis is provided with a walking mechanism, which is driven by electric power or internal combustion engine to drive the engineering vehicle to travel on the straddle-type monorail track.

[0056] The suspension side compartment 220 is connected to the engineering vehicle body 210, and at least a part of one side (the inner side) of the suspension side compartment 220 is opposite to the track side, so that the contact rail image information can be collected by the contact rail information collection device 120 arranged on the inner side of the suspension side compartment 220. The connection mode of the suspension side compartment 220 and the engineering vehicle body 210 is not limited here, but is preferably a detachable connection mode, which facilitates the maintenance and repair of the suspension side compartment 220.

[0057] The number of the suspension side compartment 220 is not limited here, and only one suspension side compartment 220 can be connected to the engineering vehicle body 210 for detecting the contact rail on one side of the track. Of course, considering the comprehensiveness of the detection, it is preferred that the suspension side compartment 220 is connected to both sides of the engineering vehicle body 210, and the suspension side compartment 220 is located on both sides of the track to detect the contact rail on both sides of the track. In the embodiment, the suspension side compartment 220 is connected to both sides of the engineering vehicle body 210, and a connecting bracket is arranged on the side (the inner side) opposite to the track of the suspension side compartment 220, and the connecting bracket is used to mount and fix the contact rail information collection device 120. The contact rail information collection device 120 collects the image information of the track beam and the contact rail, and then transmits the image information to the detection system host 110, and the detection system host 110 detects the installation position and the wear degree of the contact rail according to the image information.

[0058] The obtained installation position and wear degree information of the contact rail 320 can be transmitted to the server for storage through the existing data communication mode, and the maintenance personnel can access the data by connecting the terminal device to the server, or the installation position and wear degree information of the contact rail 320 can be directly sent to the terminal of the maintenance personnel for viewing.

[0059] The shape and structure of the suspension side compartment 220 are not limited here, and the suspension side compartment 220 can be a plate-shaped structure with a rectangular, square, or circular shape, or other non-plate-shaped structure. However, considering that the volume of the engineering vehicle body 210 after connecting the suspension side compartment 220 cannot be too large and cannot exceed the vehicle limit, the plate-shaped structure is more suitable.

[0060] The straddle-type monorail track includes a concrete track beam 310 and a contact rail 320 connected to both sides of the track beam 310. During the inspection of the engineering vehicle, the contact rail 320 needs to be comprehensively detected. The contact rail 320 detection includes installation position detection and wear detection. As shown in Figure 4 The steel-aluminum composite rail in the contact rail 320 includes an aluminum rail body 321 and a stainless steel strip 322. Although the stainless steel strip 322 is a wear-resistant material, it will still be worn after long-term use, so it is necessary to detect whether the wear of the stainless steel strip 322 exceeds the limit value.

[0061] As shown in Figure 5As shown, a first contact rail information acquisition device 121 and a second contact rail information acquisition device 122 are fixedly installed on the connecting bracket on the side of the suspended side carriage 220 opposite to the track, and there is a certain height difference between the installation positions of the two contact rail information acquisition devices (121, 122). The first contact rail information acquisition device 121, located at the upper position, is used to acquire image information of the running surface 311 of the track beam 310 and the upper surface of the contact rail 320, while the second contact rail information acquisition device 122, located at the lower position, is specifically used to acquire image information of the outer surface of the contact rail 320. The image information acquired by the first contact rail information acquisition device 121 is used to analyze the installation position of the contact rail 320, and the image information acquired by the second contact rail information acquisition device 122 is used to analyze the wear degree of the contact rail 320.

