Automatic train inspection method, device and system and storage medium

Abstract

The invention provides an automatic train inspection method, device and system and a storage medium. The method comprises the steps that a preset trench map is obtained, and the trench map comprises the preset parking position of a train and the position of each detection point under the train; controlling the automatic inspection robot in the trench to move towards the train according to the preset parking position, and acquiring a laser scanning signal of the automatic inspection robot in real time; if the laser scanning signal shows that the automatic inspection robot arrives at one end of the train, updating the position of each detection point according to the current position of the automatic inspection robot; and controlling the automatic inspection robot to move towards the other end of the train, and inspecting the train according to the updated position of each detection point in the moving process. The train inspection method can be simplified, and the inspection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle inspection, and in particular to a method, device, system and storage medium for automatic train inspection. Background Art

[0002] After the marshaling and debugging of the rail train is completed, it is necessary to re-inspect the key components such as the skirts on both sides of the train, the bottom plate under the car, the bogie area, etc., mainly to check whether the anti-loosening bolts are marked and loose, whether the bogie brake pads are installed upside down, whether the bottom plate locks are in place, whether the wire is tied upside down, whether there are foreign objects under the car, etc.

[0003] In the related art, an automatic inspection robot is usually used to re-inspect the train. The train stops above the trench, and the automatic inspection robot moves inside the trench according to its own positioning program and collects images at the corresponding detection points to detect the key components at the bottom of the train.

[0004] However, due to train manufacturing errors and train stop position deviations, it is necessary to reset the internal positioning program of the automatic inspection robot according to the train manufacturing parameters and train stop position before each inspection, and conduct train inspection only after debugging is correct.

[0005] In summary, the existing train inspection method is relatively cumbersome, which leads to low train inspection efficiency. Summary of the invention

[0006] The embodiments of the present invention provide a method, device, system and storage medium for automatic train inspection to solve the problems that the existing train inspection method is complicated and has low inspection efficiency.

[0007] In a first aspect, an embodiment of the present invention provides a train automatic inspection method, the method being applied to a train automatic inspection system, the train automatic inspection system comprising: an automatic inspection robot, the automatic inspection robot moving in a trench under the train;

[0008] The method comprises:

[0009] Obtaining a preset trench map, wherein the trench map includes a preset stop position of the train and positions of various detection points under the train;

[0010] According to the preset stop position, controlling the automatic inspection robot in the ditch to move toward the train, and acquiring the laser scanning signal of the automatic inspection robot in real time;

[0011] If the laser scanning signal shows that the automatic inspection robot has reached one end of the train, the position of each detection point is updated according to the current position of the automatic inspection robot;

[0012] The automatic inspection robot is controlled to move toward the other end of the train, and during the movement, the train is inspected according to the updated positions of the detection points.

[0013] In a possible implementation, controlling the automatic inspection robot to move toward the other end of the train and inspecting the train according to the updated positions of the detection points during the movement includes:

[0014] Control the automatic inspection robot to move toward the other end of the train, and when the automatic inspection robot reaches a position corresponding to a preset part of the train, control the automatic inspection robot to collect an actual point cloud data group of the preset part of the train; the preset part of the train is located between one end of the train and the first updated detection point;

[0015] According to the actual point cloud data set and the standard point cloud data set of the preset part of the train, the position of each detection point is updated for a second time to obtain the position of each detection point after the second update;

[0016] The automatic inspection robot is controlled to continue to move toward the other end of the train, and during the movement, the train is inspected according to the positions of each detection point after the second update.

[0017] In a possible implementation, the second updating of the position of each detection point according to the actual point cloud data set and the standard point cloud data set of the preset part of the train to obtain the second updated position of each detection point includes:

[0018] Establishing an objective function according to the sum of squares of Euclidean distances between corresponding point cloud data in the actual point cloud data set and the standard point cloud data set;

[0019] The objective function is solved with the goal of minimizing the sum of squares of the Euclidean distances to obtain a translation matrix between the actual point cloud data set and the standard point cloud data set;

[0020] According to the translation matrix, the position of each detection point is updated twice to obtain the position of each detection point after the second update.

[0021] In a possible implementation, establishing an objective function according to the sum of squares of Euclidean distances between corresponding point cloud data in the actual point cloud data set and the standard point cloud data set includes:

[0022] according to Establish the objective function;

[0023] Wherein, f represents the objective function, n represents the number of point cloud data in the point cloud data set, and q i represents the i-th actual point cloud data in the actual point cloud data set, R represents the rotation matrix, P i represents the i-th standard point cloud data in the standard point cloud data group, and t represents the translation matrix.

