Automatic derusting system and method for truck body of open wagon

Abstract

The invention provides an automatic derusting system and method for a truck body of a gondola truck, and relates to the technical field of vehicle overhauling, the automatic derusting system comprises a truss structure, the truss structure comprises a three-axis moving assembly, and the three-axis moving assembly is arranged above the truck body in a crossing mode; the industrial robot is arranged on the three-axis moving assembly; the pneumatic chipping hammer is arranged on a mechanical arm of the industrial robot and is used for removing rust on the surface of the vehicle body; the camera system and the mechanical arm keep a fixed pose relationship; and the control system is connected with the industrial robot and the camera system and is used for acquiring and processing the information acquired by the camera system so as to generate a control instruction for the industrial robot. Compared with an existing manual rust removal mode, automatic and unmanned rust removal can be achieved, and the labor intensity of operators is greatly reduced.

Description

Technical Field

[0001] The invention relates to the technical field of vehicle maintenance, and in particular to an automatic rust removal system and method for a body of an open truck. Background Art

[0002] An open wagon is a type of railway freight car. It is characterized by being uncovered and having side panels on all four sides. As it runs outdoors for a long time and is exposed to various adverse weather conditions, the corrosion of the wagon surface will be accelerated. In addition, during transportation, the interior of the wagon is exposed to various acidic and alkaline chemicals for a long time, which also cause corrosion to the wagon body. Rust removal of wagon bodies is an important part of the vehicle repair industry, which directly affects the quality and efficiency of each process of wagon body inspection and maintenance.

[0003] At present, the main method for rust removal of railway freight car bodies is manual rust removal. The operator holds an air shovel with a copper shovel head and impacts the car body to remove rust, so that the oxide on the surface of the steel car body falls off. Manual rust removal is simple to operate, but the efficiency is low, the car body area is large, and rust removal takes a long time. At the same time, the rust removal working environment is harsh, especially the air shovel will generate high-decibel noise during the impact process, which has a great impact on the health of the operator. Summary of the invention

[0004] The purpose of the present invention is to provide an automatic rust removal system and method for the body of an open truck to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0005] The present application provides an automatic rust removal system for an open truck body, comprising:

[0006] A truss structure, the truss structure comprising a three-axis moving assembly, the three-axis moving assembly being arranged across the vehicle body;

[0007] An industrial robot, the industrial robot being arranged on the three-axis moving assembly;

[0008] An air shovel, which is arranged on the mechanical arm of the industrial robot and is used to remove rust from the surface of the vehicle body;

[0009] A camera system, wherein the camera system maintains a fixed position relationship with the robotic arm;

[0010] A control system is connected to the industrial robot and the camera system, and is used to obtain and process information collected by the camera system to generate control instructions for the industrial robot.

[0011] Optionally, the air shovel includes a main body, a shovel head and a buffer mechanism, the shovel head is installed at one end of the main body, the buffer mechanism is installed at the other end of the main body, and the buffer mechanism is connected to the mechanical arm of the industrial robot.

[0012] Optionally, the camera system includes two infrared monocular imaging cameras, one color monocular camera and an infrared structured light source, wherein the infrared structured light source is used to form patterns on the surface of the vehicle body; the infrared monocular imaging camera is used to obtain point cloud data of the surface of the vehicle body; and the color monocular camera is used to collect image information of the surface of the vehicle body.

[0013] Optionally, the buffer mechanism includes any one of a steel spring, an air spring and a hydraulic spring.

[0014] Based on the same inventive concept, the present application also provides a method for automatically removing rust from the body of an open wagon truck, the method being implemented by the above-mentioned automatic rust removal system for the body of an open wagon truck, comprising:

[0015] Using a camera system to collect point cloud data and images of the vehicle surface;

[0016] Based on the image of the vehicle body surface, using a pre-trained corrosion recognition model to identify the rust area in the image;

[0017] Projecting the corroded area onto the point cloud data of the vehicle body surface to obtain the point cloud data of the corroded area;

[0018] Based on the point cloud data of the rusted area, an initial rust removal path is generated by modifying the preset rust removal path;

[0019] By comparing the body surface point cloud data with the coordinates of the initial rust removal path, it is determined whether the initial rust removal path has a collision risk. If so, the rust removal path is regenerated to obtain a target rust removal path.