[0062] To obtain image information of the running surface 311 of the track beam 310 and the upper surface of the contact rail 320, the first contact rail information acquisition device 121 is installed above the plane where the running surface 311 of the track beam 310 is located, and acquires images from a downward tilting perspective. In this embodiment, the downward tilt angle (the angle between the mounting plane and the horizontal plane) of the first contact rail information acquisition device 121 can be set in the range of 30° to 40°, preferably 35°. The second contact rail information acquisition device 122 is specifically used to acquire images of the contact rail 320. Its installation position is relatively flexible. It can be installed above or below the contact rail 320 to acquire images from a tilting perspective, or it can be directly facing the outer surface of the contact rail 320. In short, any installation position that can acquire a complete image of the outer surface of the contact rail 320 is acceptable.

[0063] The laser image information collected by the first contact rail information acquisition device 121 is as follows: Figure 6 As shown, line A corresponds to the laser beam projected onto the running surface 311 of the track beam 310, and line B corresponds to the laser beam projected onto the upper surface of the contact rail 320. The detection system host 110 analyzes and calculates the image information to obtain the spatial distance between lines A and B, which is the height difference between the running surface 311 of the track beam 310 and the upper surface of the contact rail 320. Based on this height difference, the installation position of the contact rail 320 on the track beam 310 can be determined, thereby judging whether the installation position is within an acceptable range.

[0064] The laser image information acquired by the second contact rail information acquisition device 122 is as follows: Figure 7 As shown, line C corresponds to the laser beam projected onto the surface of the stainless steel strip 322 on the contact rail 320. Figure 4 As shown, the main body of the contact rail 320, a steel-aluminum composite rail, includes an aluminum rail body 321 and a stainless steel strip 322. The stainless steel strip 322 protrudes from the aluminum rail body 321, and two feature points P1 and P2 appear at the connection point between the two. Therefore, as... Figure 7As shown, when the laser is projected on the surface of the contact rail 320, two corresponding feature points p1 and p2 are also formed. The detection system host 110 analyzes and calculates the image information, and can obtain the spatial distance between the feature point p1 and the line C and the spatial distance between the feature point p2 and the line C. The above two spatial distances represent the height value of the protrusion of the surface of the contact rail 320, and whether the wear degree of the contact rail 320 is within an acceptable range is judged.

[0065] As shown in the figure, Figure 8 As shown, the speed measuring wheel 211 and the photoelectric encoder are also fixedly installed on the chassis of the vehicle body 210 of the inspection engineering vehicle 200. The speed measuring wheel 211 rotates synchronously with the running of the engineering vehicle, and the photoelectric encoder is installed on the wheel shaft of the speed measuring wheel 211. When the wheel shaft of the speed measuring wheel 211 rotates, the inner shaft of the photoelectric encoder is driven to rotate synchronously, and the photoelectric encoder outputs pulse signals at equal intervals to the detection system host 110, which can be used as a basis for calculating the running mileage of the inspection engineering vehicle 200, so as to obtain the position of the inspection engineering vehicle 200 or the position of the contact rail 320 defect.

[0066] In addition to the contact rail detection and track beam detection functions, the inspection engineering vehicle 200 also has a limit detection function. Two laser radars are also installed at the front end of the vehicle body 210 of the inspection engineering vehicle 200. The laser radars scan to both sides of the engineering vehicle, and the scanning range of the radars can reach 360°, and the detection distance can cover the limit range. When an obstacle appears in the limit, the laser radar can detect the obstacle, and the detection system host 110 can record the data and issue an intrusion limit warning to realize the limit scanning function.

[0067] The inspection engineering vehicle provided by the application integrates the contact rail detection and limit detection functions, replaces the traditional manual inspection method, saves manpower and time, improves the detection efficiency, and further has more uniform detection standards, avoids the inspection result deviation caused by the different personal experiences of the inspection personnel, and makes the detection result more reliable.

[0068] As shown in the figure, Figure 9 In one embodiment of the application, the detection system host 110 obtains the installation position of the contact rail 320 by the laser image information collected by the first contact rail information collection device 121, and the method comprises the following steps:

[0069] S11, introduce the matrix convolution algorithm into the Steger algorithm to extract the structured light fringe center in the image.