[0024] In a possible implementation, updating the position of each detection point according to the current position of the automatic inspection robot includes:

[0025] Determine the deviation distance between the current position and the preset stop position in different directions;

[0026] The deviation distances in different directions are compensated to the positions of each detection point to obtain the updated positions of each detection point.

[0027] In a possible implementation, a laser ranging positioning unit is provided on the automatic inspection robot, the measuring surface of the laser ranging positioning unit is vertically upward, and is used to emit a laser ranging signal, and correspondingly receive a laser scanning signal formed by the reflection of the laser ranging signal; the laser scanning signal contains laser ranging data;

[0028] The method of determining that the automatic inspection robot has reached one end of the train according to the laser scanning signal includes:

[0029] When the laser ranging data is less than a preset threshold, it is determined that the automatic inspection robot has reached one end of the train.

[0030] In a possible implementation, positioning reflective columns are provided on both sides of the trench along the train stopping direction, and the automatic inspection robot is provided with a laser navigation positioning unit for transmitting a laser positioning signal in real time and correspondingly receiving a laser navigation signal formed by the laser positioning signal reflected by the positioning reflective columns; the trench map includes the position of the positioning reflective columns;

[0031] According to the preset stop position, controlling the automatic inspection robot in the trench to move toward the train includes:

[0032] Acquire the laser navigation signal of the automatic inspection robot in real time, and determine the relative distance and angle between the automatic inspection robot and each positioning reflective column according to the laser navigation signal;

[0033] Determine the real-time position of the automatic inspection robot according to the relative distance and angle, and the position of the positioning reflective column;

[0034] According to the real-time position of the automatic inspection robot and the preset stop position, the automatic inspection robot in the ditch is controlled to move toward the train.

[0035] In a second aspect, an embodiment of the present invention provides an automatic train inspection system, comprising: an automatic inspection robot and a central controller; the automatic inspection robot is provided with a laser ranging positioning unit and an image acquisition unit;

[0036] The automatic inspection robot is used to receive instructions from the central controller and move according to the instructions;

[0037] The laser ranging positioning unit is used to transmit a laser ranging signal and correspondingly receive a laser scanning signal formed by the reflection of the laser ranging signal;

[0038] The image acquisition unit is used to acquire images of various detection points under the train to realize the inspection of the train;

[0039] The central controller is used to execute the train automatic inspection method according to any one of claims 1 to 7. In a third aspect, an embodiment of the present invention provides a train automatic inspection device, the device is applied to a train automatic inspection system, the train automatic inspection system comprises: an automatic inspection robot, the automatic inspection robot moves in a trench under the train;

[0040] The device comprises:

[0041] An acquisition module, used for acquiring a preset trench map, wherein the trench map includes a preset stop position of the train and positions of various detection points under the train;

[0042] Update modules for:

[0043] According to the preset stop position, controlling the automatic inspection robot in the ditch to move toward the train, and acquiring the laser scanning signal of the automatic inspection robot in real time;

[0044] If the laser scanning signal shows that the automatic inspection robot has reached one end of the train, the position of each detection point is updated according to the current position of the automatic inspection robot;

[0045] The inspection module is used to control the automatic inspection robot to move to the other end of the train, and during the movement, inspect the train according to the updated positions of the various detection points.

[0046] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.

[0047] The embodiments of the present invention provide a method, device, system and storage medium for automatic train inspection, which can compensate and update the position of each detection point according to the current position of the automatic inspection robot when the automatic inspection robot reaches one end of the train, without resetting the positioning program, and can also maintain a high inspection accuracy. In addition, the present application can complete the update of each detection point during the process of controlling the automatic inspection robot to move from one end of the train to the other end, without the need for separate positioning and debugging, which can effectively simplify the inspection method and improve the inspection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0049] Figure 1 This is a front view of a train inspection performed using an automatic inspection robot provided by an embodiment of the present invention;

[0050] Figure 2 is a top view of a train inspection performed using an automatic inspection robot provided by an embodiment of the present invention;

[0051] Figure 3 This is a flow chart of an automatic train inspection method according to an embodiment of the present invention;

[0052] Figure 4 is a flow chart of an implementation of an automatic train inspection method provided by another embodiment of the present invention;

[0053] Figure 5 It is a structural schematic diagram of an automatic train inspection system provided by an embodiment of the present invention;

[0054] Figure 6 It is a structural schematic diagram of an automatic train inspection device provided by an embodiment of the present invention;

[0055] Figure 7 is a schematic diagram of a central controller provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0057] In the related art, when an automatic inspection robot is used to re-inspect a train, the manufacturing error of the train and the deviation of the train's stop position are taken into consideration. Each time the automatic inspection robot is used to re-inspect the train, it is necessary to reset the internal positioning program of the automatic inspection robot according to the manufacturing error of the train and the deviation of the train's stop position, and inspect the train again after debugging. This makes the process of each train inspection more cumbersome, which leads to low train inspection efficiency.