[0020] Optionally, the generating an initial rust removal path by modifying a preset rust removal path based on the point cloud data of the rusted area includes:

[0021] Performing a sparse sampling process on the point cloud data of the rusted area to obtain sampling points;

[0022] Acquire a preset rust removal path, wherein the preset rust removal path includes a plurality of rust removal points arranged in rows and columns;

[0023] According to the coverage area of ​​the sampling points, the shape and / or area of ​​the projection of the preset rust removal path is adjusted by increasing or decreasing the number of rust removal points in rows and columns to obtain an initial rust removal path that matches the coverage area of ​​the sampling points; and the starting point of the initial rust removal path is moved to align with the first sampling point in the upper left corner.

[0024] Optionally, the method further includes:

[0025] Comparing the size of the rusted area with the area covered by the preset rust removal path, if the length or width of the rusted area is twice or more the length or width of the area covered by the preset rust removal path, dividing the rusted area into at least two partitions;

[0026] The preset rust removal paths are modified based on the shape and area of ​​each partition.

[0027] Optionally, the method further includes:

[0028] A rust removal plane is obtained according to the sampling point and its neighborhood fitting, and a normal vector of each sampling point is obtained according to the rust removal plane;

[0029] The target angle of the manipulator is calculated according to the normal vector of each sampling point, and the preset manipulator arm posture data is updated based on the target angle of the manipulator.

[0030] Optionally, comparing the body surface point cloud data with the coordinates of the initial rust removal path to determine whether the initial rust removal path has a collision risk includes:

[0031] Generate a path coordinate set based on the rust removal points of the initial rust removal path;

[0032] Based on the vehicle body surface point cloud data and the path coordinate set, calculating the distance from each coordinate in the path coordinate set to the vehicle body surface, and determining whether the distance is less than a preset threshold;

[0033] If the distance is less than a preset threshold, there is a risk of collision.

[0034] Optionally, the method further includes:

[0035] Based on the image of the vehicle body surface, the rust level of the rusted area is identified using a pre-trained rust recognition model, and the number of rust removal times is generated based on the rust level. , including:

[0036] The beneficial effects of the present invention are:

[0037] The present invention processes the data obtained by scanning the camera system, and then controls the actions of the industrial robot and the three-axis moving component according to the generated rust removal path, so that the air shovel operates on the rusted area. Compared with the existing manual rust removal method, the present invention can realize automatic and unmanned rust removal, greatly reduces the labor intensity of the operator, improves the working environment, has high rust removal efficiency, stable rust removal quality and little harm to the operator.

[0038] Other features and advantages of the present invention will be set forth in the following description, and in part will become apparent from the description, or may be understood by practicing embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 This is a schematic diagram of the structure of the automatic rust removal system for the body of an open truck in an embodiment of the present application;

[0041] Figure 2 This is a schematic diagram of the air shovel structure in an embodiment of the present application.

[0042] Markings in the figure:

[0043] 100-truss structure; 200-industrial robot; 300-air shovel; 301-main body; 302-shovel head; 303-buffer mechanism; 400-camera system. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0045] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0046] Example 1

[0047] An automatic rust removal system for an open truck body, comprising:

[0048] The truss structure 100 includes a three-axis moving assembly, which is arranged across the vehicle body; the three-axis moving assembly is used to realize free movement in three directions of X, Y, and Z, and can be assembled by linear modules;

[0049] An industrial robot 200, wherein the industrial robot 200 is disposed on the three-axis moving assembly;

[0050] An air shovel 300, which is disposed on the mechanical arm of the industrial robot 200 and is used to remove rust from the surface of the vehicle body;

[0051] A camera system 400, wherein the camera system 400 maintains a fixed position relationship with the robotic arm; preferably, the camera system 400 is installed on the robotic arm;

[0052] A control system, which is connected to the industrial robot 200 and the camera system 400 via cables, and is used to obtain and process the information collected by the camera system 400 to generate control instructions for the industrial robot 200; the control system is also connected to the three-axis moving assembly to control the overall movement of the industrial robot 200.

[0053] When performing rust removal work, the truck is towed to a fixed position under the truss structure 100, and the industrial robot 200 starts to move from the initial position. The camera system 400 is first used to scan the entire working area of ​​the vehicle body, and the control system processes the scanned data. The industrial robot 200 and the three-axis moving component are then controlled according to the generated rust removal path, so that the air shovel 300 operates on the rusted area.