[0070] The principle of Steger algorithm is that the curve structure in the two-dimensional image can be approximated as having a parabolic distribution in its normal direction n(t), so that the first-order directional derivative is 0 at the expected center point, and the second-order directional derivative is a large absolute value. Therefore, the implementation steps of Steger algorithm are divided into three steps, first, in order to ensure the general denoising of the image and the point-by-point differentiation, generally, the image is convolved by using Gaussian kernels; second, the normal direction of the curve is calculated; finally, the point satisfying the above directional derivative characteristics is selected, that is, the center point to be obtained.

[0071] In order to improve the operation ability, the application uses the high-performance parallel computing framework CUDA of Nvidia GPU to realize fast and efficient convolution operation, improves the traditional Steger algorithm, and makes the calculation ability improved by about 20 times. The scheme not only greatly reduces the operation time, but also can process a large amount of image information acquired at high speed, so that the realization of the whole algorithm becomes possible.

[0072] S12, for the extracted light stripe center, through the matching algorithm, the feature position analysis of the image is carried out, and the track beam running surface feature line and the contact rail upper surface feature line are extracted.

[0073] According to the geometric shape of the track beam and the contact rail, first, a standard parallel line and a trapezoidal structure are designed as a comparison template. The extracted light stripe center in the collected image information also has corresponding parallel lines and trapezoidal structures. According to the structure information entropy Φ between the comparison template and the specific light stripe center neighborhood, the similarity between the two structures is analyzed, the light stripe center with the maximum similarity is selected as the positioning of the trapezoidal feature on the light stripe curve, and thus the specific image coordinates of the light stripe center points of the line A and the line B are obtained.

[0074] Similarly, in order to improve the operation ability, the application uses the high-performance computing framework CUDA of Nvidia GPU to improve the sequential execution in the traditional algorithm to parallel execution, improve the calculation performance of the matching, realize the batch processing ability and real-time performance.

[0075] S13, the height difference between the track beam running surface and the upper surface of the contact rail is calculated, and thus the installation position information of the contact rail is obtained.

[0076] The coordinate conversion equation of the image coordinate system and the space coordinate system is obtained by calibrating the contact rail information acquisition device. The calibration is the process of obtaining the conversion relationship between the two-dimensional image coordinates and the three-dimensional space coordinates, and the specific method is as follows: Figure 10As shown, a calibration board is set up, typically with a checkerboard pattern, and the size of each checkerboard cell is known. First, images of the calibration board are captured using a camera, and multiple images of the calibration board are processed to eliminate image aberrations. Second, multiple images of laser light illuminating the calibration board are captured. Since the size of each checkerboard cell is known, multiple laser beams can be fitted to the laser plane equation, and the transformation equation between image coordinates and spatial coordinates can be obtained.

[0077] Substitute the points on line A and line B into the coordinate transformation equation to convert the two-dimensional coordinates into three-dimensional coordinates. This will give you the coordinates of the points on the two spatial lines. Fit the points on the two spatial lines to the equations of the two lines, and then use spatial geometry to calculate the distance between the two lines. This distance is the height difference between the upper surface of the contact rail and the running surface of the track beam that needs to be measured.

[0078] The method for detecting the installation position of the contact rail further includes: S14, where the host of the detection system receives a pulse signal emitted by a photoelectric encoder, and when the installation position of the contact rail exceeds the normal range, the host calculates the running mileage of the inspection vehicle based on the pulse signal, thereby locating the position of the contact rail.

[0079] like Figure 11 As shown, in one embodiment of the present invention, the method for the detection system host 110 to obtain wear information of the contact rail 320 by acquiring laser image information from the second contact rail information acquisition device 122 includes the following steps:

[0080] S21 introduces the matrix convolution algorithm into the Steger algorithm to extract the center of structured light stripes in the image. The specific method is the same as that described in S11 above.

[0081] S22, for the extracted light stripe center, through the matching algorithm, the feature position analysis of the image is performed to extract the contact rail surface feature points p1, p2 and the feature lines between the feature points.