[0058] In order to simplify the train inspection method and improve the efficiency of train inspection, in the implementation of the present application, when the automatic inspection robot reaches one end of the train, the current position of the automatic inspection robot can be used to characterize the actual stop position of the train. By updating the position of each detection point according to the actual stop position of the train, the position of each detection point under the actual stop position of the train can be accurately determined without resetting the positioning program inside the automatic inspection robot. In addition, the present application can complete the update of each detection point during the mobile inspection process of controlling the automatic inspection robot from one end of the train to the other end, without the need for separate positioning debugging, which can effectively simplify the inspection method and improve the inspection efficiency.

[0059] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0060] See first Figure 1 and Figure 2 When inspecting the key components at the bottom of the train, the train can be parked above the ditch, and the automatic inspection robot moves inside the ditch. During the movement, image acquisition is performed at the location of each detection point. By using image recognition, it is detected whether the key components at the bottom of the train are in normal condition, thereby completing the inspection of the train.

[0061] Figure 3 The present invention provides a flowchart of an automatic train inspection method according to an embodiment of the present invention. The method can be applied to an automatic train inspection system, which includes an automatic inspection robot. The details are as follows:

[0062] Step 301, obtaining a preset trench map, which includes the preset stop position of the train and the positions of various detection points under the train.

[0063] The position of each detection point can be understood as the position where the image of each key component that needs to be inspected at the bottom of the train is collected. On the basis of determining the stop position of the train, the position of each key component that needs to be inspected at the bottom of the train can be determined accordingly, and then the position of image collection of each key component can be determined.

[0064] In an embodiment of the present invention, the train can be pre-stopped at a preset stop position, and at the preset stop position, an automatic inspection robot can be used to move and debug inside the trench to determine the optimal image acquisition position of each key component, and the optimal image acquisition position of each key component is added to the trench map as the position of each detection point.

[0065] Step 302, according to the preset stop position, control the automatic inspection robot in the ditch to move toward the train, and obtain the laser scanning signal of the automatic inspection robot in real time.

[0066] Here, when inspecting a train, the automatic inspection robot can be controlled to move toward the preset stop position according to the preset stop position of the train indicated in the trench map, and a laser scanning signal can be obtained in real time during the movement. The laser scanning signal can be used to indicate whether the automatic inspection robot has moved to one end of the train.

[0067] In some embodiments, see Figure 2 , positioning reflective columns are provided on both sides of the trench along the train stop direction. The positioning reflective columns are used to help the automatic inspection robot locate its current position. Accordingly, the trench map contains the position of the positioning reflective columns. The automatic inspection robot is provided with a laser navigation positioning unit, which is used to emit laser positioning signals in real time and correspondingly receive laser navigation signals formed by the reflection of the laser positioning signals via the positioning reflective columns.

[0068] When the automatic inspection robot moves toward the train, it can obtain the laser navigation signal of the automatic inspection robot in real time, and determine the relative distance and angle between the automatic inspection robot and each positioning reflective column based on the laser navigation signal. The real-time position of the automatic inspection robot can be determined based on the relative distance and angle, as well as the position of the positioning reflective column. Finally, based on the real-time position of the automatic inspection robot and the preset stop position, the automatic inspection robot in the ditch is controlled to move toward the train.

[0069] Step 303: If the laser scanning signal shows that the automatic inspection robot has reached one end of the train, the position of each detection point is updated according to the current position of the automatic inspection robot.

[0070] In some embodiments, a laser ranging positioning unit is provided on the automatic inspection robot, and the measuring surface of the laser ranging positioning unit is vertically upward, and is used to emit a laser ranging signal and correspondingly receive a laser scanning signal formed by the reflection of the laser ranging signal. The laser scanning signal contains laser ranging data.

[0071] When the laser ranging data is less than a preset threshold, it is determined that the automatic inspection robot has reached one end of the train. The preset threshold here can be determined based on the distance between the bottom of the train and the measuring surface of the laser ranging unit when the automatic inspection robot is under the train. Exemplarily, the preset threshold can be 1.5 meters.

