Electric locomotive inspection method and device

Abstract

The invention provides an electric locomotive inspection method, which comprises the following steps: firstly, determining an offset distance between a parking point location of a to-be-detected electric locomotive and a standard locomotive parking point location, and sending a correction instruction for inspecting the parking point location to a robot according to the offset distance, the inspection method comprises the steps of modifying inspection parking points of the robot, then obtaining to-be-analyzed images collected by the robot for all the to-be-detected parts at the modified inspection parking points, and then determining detection results of the to-be-detected parts according to the to-be-analyzed images, so that the inspection method not only replaces manual inspection, but also corrects the inspection parking points of the robot, and the inspection efficiency is improved. The to-be-analyzed image capable of accurately reflecting the condition of the to-be-detected part is obtained, and then an accurate detection result is obtained.

Description

Technical Field

[0001] This document relates to the field of electric locomotive technology, and in particular to a method and apparatus for inspecting electric locomotives. Background Technology

[0002] With the rapid development of electric locomotives in recent years, the inspection of electric locomotives has become the most labor-intensive part of the maintenance work.

[0003] Currently, locomotive maintenance mainly relies on manual inspection using methods such as visual inspection and hammering. However, the quality of manual inspection is inconsistent and the efficiency is low, while the accuracy of robot inspection needs to be improved. Summary of the Invention

[0004] This application provides a method and apparatus for inspecting electric locomotives to solve the problems existing in the current manual inspection and improve the accuracy of inspection.

[0005] To solve the above-mentioned technical problems, this application is implemented as follows: Firstly, a method for inspecting electric locomotives is provided, the method comprising: Determine the offset distance between the stopping point of the electric locomotive to be tested and the standard locomotive stopping point; Based on the offset distance, a correction command for the inspection operation parking point is sent to the robot; The robot acquires images of each component to be inspected at each of the corrected inspection operation parking points; Based on the image to be analyzed, the detection result of the component to be detected is determined.

[0006] Secondly, a method for inspecting electric locomotives is provided, the method comprising: In response to the received correction command, the parking points for the inspection operation are corrected; Images are collected from each component of the electric locomotive to be inspected at each of the revised inspection operation stopping points to obtain images to be analyzed; Upload the image to be analyzed.

[0007] Thirdly, an electric locomotive inspection device is provided, the device comprising: The offset distance determination module is used to determine the offset distance between the parking point of the electric locomotive to be tested and the standard locomotive parking point; The correction module is used to send correction instructions for the inspection operation stopping point to the robot based on the offset distance; The image acquisition module is used to acquire images of the components to be inspected collected by the robot at each of the corrected inspection operation parking points according to a preset action path. The detection module is used to determine the detection result of the component to be detected based on the image to be analyzed.

[0008] Fourthly, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the data transmission method described above.

[0009] Fifthly, a computer program product is provided, the computer program product including a data access processing program, which, when executed by a processor, is capable of implementing the steps of the method described above.

[0010] This application provides a method for inspecting electric locomotives. First, the offset distance between the parking point of the electric locomotive to be inspected and the standard locomotive parking point is determined. Based on this offset distance, a correction command for the inspection operation parking point is sent to the robot. Then, images to be analyzed are acquired by the robot at the modified inspection parking point for each component to be inspected. Based on these images, the inspection results of the components to be inspected are determined. Thus, this inspection method not only replaces manual inspection but also corrects the robot's inspection operation parking point to obtain images to be analyzed that accurately reflect the condition of the components to be inspected, thereby obtaining accurate inspection results. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in one or more embodiments of this specification, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A flowchart illustrating an electric locomotive inspection method provided in this specification's embodiments; Figure 2 A flowchart illustrating yet another electric locomotive inspection method provided in the embodiments of this specification; Figure 3 This is a schematic diagram of a two-dimensional list data in an electric locomotive inspection method provided in an embodiment of this specification; Figure 4 A flowchart illustrating yet another electric locomotive inspection method provided in the embodiments of this specification; Figure 5 This is a schematic diagram of the standard wheel spacing of a single HXD3C locomotive provided in the embodiments of this specification; Figure 6 A flowchart illustrating yet another electric locomotive inspection method provided in the embodiments of this specification; Figure 7This is a schematic diagram of the structure of an electric locomotive inspection device provided in the embodiments of this specification; Figure 8 A schematic diagram of another electric locomotive inspection device provided in the embodiments of this specification; Figure 9 A schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0013] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0014] One or more embodiments of an electric locomotive inspection method provided in this specification are as follows: Reference Figure 1 The document illustrates a flowchart of an electric locomotive inspection method provided in this embodiment, which may include steps 102 to 108. This method can be applied to a server, an intelligent electric locomotive management platform, or electronic devices. The server or intelligent electric locomotive management platform can manage multiple electric locomotives (including locomotives to be inspected) and multiple robots (including robots located under or on the sides of the locomotive, inspection robots, and positioning robots). Electronic devices include, but are not limited to, mobile phones, tablets, and computers. The aforementioned inspection method includes: Step 102: Determine the offset distance between the parking point of the electric locomotive to be tested and the standard locomotive parking point.