[0082] The surface of contact rail 320 has significant turning points P1 and P2. A matching algorithm identifies feature points p1, p2, and line C in the image. The matching algorithm is similar to the method described in S12, using pre-designed standard feature points as comparison templates. Based on the structural information entropy Φ between the comparison template and the neighborhood of a specific light stripe center, a similarity analysis is performed between the two structures. The center of the light stripe with the highest similarity is selected as the location of the feature point on the light stripe curve.

[0083] S23, calculate the height of the protrusion on the contact rail surface, and then compare it with the initial height of the protrusion on the contact rail surface to obtain contact rail wear information.

[0084] After the feature points p1 and p2 and the line C in the image are recognized, the coordinates of the feature points p1 and p2 and the coordinates of the point set on the line C are obtained. The above coordinates are respectively brought into the coordinate conversion equation, the two-dimensional coordinates are converted into three-dimensional coordinates, the points on the line C are fitted into a spatial straight line equation, and the distance from the feature point p1 to the spatial straight line and the distance from the feature point p2 to the spatial straight line are calculated as the height value of the protrusion on the side surface of the contact rail. Further, it can be judged whether the wear of the contact rail exceeds the normal range. Through the distance from the feature point p1 to the spatial straight line and the distance from the feature point p2 to the spatial straight line, not only the overall wear degree information of the contact rail 320 can be obtained, but also it can be further known whether the contact rail 320 has occurred eccentric wear. For example, if the distance from the feature point p1 to the spatial straight line exceeds the reasonable range, but the distance from the feature point p2 to the spatial straight line does not exceed the reasonable range, it means that the wear degree of the upper end surface of the contact rail 320 is more serious than that of the lower end surface. According to the eccentric wear information, the contact rail 320 can be adjusted.

[0085] The method for detecting the wear degree of the contact rail further includes: S24, the detection system host receives the pulse signal sent by the photoelectric encoder, and calculates the running mileage of the inspection engineering vehicle according to the pulse signal when the wear degree of the contact rail exceeds the normal range, so as to position the contact rail.

[0086] The above description of the disclosed embodiments enables one skilled in the art to make or use the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A contact rail detection system for a straddle-type monorail, characterized in that, The detection system comprises a detection system host and a contact rail information acquisition device, the contact rail information acquisition device is used to acquire track beam and contact rail image information, and the detection system host obtains installation position information and wear information of the contact rail according to the image information; The contact rail information acquisition device comprises a first contact rail information acquisition device and a second contact rail information acquisition device, the image information acquired by the first contact rail information acquisition device is used for the detection system host to obtain the installation position information, the image information acquired by the second contact rail information acquisition device is used for the detection system host to extract the center of the structured light stripe in the image by using the Steger algorithm with the introduction of the matrix convolution algorithm, and the extracted light stripe center is used for the detection system host to analyze the feature position of the image by using a matching algorithm, extract the feature points p1 and p2 on the surface of the contact rail and the feature lines between the feature points, and calculate the height of the protrusion on the surface of the contact rail, and then the wear information is obtained by comparing with the initial protrusion height on the surface of the contact rail; the wear information comprises overall wear degree information and eccentric wear degree information, the image information acquired by the first contact rail information acquisition device is image information of a track beam running surface and an upper surface of the contact rail, and the image information acquired by the second contact rail information acquisition device is image information of an outer surface of the contact rail; The installation position information is information determined based on the height difference between the track beam running surface and the upper surface of the contact rail after the detection system host extracts the center of the structured light stripe in the image by using the Steger algorithm with the introduction of the matrix convolution algorithm and analyzes the feature position of the image by using a matching algorithm and extracts the feature lines on the track beam running surface and the upper surface of the contact rail; The contact rail information acquisition device has a shell, a plane array camera and a linear laser are fixedly arranged in the shell, a window is arranged on the shell, the linear laser projects laser onto the track surface through the window, and the plane array camera acquires laser image information projected onto the track surface through the window; the axis line of the plane array camera and the linear laser forms an included angle, and the included angle is 23°-39°.