[0072] Here, the laser ranging positioning unit may include a laser ranging sensor. When the automatic inspection robot moves toward the train, the laser ranging sensor emits a laser ranging signal in real time. When there is no train parked above the automatic inspection robot, the laser ranging data is the distance from the measuring surface of the laser ranging sensor to the top of the test site. When the automatic inspection robot moves to the bottom of the train, the laser ranging data decreases sharply and is reduced to the distance from the measuring surface of the laser ranging sensor to the bottom of the train. When the laser ranging data decreases sharply, it proves that the automatic inspection robot has moved to one end of the train.

[0073] When the automatic inspection robot moves to one end of the train, the current position of the automatic inspection robot can be used to represent the actual stop position of the train. According to the deviation between the actual stop position and the preset stop position, the position of each detection point on the trench map can be compensated and updated to obtain the updated position of each detection point.

[0074] In some embodiments, when updating the position of each detection point, the deviation distance between the current position and the preset docking position in different directions can be determined first; then the deviation distance in different directions is compensated to the position of each detection point to obtain the updated position of each detection point.

[0075] Here, see Figure 2 , a coordinate system can be established along the horizontal and vertical directions of the trench. The deviation distances in different directions are the deviation distances in the X-axis direction and the Y-axis direction. Correspondingly, the position of each detection point can also be expressed in coordinate form. The embodiment of the present invention can achieve compensation update for the position of each detection point by respectively superimposing the deviation distances in the X-axis direction and the Y-axis direction to the X-axis coordinates and the Y-axis coordinates of the detection point.

[0076] The embodiment of the present invention compensates and updates the position of each detection point through the vehicle stopping deviation between the actual stopping position and the preset stopping position, which can effectively avoid the problem of reduced inspection accuracy caused by the actual stopping position of the train not matching the preset stopping position, without the need to re-set the positioning program.

[0077] Step 304, control the automatic inspection robot to move to the other end of the train, and during the movement, inspect the train according to the updated positions of each detection point.

[0078] In the embodiment of the present invention, when the automatic inspection robot moves to one end of the bottom of the train, the position of each detection point can be compensated and updated to obtain the updated detection points. On this basis, the automatic inspection robot is controlled to move to the other end of the train, and image acquisition is performed according to the updated positions of each detection point, thereby realizing the train inspection work.

[0079] Compared with the prior art, the embodiment of the present invention compensates and updates the position of each detection point according to the current position of the automatic inspection robot when the automatic inspection robot reaches one end of the train, without resetting the positioning program, while maintaining a high inspection accuracy. In addition, the present application can complete the update of each detection point during the process of controlling the automatic inspection robot to move from one end of the train to the other end, without the need for separate positioning and debugging, which can effectively simplify the inspection method and improve the inspection efficiency.

[0080] The above embodiment mainly considers that when the automatic inspection robot reaches one end of the train, each detection point is compensated and updated according to the current position of the automatic inspection robot. This method can solve the problem that the inspection accuracy is reduced due to the deviation of the train stop position, which leads to the need to re-set the positioning program. On this basis, in order to further solve the problem that the inspection accuracy is reduced due to the deviation of the train manufacturing, which leads to the need to re-set the positioning program, the present invention provides another train automatic inspection system method, see Figure 4 , the method comprising:

[0081] Step 401, obtaining a preset trench map, the trench map including the preset stop position of the train and the positions of various detection points under the train;

[0082] Step 402, according to the preset stop position, control the automatic inspection robot in the ditch to move toward the train, and obtain the laser scanning signal of the automatic inspection robot in real time;

[0083] Step 403: if the laser scanning signal shows that the automatic inspection robot has reached one end of the train, the position of each detection point is updated according to the current position of the automatic inspection robot;

[0084] The implementation methods of the above steps 401 to 403 are the same as Figure 3 The embodiments are the same as those in the embodiments, and will not be repeated here.

[0085] Step 404, control the automatic inspection robot to move to the other end of the train. When the automatic inspection robot reaches the position corresponding to the preset part of the train, control the automatic inspection robot to collect the actual point cloud data group of the preset part of the train; the preset part of the train is located between one end of the train and the first updated detection point.

[0086] It is understandable that after determining the actual stop position of the train, the position corresponding to the preset part of the train can be determined. During the movement of the automatic inspection robot from one end of the train to the other end, when the automatic inspection robot reaches the position corresponding to the preset part of the train, the actual point cloud data group of the preset part of the train can be collected. The actual point cloud data group can be used to compare with the standard point cloud data group of the preset part of the train to determine the deviation between the two. Here, in order to avoid the reciprocating motion of the automatic inspection train, any part between one end of the train and the first updated detection point can be set as the preset part of the train. Exemplarily, the preset part of the train can be the center axis of the bogie.