[0015] Step 104: Based on the offset distance, send a correction command for the inspection operation parking point to the robot.

[0016] Step 106: Acquire the images to be analyzed collected by the robot at each of the corrected inspection operation parking points for each component to be inspected. The robot can acquire these images at each inspection operation parking point according to a preset motion path.

[0017] Step 108: Determine the detection result of the component to be detected based on the image to be analyzed. After acquiring the image to be analyzed, detection can be performed according to a pre-set detection template, and the detection result can be obtained. The pre-set detection template is obtained through learning and training.

[0018] The aforementioned components to be tested may be key components of the locomotive, and the testing items or contents for the aforementioned components to be tested may include loosening, cracking, loss, foreign objects, distance, etc.

[0019] In the above steps, the robot can be a single type of robot or multiple types of robots. If it is a single robot, it not only has the function of acquiring images to be analyzed for inspection, but also can scan and locate the electric locomotive to be inspected to determine the offset distance between the locomotive's stopping point and the standard locomotive stopping point. If multiple robots are used, one type of robot can acquire images to be analyzed for inspection, and another type can scan and locate the electric locomotive to be inspected.

[0020] An embodiment of this application discloses an electric locomotive inspection method. First, the offset distance between the parking point of the electric locomotive to be inspected and the standard locomotive parking point is determined. Based on the offset distance, a correction instruction for the inspection operation parking point is sent to the robot. Then, images to be analyzed are acquired by the robot at the modified inspection parking point for each component to be inspected. Based on these images, the inspection results of the components to be inspected are determined. Thus, the inspection method of this application not only replaces manual inspection but also corrects the robot's inspection operation parking point to obtain images to be analyzed that more accurately reflect the condition of the components to be inspected, thereby obtaining more accurate inspection results.

[0021] When an electric locomotive enters the maintenance bay, the driver manually slows down and brakes, resulting in a different stopping position each time. This means the stopping point for each locomotive under inspection is different. If this difference is ignored, and the robot directly collects images of the component under test based on the standard inspection points corresponding to the standard locomotive stopping points, the images may not accurately reflect the component under inspection, leading to inaccurate detection results. Therefore, in the embodiments of this application, it is necessary to determine the offset distance between the stopping point of the electric locomotive under inspection and the standard locomotive stopping point. Based on this offset distance, the robot's inspection stopping point is modified to collect images at the corrected stopping point, thereby obtaining more accurate detection results.

[0022] Of course, the inspection method of this application can be used for the inspection of electric locomotives or for the inspection of non-electric locomotives, such as other types of locomotives.

[0023] In one embodiment, the electric locomotive inspection method provided in this embodiment may include the following steps 202 to 216, as referred to Figure 2 This illustrates steps 202 to 208 provided in this embodiment.

[0024] Step 202: Based on the scanning of multiple first components in the electric locomotive to be inspected during the robot's movement, determine the two-dimensional list data List(x,h). The two-dimensional list data includes coordinate data x along the direction of movement and the corresponding contour data h of the multiple first components, which are arranged along the direction of movement.

[0025] During its movement, the robot can travel at a preset, constant speed to achieve uniform scanning, such as moving in a straight line at a constant speed of 1.0 m / s. The robot can be equipped with a TOF laser sensor or other scanning sensors. The sensor's light spot can be positioned at a preset distance (e.g., 5 cm) from the countertop or ground. The robot can collect real-time coordinate data (x, y) and TOF sensor data at a frequency of 10 Hz (valid data value is 5, invalid value is 0), ultimately resulting in a two-dimensional list data List(x, h) containing the robot's X-axis coordinate data and TOF sensor data during its movement. The data is illustrated below. Figure 3 As shown.

[0026] Before the robot scans to obtain two-dimensional list data, it can use its onboard 2D color line scan camera to perform a panoramic scan of the undercarriage components to determine the approximate location of the electric locomotive to be inspected.