[0054] As an optional embodiment, the air shovel 300 includes a main body 301, a shovel head 302 and a buffer mechanism 303, wherein the shovel head 302 is installed at one end of the main body 301, and the buffer mechanism 303 is installed at the other end of the main body 301, and the buffer mechanism 303 is connected to the mechanical arm of the industrial robot 200. The main body 301 of the air shovel 300 impacts forward, driving the copper shovel head 302 to impact the rusted part of the vehicle body. The vibration generated by the impact is buffered by the buffer mechanism 303 to prevent damage to the industrial robot 200.

[0055] As an optional implementation, the buffer mechanism 303 includes any one of a steel spring, an air spring and a hydraulic spring.

[0056] As an optional implementation, the camera system 400 includes two infrared monocular imaging cameras, one color monocular camera and an infrared structured light source, wherein the infrared structured light source is used to form spots, i.e., feature points, on the surface of a vehicle body with fewer features, so as to assist the two infrared monocular cameras in feature matching and form 3D point cloud data. The infrared monocular imaging camera is used to obtain point cloud data on the surface of the vehicle body; the color monocular camera takes pictures at a fixed frame rate and is used to collect image information on the surface of the vehicle body to identify the rusted area. The collected image information and point cloud data are uploaded to the control system for processing.

[0057] Example 2

[0058] A method for automatically removing rust from the body of an open wagon truck is implemented based on the automatic rust removal system for the body of an open wagon truck described in Example 1, and includes steps S100, S200, S300, S400 and S500.

[0059] S100, using the camera system 400 to collect vehicle body surface point cloud data and vehicle body surface images;

[0060] The infrared structured light source provides spots for the infrared monocular cameras, helping the two infrared monocular cameras to form point cloud data on the surface of the C70 truck body with fewer features;

[0061] Specifically, two infrared monocular cameras form a binocular system. Since there are two cameras, two images can be formed. Based on two or more images, the depth information of each pixel in the image can be inferred, thereby obtaining the three-dimensional spatial coordinates of each point in the image, which are calculated in the camera coordinate system.

[0062] After obtaining the spatial coordinates of each point on the surface of the object, a collection of points is obtained, namely the "point cloud". The content of the point cloud includes: three-dimensional coordinates (XYZ), laser reflection intensity (Intensity) and color information (RGB).

[0063] Before normal rust removal tasks are performed, the following preprocessing operations are required: calibrate the coordinate system between the industrial robot 200 and the camera system 400, calibrate the coordinate system between the industrial robot 200 and the air shovel 300, determine the conversion matrix, and convert all coordinate systems to a world coordinate system that coincides with the x-axis, y-axis, and z-axis of the truss structure 100. Through teaching operations, the preset rust removal path for the camera system 400 to collect vehicle surface data is planned, and the servo position information of the industrial robot 200 and the three-axis moving component is recorded at the same time to form a script document for subsequent calls.

[0064] S200, based on the image of the vehicle body surface, identifying the rusted area in the image using a pre-trained rust recognition model;

[0065] The input of the pre-trained rust recognition model is a number of historical vehicle surface images, and the output is the rust area and the corresponding rust grade determined manually based on experience. The rust grade represents the number of times rust removal is required, that is, multiple rust removals may be required at the same location to ensure the rust removal effect.

[0066] S300, projecting the rusted area onto the point cloud data of the vehicle body surface to obtain the point cloud data of the rusted area;

[0067] In the preprocessing operation, the coordinate system of the camera system 400 is calibrated, that is, the conversion relationship between the three-dimensional point cloud data and the two-dimensional coordinates of the pixels in the image can be obtained, so that the two-dimensional coordinates of the rusted area in the image can be converted into the point cloud data.

[0068] S400, based on the point cloud data of the rusted area, generating an initial rust removal path by modifying the preset rust removal path; comprising:

[0069] S410. Perform thinning sampling on the point cloud data of the rusted area to obtain sampling points. Specifically, the present application adopts distance-based thinning sampling, that is, by calculating the distance between point clouds and deciding whether to retain the point cloud according to a set distance threshold. Specifically, a minimum distance threshold can be set. When the distance between two points is less than the threshold, only one of the points is retained; when the distance between two points is greater than the threshold, both points are retained. Thinning sampling can reduce the point cloud density and data volume, facilitating subsequent calculations.

[0070] S420, obtaining a preset rust removal path, wherein the preset rust removal path includes a plurality of rust removal points arranged in rows and columns; the preset rust removal path is a path established through a teaching operation, which traverses all rust removal points starting from the upper left according to a "bow"-shaped route and according to a preset step length.