[0087] Here, based on the determined vehicle stop position, the deviation between the actual point cloud data set and the standard point cloud data set can be used to characterize the train manufacturing deviation.

[0088] Step 405 , performing a second update on the position of each detection point according to the actual point cloud data set and the standard point cloud data set of the preset position of the train, to obtain the position of each detection point after the second update.

[0089] The embodiment of the present invention can update the position of each detection point by secondarily compensating by determining the deviation between the actual point cloud data set and the standard point cloud data set, thereby overcoming the problem of reduced inspection accuracy caused by train manufacturing errors, which in turn requires resetting the positioning program.

[0090] In some embodiments, when updating the position of each detection point with quadratic compensation, an objective function can be first established based on the sum of squared Euclidean distances between corresponding point cloud data in the actual point cloud data set and the standard point cloud data set; then, the objective function is solved with the goal of minimizing the sum of squared Euclidean distances to obtain a translation matrix between the actual point cloud data set and the standard point cloud data set; then, based on the translation matrix, the position of each detection point is updated for a second time to obtain the position of each detection point after the second update.

[0091] Here, the actual point cloud data set can be expressed as Q = {q1, q2, ..., q n}, the standard point cloud data set can be expressed as P = {p1, p2, ..., p n}. In the absence of errors, the actual point cloud data can be transformed into standard point cloud data after rotation and translation. The formula for converting the actual point cloud data set to the standard point cloud data set can be expressed as: i =RP i +t.

[0092] However, due to the existence of noise and false matching, the above formula is not always true. Therefore, the present application can establish an objective function by minimizing the sum of squares of the Euclidean distances between each corresponding point cloud data in the actual point cloud data set and the standard point cloud data set, thereby determining the deviation between the actual point cloud data set and the standard point cloud data set.

[0093] In some embodiments, the Establish the objective function;

[0094] Among them, f represents the objective function, n represents the number of point cloud data in the point cloud data group, and q i represents the i-th actual point cloud data in the actual point cloud data group, R represents the rotation matrix, P i represents the i-th standard point cloud data in the standard point cloud data group, and t represents the translation matrix.

[0095] For train inspection scenarios, there is only a single direction change, and there is no rotation. The present application can determine the deviation between the actual point cloud data and the standard point cloud data set based on the translation matrix. Among them, the translation matrix contains the translation distances in different directions. The present application can translate the position of each detection point according to the translation distances in different directions, thereby determining the position of each detection point after the secondary compensation update.

[0096] Step 406, control the automatic inspection robot to continue to move to the other end of the train, and during the movement, inspect the train according to the positions of each detection point after the second update.

[0097] In the embodiment of the present application, before the automatic inspection robot reaches the first inspection point, each inspection point is updated with secondary compensation according to the preset position of the train. After the secondary supplementary update, the automatic inspection robot continues to be controlled to move to the other end of the train to implement the inspection of the train.

[0098] In the embodiment of the present application, during the movement of the automatic inspection robot from one end of a train to the other end of the train, when the automatic inspection robot reaches one end of the train, a compensation update is performed on each detection point to overcome the problem of reduced inspection accuracy caused by the train stop error, and the automatic inspection robot continues to be controlled to move to the other end of the train. When the automatic inspection robot reaches a preset position of the train, a second compensation update is performed on each detection point to overcome the problem of reduced inspection accuracy caused by the train manufacturing error.

[0099] It should be emphasized that, in the process of the automatic inspection robot moving from one end of the train to the other end of the train, the present application can not only realize the compensation update of each detection point, but also realize the inspection of the vehicle according to the updated detection point. The positioning and inspection can be completed simultaneously during the unidirectional movement, which can avoid the problem of positioning in the first trip and inspection in the second trip, save the inspection cycle, and improve the equipment operation efficiency.

[0100] Based on the above train automatic inspection method, the embodiment of the present invention also provides a train automatic inspection system. Figure 5 The train inspection system includes: an automatic inspection robot and a central controller (not shown in the figure). The automatic inspection robot is provided with a laser ranging positioning unit and an image acquisition unit.

[0101] The automatic inspection robot may be an automatic guided vehicle (AGV), which is used to receive instructions from a central controller and move according to the instructions.

[0102] The laser ranging positioning unit is used to transmit a laser ranging signal and correspondingly receive a laser scanning signal formed by the reflection of the laser ranging signal.