[0027] The robot described above can be equipped with a 6-DOF collaborative robotic arm and a 3D camera.

[0028] Step 204: Determine the first position information of each first component relative to the robot coordinate system based on the two-dimensional list data.

[0029] Here, the robot coordinate system refers to the coordinate map on which the robot operates. The first component can be a wheel pair or a wheel, or other components on the electric locomotive. The first component can be components arranged relatively evenly on the electric locomotive. When the first component is a wheel pair, the robot in step 202 travels under the electric locomotive to scan the contours of multiple wheel pairs.

[0030] Among them, wheelset refers to the wheels of the two cars of an electric locomotive.

[0031] In one embodiment, step 204 may include steps 2041, 2042 and 2043.

[0032] Step 2041: Determine the target two-dimensional list data from multiple sets of two-dimensional list data of the electric locomotive to be tested. For the same electric locomotive to be tested, since the two-dimensional category data acquired in a single instance may be invalid or have large errors, multiple sets of two-dimensional list data can be acquired for a single electric locomotive to be tested, and the target two-dimensional list data can be determined from these multiple sets of two-dimensional list data.

[0033] Step 2042: Based on the target two-dimensional list data, determine the median value of the coordinate data corresponding to each data segment h1. The median value represents the position of each wheelset in the work track map. The data segment h1 is selected from the contour data h and represents the presence of a wheelset.

[0034] The data segment h1 representing the wheelset can be filtered from the contour data of the two-dimensional list data. As mentioned above, the valid value of the TOF sensor data received is 5, and the invalid value is 0. Figure 3 In this process, the data segment h1 corresponding to the wheel pair can be determined based on the valid and invalid values. This data segment h1 represents the wheel pair that has been scanned.

[0035] Step 2043: Determine the wheel position information of each wheel pair relative to the robot coordinate system based on the intermediate value.

[0036] The intermediate value is the contact position of each wheel pair. Based on the correspondence between the pre-established work track map and the robot coordinate system (robot coordinate map), the wheel position information of each wheel pair relative to the robot coordinate system can be determined.

[0037] The process of determining target two-dimensional list data from multiple sets of two-dimensional list data of the electric locomotive to be inspected includes: determining valid two-dimensional list data from the multiple sets of two-dimensional list data. Specifically, the validity of each set of two-dimensional list data can be determined based on the number of data segments h1 in each set of two-dimensional list data and the number N of standard wheelsets of the electric locomotive. Data segment h1 is selected from the contour data h and indicates the presence of wheelsets. The number of data segments h1 represents the number of wheelsets. Each type of electric locomotive has a corresponding number of standard wheelsets N. If the number of data segments h1 in the two-dimensional list data is less than the corresponding number of standard wheelsets, it indicates a scanning error or missed scan, and the two-dimensional list data is considered invalid; otherwise, the two-dimensional list data is considered valid.

[0038] Determining the target two-dimensional list data from multiple sets of two-dimensional list data of the electric locomotive under test further includes: determining the target two-dimensional list data based on the error value between the valid two-dimensional list data and the standard wheel data. Specifically, the error can be calculated between the data set consisting of the median values ​​of the coordinate data corresponding to each data segment h1 in the multiple sets of valid two-dimensional list data and the data set of the standard distance between the standard wheelset, and the set of valid two-dimensional list data with the smallest error can be determined as the target two-dimensional list data. The error calculation can be performed using the least squares method.

[0039] Specifically, the standard spacing between N standard wheelsets is obtained from the locomotive configuration file. The locomotive configuration file contains pre-existing component and assembly information for various models of electric locomotives, thus enabling the extraction of the standard spacing between N standard wheelsets corresponding to the model of the electric locomotive to be tested from the locomotive configuration file.

[0040] Step 206: Determine the parking location of the electric locomotive to be detected based on the first location information.

[0041] Since the position of the first component on the electric locomotive is relatively fixed, the stopping point of the electric locomotive to be tested can be determined based on the first position information of the first component relative to the robot coordinate system, that is, the stopping point of the electric locomotive to be tested in the robot coordinate system can be determined.

[0042] Step 208: Determine the offset distance based on the parking point of the electric locomotive to be tested and the standard locomotive parking point. The standard locomotive parking point is pre-acquired and refers to the parking point of the electric locomotive in the robot coordinate system under standard conditions. Therefore, the offset distance of the electric locomotive to be tested relative to the standard locomotive parking point can be determined.