2. A straddle-type monorail inspection engineering vehicle, comprising a vehicle body, a walking mechanism is arranged on a chassis of the vehicle body, characterized in that, The detection system further comprises a suspension side compartment connected with the vehicle body, the detection system host is arranged in the vehicle body, and the contact rail information acquisition device is arranged on the side opposite to the track of the suspension side compartment.

3. A method of detecting a position of a contact rail of a straddle-type monorail by using the contact rail detection system according to claim 1, characterized by The method comprises the following steps: The first contact rail information acquisition device transmits the acquired track beam and contact rail image information to the detection system host; The detection system host introduces the matrix convolution algorithm into the Steger algorithm to extract the center of the structured light stripe in the image; The extracted light stripe center is used for the detection system host to analyze the feature position of the image by using a matching algorithm, and extract the feature lines on the track beam running surface and the upper surface of the contact rail; The height difference between the track beam running surface and the upper surface of the contact rail is calculated, and the installation position information of the contact rail is obtained.

4. The method of claim 3, wherein the position of the conductor rail is detected by the sensor. The specific method for extracting the characteristic line of the track beam running surface and the upper surface of the contact rail is as follows: first, according to the geometric shape of the track beam running surface and the contact rail, a standard parallel line and a trapezoidal structure are designed as a comparison template; second, the structural information entropy between the comparison template and the extracted light stripe center neighborhood is taken as the basis for similarity analysis between the two structures, and the light stripe center with the largest similarity is selected as the trapezoidal feature on the light stripe curve, so as to identify the characteristic line of the track beam running surface and the upper surface of the contact rail.

5. A method for detecting wear of a contact rail of a straddle-type monorail, using the contact rail detection system according to claim 1, characterized by The method comprises the following steps: The second contact rail information acquisition device transmits the collected contact rail image information to the detection system host; The detection system host introduces a matrix convolution algorithm into the Steger algorithm to extract the structural light stripe center in the image; For the extracted light stripe center, the feature position of the image is analyzed by a matching algorithm to extract the contact rail surface feature points p1 and p2 and the characteristic line between the feature points; The height of the contact rail surface protrusion is calculated, and the contact rail wear information is obtained by comparing with the initial contact rail surface protrusion height.

6. The method of claim 5, wherein the method comprises the steps of: determining the distance between the contact rail and the contact rail support; and determining the wear of the contact rail based on the distance between the contact rail and the contact rail support. The specific method for extracting the contact rail surface feature points p1 and p2 and the characteristic line between the feature points is as follows: first, according to the geometric shape of the contact rail surface, a standard feature point is designed as a comparison template; second, the structural information entropy between the comparison template and the extracted light stripe center neighborhood is taken as the basis for similarity analysis between the two structures, and the light stripe center with the largest similarity is selected as the feature point on the light stripe curve, so as to identify the contact rail surface feature points p1 and p2 and the characteristic line between the feature points p1 and p2.

7. The method of claim 6, wherein the method further comprises: determining a distance between the contact rail and the contact rail sensor; and determining a wear of the contact rail based on the determined distance. The specific method for obtaining the contact rail wear information is as follows: after identifying the feature points p1 and p2 and the characteristic line, the coordinates of the feature points p1 and p2 and the coordinates of the point set on the characteristic line are obtained, the two-dimensional coordinates are converted into three-dimensional coordinates through a coordinate conversion equation, the points on the characteristic line are fitted into a spatial straight line equation, the distance from the feature point p1 to the spatial straight line and the distance from the feature point p2 to the spatial straight line are calculated, the height value of the contact rail surface protrusion is represented, and the contact rail wear information is obtained by comparing with the initial contact rail surface protrusion height value.

Images