[0103] The laser ranging positioning unit mainly includes a laser ranging sensor, which is installed at the front end of the automatic inspection robot with the measuring surface facing vertically upward. When the automatic inspection robot moves from one end to the other end of the bottom of the vehicle, the distance of the laser ranging sensor to the front end of the bottom of the vehicle will change from infinity to a certain fixed height distance, indicating that the laser ranging sensor measures the position of the vehicle body and feeds back the position coordinates of the automatic inspection robot to the central controller so that the central controller can compensate and update each detection point according to the position coordinates.

[0104] The image acquisition unit is used to acquire images of various detection points under the train to realize the inspection of the train.

[0105] The image acquisition unit mainly includes a collaborative robot and an industrial-grade 3D camera. The collaborative robot can be installed above the automatic guided vehicle, and the industrial-grade 3D camera can be installed at the six-axis end flange of the collaborative robot. The collaborative robot can adjust the shooting posture of the industrial-grade 3D camera, and the industrial-grade 3D camera is used to collect photos of components.

[0106] The central controller is used to execute the automatic train inspection method in the method embodiment.

[0107] In some embodiments, the automatic inspection robot also includes a laser navigation positioning unit and a vehicle feature positioning unit.

[0108] The laser navigation and positioning unit may be a laser scanning navigation system. The laser scanning navigation system may perform laser scanning on the positioning reflective columns inside the trench, thereby drawing a preset trench map, and may also locate the position of the automatic inspection robot by identifying the positioning reflective columns during the movement of the automatic inspection robot;

[0109] The vehicle feature positioning unit mainly includes a binocular vision sensor, which can be installed at the front end of the automatic inspection robot and behind the laser ranging sensor. When a compensation update is completed, the central controller issues a command to move to a preset position of the train, such as the center axis of the bogie, to identify feature components. The three-dimensional point cloud data of the bogie components is collected by the binocular vision sensor and transmitted to the central controller. The central controller matches the standard point cloud data group to obtain the deviation value between the current position of the automatic inspection robot and the standard detection position, and performs a secondary compensation update based on the deviation value.

[0110] Here, the automatic inspection robot, the laser ranging positioning unit, the laser navigation positioning unit, the vehicle feature positioning unit and the image information acquisition unit are all connected to the central controller for communication.

[0111] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0112] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0113] Figure 6 The structure diagram of the automatic train inspection device provided by the embodiment of the present invention is shown. For the convenience of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0114] like Figure 6 As shown, the train automatic inspection device 6 is applied to the train automatic inspection system, and the train automatic inspection system includes: an automatic inspection robot, which moves in the ditch under the train;

[0115] The device includes:

[0116] The acquisition module 61 is used to acquire a preset trench map, which includes the preset stop position of the train and the positions of various detection points under the train;

[0117] The update module 62 is used to:

[0118] According to the preset stop position, the automatic inspection robot in the trench is controlled to move toward the train, and the laser scanning signal of the automatic inspection robot is obtained in real time;

[0119] If the laser scanning signal shows that the automatic inspection robot has reached one end of the train, the position of each detection point is updated according to the current position of the automatic inspection robot;

[0120] The inspection module 63 is used to control the automatic inspection robot to move to the other end of the train, and during the movement, inspect the train according to the updated positions of each detection point.

[0121] Optionally, the inspection module 63 is specifically used for:

[0122] The automatic inspection robot is controlled to move toward the other end of the train. When the automatic inspection robot reaches a position corresponding to a preset part of the train, the automatic inspection robot is controlled to collect an actual point cloud data group of the preset part of the train; the preset part of the train is located between one end of the train and the first detection point after the update;

[0123] According to the actual point cloud data set and the standard point cloud data set of the preset position of the train, the position of each detection point is updated twice to obtain the position of each detection point after the second update;

[0124] The automatic inspection robot is controlled to continue to move to the other end of the train, and during the movement, the train is inspected according to the positions of each detection point after the second update.

[0125] Optionally, the inspection module 63 is specifically used for:

[0126] Establishing an objective function according to the sum of squares of the Euclidean distances between corresponding point cloud data in the actual point cloud data set and the standard point cloud data set;

[0127] With the goal of minimizing the sum of squared Euclidean distances, the objective function is solved to obtain the translation matrix between the actual point cloud data set and the standard point cloud data set;

[0128] According to the translation matrix, the position of each detection point is updated twice to obtain the position of each detection point after the second update.

[0129] Optionally, the inspection module 63 is specifically used for:

[0130] according to Establish the objective function;

[0131] Among them, f represents the objective function, n represents the number of point cloud data in the point cloud data group, and q i represents the i-th actual point cloud data in the actual point cloud data set, R represents the rotation matrix, P i represents the i-th standard point cloud data in the standard point cloud data group, and t represents the translation matrix.