[0043] Steps 210 to 216 can refer to steps 102 to 108 disclosed in the above embodiments, and will not be repeated here.

[0044] In this embodiment of the application, by scanning multiple first components in the electric locomotive to be inspected, a two-dimensional list data List(x,h) is determined, thereby determining the first position information of the multiple first components, and thus accurately determining the stopping point of the electric locomotive to be inspected, thereby improving the inspection accuracy.

[0045] The first position information of the first component (such as the wheelset) is inferred by scanning during the robot's movement. Because fluctuations may occur during robot movement, and there may be interfering components around the first component (such as wheel chocks or sand-spreading pipes), the obtained first position information may have a large error, leading to a large error in the obtained offset distance. To eliminate this error, after determining the initial position coordinates, the offset distance needs to be determined more precisely. Therefore, in one embodiment, step 206 may include step 402, which includes: determining the initial position coordinates of the electric locomotive to be detected in the robot coordinate system based on the first position information. The positioning accuracy of these initial position coordinates can be maintained at approximately ±3cm. Step 208 may include steps 404 to 410, and steps 402 to 410, which can be referred to... Figure 4 .

[0046] Step 404: Determine the current target position based on the primary position coordinates. Based on these primary position coordinates, the approximate position of the electric locomotive to be detected can be determined, thereby enabling the rapid determination of the target position corresponding to the electric locomotive.

[0047] Step 406: Acquire the image of the second component of the electric locomotive under test collected by the robot at the current target point position, and determine it as the image to be registered. The robot moves to the current target point position and collects an image of the second component on the electric locomotive under test in a preset posture, and determines the image to be registered.

[0048] Step 408: Based on the image to be registered corresponding to the electric locomotive to be detected and the pre-acquired standard target point image corresponding to the standard locomotive parking point, determine the deviation value between the current target point position and the pre-set standard target point position. The positioning accuracy of this deviation value can be improved to ±5mm, which is significantly improved compared to the positioning accuracy of the primary position coordinates.

[0049] Step 410: Determine the offset distance based on the deviation value.

[0050] In the above embodiments, compared with the information scanned during the robot's movement, the image to be registered is collected when the robot is stopped. Therefore, the collected image information is more accurate, the deviation value obtained is smaller, and the offset distance is determined more accurately.

[0051] The second component can be a distinctive and structurally uniform part, such as a traction beam star disk and / or a bogie. The second component can be located under and / or on the side of the electric locomotive. Based on the position of the second component and the primary position coordinates, the current target location can be quickly determined.

[0052] In one embodiment, step 206 may include, after step 402, directly determining the parking location of the electric locomotive to be detected using the primary position coordinates in step 402.

[0053] Among them, the standard locomotive parking point can be a pre-set point, and the standard target point is also a pre-set object.

[0054] Taking the HXD3C double-unit electric locomotive under test as an example, its standard wheelset count is 12. Therefore, the aforementioned N can be 12, and Figure 5 The standard wheel spacing of a single HXD3C locomotive is shown.

[0055] This application provides another method for inspecting electric locomotives, see embodiments thereof. Figure 6The method may include steps 602 to 606, and can be applied to robots or electronic devices. The robot may include a positioning or inspection robot, and may be equipped with wheels, a camera, and a robotic arm; the camera may be located at the end of the robotic arm. The method includes: Step 602: In response to the received correction command, the inspection operation parking point is corrected. According to the received correction command, the robot moves from the preset standard inspection operation point to the corrected inspection operation parking point.

[0056] Step 604: Images are acquired at each of the inspected components of the electric locomotive at the corrected inspection operation stopping points to obtain images for analysis. The robot can acquire images of each inspected component according to a preset motion path. The robot can acquire images at each inspection operation stopping point, i.e., when the robot is stopped, resulting in clearer and more accurate images.

[0057] Step 606: Upload the image to be analyzed.

[0058] When an electric locomotive enters the maintenance bay, the driver manually slows down and brakes, resulting in a different stopping position each time. This means the stopping point for each locomotive under inspection is different. If this difference is ignored, and the robot directly collects images of the component under test based on the standard inspection points corresponding to the standard locomotive stopping points, the images may not accurately reflect the component under inspection, leading to inaccurate detection results. Therefore, in the embodiments of this application, it is necessary to determine the offset distance between the stopping point of the electric locomotive under inspection and the standard locomotive stopping point. Based on this offset distance, the robot's inspection stopping point is modified to collect images at the corrected stopping point, thereby obtaining more accurate detection results.