[0132] Optionally, the update module 62 is specifically used for:

[0133] Determine the deviation distance between the current position and the preset docking position in different directions;

[0134] The deviation distances in different directions are compensated to the positions of each detection point to obtain the updated positions of each detection point.

[0135] Optionally, a laser ranging positioning unit is provided on the automatic inspection robot, the measuring surface of the laser ranging positioning unit is vertically facing upward, and is used to emit a laser ranging signal, and correspondingly receive a laser scanning signal formed by the reflection of the laser ranging signal; the laser scanning signal contains laser ranging data;

[0136] When the laser ranging data is less than a preset threshold, it is determined that the automatic inspection robot has reached one end of the train.

[0137] Optionally, positioning reflective columns are provided on both sides of the trench along the train stop direction, and the automatic inspection robot is provided with a laser navigation positioning unit for transmitting a laser positioning signal in real time and correspondingly receiving a laser navigation signal formed by the laser positioning signal reflected by the positioning reflective columns; the trench map includes the position of the positioning reflective columns;

[0138] The update module 62 is specifically used for:

[0139] Acquire the laser navigation signal of the automatic inspection robot in real time, and determine the relative distance and angle between the automatic inspection robot and each positioning reflective column according to the laser navigation signal;

[0140] Determine the real-time position of the automatic inspection robot based on the relative distance and angle, as well as the position of the positioning reflective column;

[0141] According to the real-time position of the automatic inspection robot and the preset stop position, the automatic inspection robot in the ditch is controlled to move towards the train.

[0142] This device embodiment is used to implement the above method embodiment. Its technical principle and implementation effect are the same as those of the above method embodiment, and will not be repeated here.

[0143] Figure 7 Schematic diagram of a central controller provided by an embodiment of the present invention. Figure 7 As shown, the central controller 7 of this embodiment includes: a processor 70, a memory 71, and a computer program 72 stored in the memory 71 and executable on the processor 70. When the processor 70 executes the computer program 72, the steps in the above-mentioned embodiments of the automatic train inspection method are implemented, for example Figure 3 Alternatively, when the processor 70 executes the computer program 72, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 6 The functions of modules 61 to 63 are shown.

[0144] Exemplarily, the computer program 72 may be divided into one or more modules / units, which are stored in the memory 71 and executed by the processor 70 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 72 in the central controller 7. For example, the computer program 72 may be divided into Figure 6 Modules 61 to 63 are shown.

[0145] The central controller 7 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The central controller 7 may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will appreciate that Figure 7 It is only an example of the central controller 7 and does not constitute a limitation of the central controller 7. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the central controller may also include input and output devices, network access devices, buses, etc.

[0146] The processor 70 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0147] The memory 71 may be an internal storage unit of the central controller 7, such as a hard disk or memory of the central controller 7. The memory 71 may also be an external storage device of the central controller 7, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the central controller 7. Further, the memory 71 may include both an internal storage unit of the central controller 7 and an external storage device. The memory 71 is used to store the computer program and other programs and data required by the central controller. The memory 71 may also be used to temporarily store data that has been output or is to be output.

[0148] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0149] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0150] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0151] In the embodiments provided by the present invention, it should be understood that the disclosed device / central controller and method can be implemented in other ways. For example, the device / central controller embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0152] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0153] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0154] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various train automatic inspection method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A train automatic inspection method, characterized in that: The method is applied to an automatic train inspection system, which includes: an automatic inspection robot, which moves in a trench under the train; The method comprises: Obtaining a preset trench map, wherein the trench map includes a preset stop position of the train and positions of various detection points under the train; According to the preset stop position, controlling the automatic inspection robot in the ditch to move toward the train, and acquiring the laser scanning signal of the automatic inspection robot in real time; If the laser scanning signal shows that the automatic inspection robot has reached one end of the train, the position of each detection point is updated according to the current position of the automatic inspection robot; The automatic inspection robot is controlled to move toward the other end of the train, and during the movement, the train is inspected according to the updated positions of the detection points.

2. The automatic train inspection method according to claim 1, characterized in that: The controlling the automatic inspection robot to move toward the other end of the train and inspecting the train according to the updated positions of the detection points during the movement includes: Control the automatic inspection robot to move toward the other end of the train, and when the automatic inspection robot reaches a position corresponding to a preset part of the train, control the automatic inspection robot to collect an actual point cloud data group of the preset part of the train; the preset part of the train is located between one end of the train and the first updated detection point; According to the actual point cloud data set and the standard point cloud data set of the preset part of the train, the position of each detection point is updated for a second time to obtain the position of each detection point after the second update; The automatic inspection robot is controlled to continue to move toward the other end of the train, and during the movement, the train is inspected according to the positions of each detection point after the second update.