[0059] The method includes, prior to responding to the received correction instruction: In response to the received scanning command, the system continuously scans multiple first components in the electric locomotive to be inspected along a preset path during its journey, and determines a two-dimensional list data List(x,h). The two-dimensional list data includes coordinate data x along the direction of travel and contour data h of the corresponding multiple first components, which are arranged along the direction of travel.

[0060] For more accurate detection, multiple first components should be arranged along the length of the electric locomotive to be inspected; therefore, the first components can be wheelsets. Of course, the first components can also be arranged outside the length of the electric locomotive. When the first components are wheelsets, the robot can travel along the length of the electric locomotive under its chassis.

[0061] In one implementation, the robot can achieve the above functions based on laser SLAM navigation technology, including the scanning and inspection functions.

[0062] In one implementation, multiple robots can work collaboratively, including dynamic allocation of tasks, dynamic path planning, and information sharing. Each robot, upon receiving a task, autonomously plans its path from the current station to the target station. When multiple robots work simultaneously, conflicts may arise in their paths. To address this, robots share their real-time positions on the station map, and traffic control is implemented at intersections. Furthermore, the location where a robot waits to pass must not interfere with the routes of any electric locomotives on the tracks.

[0063] To meet the timeliness requirements of operations, various robot working modes can be configured for the electric locomotives to be inspected, including: 2+2 mode, 1+2 mode, 1+1 mode, and a single robot full-operation mode. In the 2+2 mode, the locomotive preparation and inspection operation is broken down into four independent modules: left-side inspection, right-side inspection, front half of the undercarriage inspection, and rear half of the undercarriage inspection. Each of the four robots undertakes one task and works collaboratively to complete it. In the 1+2 mode, the locomotive preparation and inspection operation is broken down into three independent modules: left-side inspection, right-side inspection, and undercarriage inspection, which are completed collaboratively by three robots. In the 1+1 mode, one robot completes the inspection of the side and the undercarriage, respectively. A single robot can also complete the entire locomotive inspection, with the workflow being: first the undercarriage inspection, then the side inspection. The aforementioned server or intelligent electric locomotive management platform can communicate with multiple robots simultaneously.

[0064] In one implementation, the robot may perform multiple tasks. Once the backend scheduling system (such as a server, intelligent electric locomotive management platform, electronic equipment, etc.) determines that a vehicle has entered the depot, it checks the robot and determines whether the operational conditions are met. If the robot meets the operational conditions, a predefined allocation strategy can be used to assign the task to a designated robot based on the task track number. The scheduling system can establish a robot task thread for each robot + task combination to manage the operation process. For each robot, if there are multiple tasks, new tasks are placed in a task queue, and the robot executes them sequentially according to the queue order. When a robot task thread terminates abnormally or normally, it reprocesses the robot task queue, re-executing the next task or assigning the task to another robot. These tasks include, but are not limited to, locating the electric locomotive, inspecting the electric locomotive, using cameras to collect images, moving, and changing the robotic arm's posture.

[0065] As mentioned above, the robot may include a robotic arm and a 3D camera. Before using the camera to capture images, hand-eye calibration of the robot is required. The following is an introduction to hand-eye calibration.

[0066] Because the camera is mounted on the end effector of the robotic arm, the calibration method is hand-eye calibration with the eye on the hand. Based on the analysis, the following equation exists:

[0067] in This indicates the pose between the robotic arm's base coordinate system and the imaging component. The poses of the robot arm's base coordinate system and end effector are known and provided by the robot arm controller. It is the pose of the robotic arm end effector to the center of the camera, which is a constant and also the target of the hand-eye calibration solution. This refers to the pose between the camera center and the capturing component. Since the calibration plate contains known geometric data, these shapes can be identified from the captured images, and then the pose relative to the camera can be calculated. .

[0068] Since the robotic arm and calibration plate are fixed during calibration, therefore The value is a constant. During calibration, the camera needs to acquire images of the calibration board from multiple different angles. The pose acquired in the first and second acquisitions has the following relationship:

[0069] Transform the above formula:

[0070] Let and let and let Then there exists the following equation:

[0071] During calibration, multiple groups of images were taken, so multiple above equations can be formed to constitute a system of equations, and then solved simultaneously to obtain , that is, the hand-eye matrix X is obtained.

[0072] After obtaining the hand-eye matrix, the above step 408 can be registered.

[0073] During registration, first perform conditional filtering on the current point cloud of the to-be-registered image belonging to the to-be-detected electric locomotive and the template point cloud of the standard target image belonging to the pre-acquired locomotive parking position corresponding to the standard. All point clouds with z b can be filtered out, where z is the depth of the point cloud, and a and b are the minimum depth and maximum depth of the to-be-detected component. Then, the coordinate systems of the current point cloud and the template point cloud are converted to the robotic arm base coordinate system using the following formula:

[0074] where is the pose from the end of the robotic arm to the camera center. represents the pose between the robotic arm base coordinate system and the end effector of the robotic arm, which is known and provided by the robotic arm controller. is the result of hand-eye calibration, that is, the above hand-eye matrix X. Multiply all points in the current point cloud and the template point cloud by to convert the point cloud in the camera coordinate system to the robotic arm base coordinate system.

[0075] During the registration of the current point cloud and the template point cloud, the NDT algorithm can be used for rough registration first, and then the ICP algorithm can be used for precise registration to improve the registration accuracy.

[0076] Among them, the above hand-eye calibration and registration between point clouds are prior arts and will not be elaborated here in detail.

[0077] In one implementation, the server or the intelligent electric locomotive management and control platform can, according to the locomotive operation plan and the locomotive's previous operation data, evaluate the duration requirement of each locomotive for in-depot maintenance operations through data analysis, and reasonably arrange the intelligent inspection robot for maintenance inspection operations accordingly; when multiple robots receive the integrated issued locomotive entry instruction, based on the relative position relationship between the standby positions of the robots and the target operation tracks, and according to the principles of preferentially arranging the underbody operation tasks, preferentially changing adjacent tracks, and the highest operation efficiency of the robots, dynamically allocate the target tasks of each robot.

[0078] In one implementation, after receiving the target task, each robot autonomously plans its path using an ant colony algorithm based on the shortest path principle. It then starts from the charging pile (or standby point) and proceeds to the starting point of the designated track and platform based on SLAM navigation technology. During this process, the robot provides real-time feedback on its location information and preempts critical paths. Once a path is occupied, other robots must wait to pass before they can proceed, allowing the path to be temporarily released after the previous robot has passed. This avoids interference between multiple robot paths.

[0079] In one implementation, after the robot arrives at the work start point and waits for the locomotive to enter the maintenance depot and stop on the track, the robot located under the locomotive first uses its onboard 2D color line scan camera to perform a panoramic scan of the undercarriage components; at the same time, it uses its onboard distance sensor to collect the coordinate data of the locomotive bogie axles, wheels and robot, and combines the locomotive configuration data with the least squares method to match the wheel information to obtain the approximate position coordinates of the locomotive on the robot map under the locomotive (with an accuracy of approximately ±3cm).

[0080] In one implementation, after completing its inspection, the robot will automatically return to the charging station or proceed to the next track to perform its task.

[0081] This application also provides an electric locomotive inspection device, which can perform the steps in the above-described electric locomotive inspection method and can be applied to servers, electronic devices, or intelligent electric locomotive management and control platforms. Figure 7 The device includes: The offset distance determination module 71 is used to determine the offset distance between the parking point of the electric locomotive to be tested and the standard locomotive parking point; The correction module 72 is used to send a correction command for the inspection operation parking point to the robot according to the offset distance; The image acquisition module 73 is used to acquire the images to be analyzed collected by the robot at each of the inspection operation parking points according to the preset action path for each component to be detected. The detection module 74 is used to determine the detection result of the component to be detected based on the image to be analyzed.

[0082] In one implementation, the offset distance determination module is specifically used for: Based on the scanning of multiple first components in the electric locomotive to be inspected during the robot's movement, a two-dimensional list data List(x,h) is determined. The two-dimensional list data includes coordinate data x along the direction of movement and contour data h of the corresponding multiple first components, which are arranged along the direction of movement. Based on the two-dimensional list data, determine the first position information of each of the first components relative to the robot coordinate system; Based on the first location information, the stopping point of the electric locomotive to be detected is determined; The offset distance is determined based on the parking point of the electric locomotive to be tested and the standard locomotive parking point.

[0083] In one embodiment, determining the parking location of the electric locomotive to be tested based on the first location information includes: determining the primary position coordinates of the electric locomotive to be tested in the robot coordinate system based on the first location information; The step of determining the offset distance based on the parking point of the electric locomotive to be tested and the standard locomotive parking point includes: determining the current target point position based on the primary position coordinates; acquiring a second component image of the electric locomotive to be tested collected by the robot at the current target point position, and determining it as the image to be registered; determining the deviation value between the current target point position and the pre-set standard target point position based on the image to be registered corresponding to the electric locomotive to be tested and the pre-acquired standard target point image corresponding to the standard locomotive parking point; and determining the offset distance based on the deviation value.