3. The automatic train inspection method according to claim 2, characterized in that: The second updating of the position of each detection point according to the actual point cloud data set and the standard point cloud data set of the preset part of the train to obtain the position of each detection point after the second update includes: Establishing an objective function according to the sum of squares of Euclidean distances between corresponding point cloud data in the actual point cloud data set and the standard point cloud data set; The objective function is solved with the goal of minimizing the sum of squares of the Euclidean distances to obtain a translation matrix between the actual point cloud data set and the standard point cloud data set; According to the translation matrix, the position of each detection point is updated twice to obtain the position of each detection point after the second update.

4. The automatic train inspection method according to claim 3, characterized in that: The objective function is established according to the sum of squares of the Euclidean distances between corresponding point cloud data in the actual point cloud data set and the standard point cloud data set, including: according to Establish the objective function; Wherein, f represents the objective function, n represents the number of point cloud data in the point cloud data set, and q i represents the i-th actual point cloud data in the actual point cloud data group, R represents the rotation matrix, P i represents the i-th standard point cloud data in the standard point cloud data group, and t represents the translation matrix.

5. The automatic train inspection method according to any one of claims 1 to 4, characterized in that: The updating of the position of each detection point according to the current position of the automatic inspection robot includes: Determine the deviation distance between the current position and the preset stop position in different directions; The deviation distances in different directions are compensated to the positions of each detection point to obtain the updated positions of each detection point.

6. The automatic train inspection method according to any one of claims 1 to 4, characterized in that: The automatic inspection robot is provided with a laser ranging positioning unit, the measuring surface of which is vertically upward, and is used to emit a laser ranging signal and correspondingly receive a laser scanning signal formed by the reflection of the laser ranging signal; the laser scanning signal contains laser ranging data; The method of determining that the automatic inspection robot has reached one end of the train according to the laser scanning signal includes: When the laser ranging data is less than a preset threshold, it is determined that the automatic inspection robot has reached one end of the train.

7. The automatic train inspection method according to any one of claims 1 to 4, characterized in that: Positioning reflective columns are arranged on both sides of the trench along the train stopping direction, and the automatic inspection robot is provided with a laser navigation positioning unit for transmitting a laser positioning signal in real time and correspondingly receiving a laser navigation signal formed by the laser positioning signal reflected by the positioning reflective columns; the trench map includes the position of the positioning reflective columns; According to the preset stop position, controlling the automatic inspection robot in the trench to move toward the train includes: Acquire the laser navigation signal of the automatic inspection robot in real time, and determine the relative distance and angle between the automatic inspection robot and each positioning reflective column according to the laser navigation signal; Determine the real-time position of the automatic inspection robot according to the relative distance and angle, and the position of the positioning reflective column; According to the real-time position of the automatic inspection robot and the preset stop position, the automatic inspection robot in the ditch is controlled to move toward the train.

8. An automatic train inspection system, characterized in that: include: An automatic inspection robot and a central controller; the automatic inspection robot is provided with a laser ranging positioning unit and an image acquisition unit; The automatic inspection robot is used to receive instructions from the central controller and move according to the instructions; The laser ranging positioning unit is used to transmit a laser ranging signal and correspondingly receive a laser scanning signal formed by the reflection of the laser ranging signal; The image acquisition unit is used to acquire images of various detection points under the train to realize the inspection of the train; The central controller is used to execute the automatic train inspection method described in any one of claims 1-7.

9. An automatic train inspection device, characterized in that: The device is applied to an automatic train inspection system, which includes: an automatic inspection robot, which moves in a trench under the train; The device comprises: An acquisition module, used to acquire a preset trench map, wherein the trench map includes a preset stop position of the train and positions of various detection points under the train; Update modules for: According to the preset stop position, controlling the automatic inspection robot in the ditch to move toward the train, and acquiring the laser scanning signal of the automatic inspection robot in real time; If the laser scanning signal shows that the automatic inspection robot has reached one end of the train, the position of each detection point is updated according to the current position of the automatic inspection robot; The inspection module is used to control the automatic inspection robot to move to the other end of the train, and during the movement, inspect the train according to the updated positions of the various detection points.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the automatic train inspection method as described in any one of claims 1 to 7 are implemented.

Images