[0084] In one embodiment, the first component includes a wheel pair; Based on the two-dimensional list data, the first position information of each first component relative to the robot coordinate system is determined, including: The target two-dimensional list data is determined from multiple sets of two-dimensional list data of the electric locomotive to be tested; Based on the target two-dimensional list data, determine the median value of the coordinate data corresponding to each data segment h1. The median value represents the position of each wheelset in the work track map. The data segment h1 is selected from the contour data h and represents the existence of a wheelset. Based on the intermediate value, the wheel position information of each wheel pair relative to the robot coordinate system is determined.

[0085] In one implementation, determining the target two-dimensional list data from multiple sets of two-dimensional list data of the electric locomotive to be detected includes: Valid two-dimensional list data is determined from multiple sets of the two-dimensional list data; The target two-dimensional list data is determined based on the error value between the valid two-dimensional list data and the standard wheel data.

[0086] In one implementation, determining valid two-dimensional list data from multiple sets of the two-dimensional list data includes: Based on the number of data segments h1 in each of the two-dimensional list data and the number of standard wheelsets N of the electric locomotive, determine whether each of the two-dimensional list data is valid two-dimensional list data.

[0087] This application also provides an electric locomotive inspection device, which can perform the steps in the above-described electric locomotive inspection method and can be applied to robots. Figure 8 The device includes: The response module 81 is used to correct the inspection operation parking point in response to the received correction command; The acquisition module 82 is used to acquire images of each component to be inspected of the electric locomotive at each of the corrected inspection operation stopping points, and to acquire images to be analyzed. Upload module 83 is used to upload the image to be analyzed.

[0088] In one implementation, prior to responding to a received correction instruction, the method includes: In response to the received scanning command, the system continuously scans multiple first components in the electric locomotive to be inspected along a preset path during its journey, and determines a two-dimensional list data List(x,h). The two-dimensional list data includes coordinate data x along the direction of travel and contour data h of the corresponding multiple first components, which are arranged along the direction of travel.

[0089] Figure 9 The diagram illustrates the hardware structure of an electronic device implementing the embodiments of this application. Referring to the diagram, at the hardware level, the electronic device includes a processor and optionally, an internal bus, a network interface, and a memory. The memory may include RAM, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk storage device. Of course, the electronic device may also include other hardware required for other services.

[0090] The processor, network interface, and memory can be interconnected via an internal bus, which can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be categorized as an address bus, data bus, control bus, etc. For ease of illustration, only a single bidirectional arrow is used in this diagram, but this does not imply that there is only one bus or one type of bus.

[0091] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0092] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a device at the logical level that locates the target user. The processor executes the program stored in memory and specifically performs the following: Figure 1 , Figure 2 , Figure 4 and Figure 6 The methods disclosed in the embodiments shown achieve the functions and beneficial effects of the methods described in the preceding method embodiments, and will not be repeated here.

[0093] The above is as stated in this application. Figure 1 , Figure 2 , Figure 4 and Figure 6 The methods disclosed in the illustrated embodiments can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above methods can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0094] The electronic device can also execute the methods described in the preceding method embodiments and achieve the functions and beneficial effects of the methods described in the preceding method embodiments, which will not be repeated here.

[0095] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0096] This application also proposes a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform... Figure 1 , Figure 2 , Figure 4 and Figure 6 The methods disclosed in the embodiments shown achieve the functions and beneficial effects of the methods described in the preceding method embodiments, and will not be repeated here.

[0097] The computer-readable storage medium mentioned above includes read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc.

[0098] This application also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the various processes of the above-described method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0099] The computer program product provided in this application embodiment can implement the various processes in the foregoing method embodiments and achieve the same functions and effects, which will not be repeated here.

[0100] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 2 A device that provides the functions specified in one or more boxes.

[0102] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 4 One or more processes and / or boxes Figure 6 The function specified in one or more boxes.

[0103] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 2 Figure 4 Figure 6 Figure 1 Figure 2 Figure 4 Figure 6 Figure 1 Figure 2 Figure 4 Figure 6 Figure 1 Figure 2 Figure 4 Figure 6 Figure 1 Figure 2 Figure 4 Figure 6 Figure 1 The steps of the function specified in one or more boxes.

[0104] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0105] Memory may include non-persistent storage in computer-readable storage media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable storage media.

[0106] Computer-readable storage media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable storage media does not include transient media, such as modulated data signals and carrier waves.

[0107] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0108] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for inspecting an electric locomotive, characterized by, The method comprises: determining the offset distance between the parking point of the electric locomotive to be detected and the standard locomotive parking point; sending a correction instruction of the inspection operation parking point to the robot according to the offset distance; acquiring the images to be analyzed collected by the robot at the corrected inspection operation parking points on each component to be detected; determining the detection result of the component to be detected according to the images to be analyzed.

2. The method of claim 1, wherein, The determination of the offset distance between the parking point of the electric locomotive to be detected and the standard locomotive parking point comprises: determining a two-dimensional list data List(x, h) according to the scanning of a plurality of first components in the electric locomotive to be detected during the travel of the robot, the two-dimensional list data comprising coordinate data x along the travel direction and profile data h of the plurality of first components corresponding to the plurality of first components arranged along the travel direction; determining first position information of each of the first components relative to the robot coordinate system according to the two-dimensional list data; determining the parking point of the electric locomotive to be detected according to the first position information; determining the offset distance according to the parking point of the electric locomotive to be detected and the standard locomotive parking point.

3. The method of claim 2, wherein, The determination of the parking point of the electric locomotive to be detected according to the first position information comprises: determining a primary position coordinate of the electric locomotive to be detected in the robot coordinate system according to the first position information; The determination of the offset distance according to the parking point of the electric locomotive to be detected and the standard locomotive parking point comprises: determining a current target point position according to the primary position coordinate; acquiring a second component image of the electric locomotive to be detected collected by the robot at the current target point position, and determining the second component image as a to-be-registered image; determining a deviation value between the current target point position and a standard target point position set in advance according to the to-be-registered image corresponding to the electric locomotive to be detected and a standard target point image corresponding to the standard locomotive parking point acquired in advance; determining the offset distance according to the deviation value.

4. The method of claim 2, wherein, The first component comprises a wheel pair; The determination of the first position information of each of the first components relative to the robot coordinate system according to the two-dimensional list data comprises: determining a target two-dimensional list data from a plurality of two-dimensional list data of the electric locomotive to be detected; determining a middle value of the coordinate data corresponding to each of the data segments h1 in the target two-dimensional list data, the middle value representing the position of each of the wheel pairs in the operation track map, and the data segment h1 being selected from the profile data h and representing the existence of the wheel pair; determining wheel position information of each of the wheel pairs relative to the robot coordinate system according to the middle value.

5. The method of claim 4, wherein, The determination of the target two-dimensional list data from the plurality of two-dimensional list data of the electric locomotive to be detected comprises: determining effective two-dimensional list data from the plurality of two-dimensional list data; determining the target two-dimensional list data according to the error value between the effective two-dimensional list data and standard wheel data.

6. The method of claim 5, wherein, The determination of the effective two-dimensional list data from the plurality of two-dimensional list data comprises: According to the number of data segments h1 in each two-dimensional list data and the number N of standard wheel pairs of the electric locomotive, it is determined whether each two-dimensional list data is valid two-dimensional list data.

7. A method of inspecting an electric locomotive, characterized by, The method comprises: In response to the received correction instruction, the inspection operation parking position is corrected; At each of the corrected inspection operation parking positions, an image of each component to be detected of the electric locomotive is collected to obtain an image to be analyzed; The image to be analyzed is uploaded.

8. The method of claim 1, wherein, Before the response to the received correction instruction, the method comprises: In response to the received scanning instruction, a continuous scan of a plurality of first components in the electric locomotive to be detected is performed along a preset path during travel to determine two-dimensional list data List(x, h), the two-dimensional list data comprising coordinate data x along the travel direction and profile data h of the plurality of first components corresponding to the plurality of first components arranged along the travel direction.

9. An electric locomotive inspection device, characterized by comprising: The device comprises: An offset distance determination module for determining an offset distance between a parking position of the electric locomotive to be detected and a standard locomotive parking position; A correction module for sending a correction instruction of an inspection operation parking position to a robot according to the offset distance; An image to be analyzed acquisition module for acquiring an image to be analyzed collected by the robot at each of the corrected inspection operation parking positions according to a preset action path for each component to be detected; A detection module for determining a detection result of the component to be detected according to the image to be analyzed.

10. A readable storage medium, characterized by, The readable storage medium stores programs or instructions, which are executed by the processor to implement the steps of the data transmission method according to claims 1-8.

Images