[0071] S430, comparing the size of the rusted area and the area covered by the preset rust removal path, if the length or width of the rusted area is twice or more the length or width of the area covered by the preset rust removal path, dividing the rusted area into at least two partitions;

[0072] That is, when the length or width of the rusted area is too large, it is preferably divided into multiple partitions for rust removal, and each partition performs the same operation: based on the shape and area of ​​the rusted area or each partition thereof, the preset rust removal path is modified, and the modification operation is shown in step S430.

[0073] S430. According to the coverage area of ​​the sampling points, the shape and / or area of ​​the projection of the preset rust removal path is adjusted by increasing or decreasing the number of rust removal points in rows and columns; the projection of the preset rust removal path is initially a rectangle. If the path coverage needs to be expanded, taking horizontal stretching as an example, first align the center of the preset rust removal path with the center of the rusted area, divide the rusted area according to the longitudinal spacing of the rust removal points of the preset rust removal path, and form multiple rows of areas. Each row of rust removal points has a corresponding row of overlapping areas. Calculate the distance of the left and right ends of the overlapping area that exceeds the rust removal points, and then divide the excess distance by the step size of the rust removal points to obtain the number of rust removal points that need to be added, and add the newly added rust removal points to the path. The longitudinal stretching method is similar.

[0074] Through the above operations, an initial rust removal path matching the coverage area of ​​the sampling points is obtained; and the starting point of the initial rust removal path is moved to align with the first sampling point in the upper left corner.

[0075] In addition, the rusted area may be slightly uneven. In order to ensure that the air shovel 300 reaches the best angle with the rusted surface of the vehicle body during operation, this embodiment further includes step S440:

[0076] A rust removal plane is obtained according to the sampling point and its neighborhood fitting, and a normal vector of each sampling point is obtained according to the rust removal plane;

[0077] The target angle of the manipulator is calculated according to the normal vector of each sampling point, and the preset manipulator arm posture data is updated based on the manipulator target angle to ensure that the manipulator and the normal vector of the sampling point are at a fixed angle.

[0078] S500, by comparing the body surface point cloud data with the coordinates of the initial rust removal path, determining whether the initial rust removal path has a collision risk, and if so, regenerating the rust removal path to obtain a target rust removal path, including:

[0079] Generate a path coordinate set based on the rust removal points of the initial rust removal path;

[0080] Based on the vehicle body surface point cloud data and the path coordinate set, calculating the distance from each coordinate in the path coordinate set to the vehicle body surface, and determining whether the distance is less than a preset threshold;

[0081] If the distance is less than the preset threshold, there is a risk of collision. In addition, in addition to considering the collision between the rust removal path itself and the vehicle body, it is also necessary to consider whether the air shovel 300 and the mechanical arm collide with the vehicle body during the rust removal process. Specifically, during the pre-processing operation, a three-dimensional model of the mechanical arm and the air shovel 300 is established, and the position of the model in the world coordinate system is calibrated, and the coordinates of any point on the model can be obtained. Therefore, after obtaining the initial rust removal path, the minimum distance between the three-dimensional model of the mechanical arm and the air shovel 300 and the vehicle body point cloud when moving to each rust removal point position can be calculated to determine whether a collision occurs. If so, it also indicates that there is a risk of collision.

[0082] If there is a risk of collision, the path coordinate set is adjusted, for example, the Y value of each coordinate is reduced to make the coordinate farther away from the vehicle body. After the adjustment, it is determined whether there is a risk of collision. If there is no risk, the target rust removal path is obtained.

[0083] After moving along the target rust removal path to perform rust removal, the operation is completed, and the three-axis moving assembly and the industrial robot 200 return to the original preset position and continue to wait for new tasks.

[0084] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An automatic rust removal system for an open truck body, characterized in that: include: A truss structure (100), the truss structure (100) comprising a three-axis moving assembly, the three-axis moving assembly being arranged across the top of the vehicle body; An industrial robot (200), the industrial robot (200) being arranged on the three-axis moving assembly; An air shovel (300), the air shovel (300) being arranged on the mechanical arm of the industrial robot (200) and being used for removing rust from the surface of the vehicle body; A camera system (400), wherein the camera system (400) maintains a fixed position relationship with the robotic arm; A control system is connected to the industrial robot (200) and the camera system (400) and is used to obtain and process information collected by the camera system (400) to generate control instructions for the industrial robot (200).

2. The automatic rust removal system for an open truck body according to claim 1, characterized in that: The air shovel (300) comprises a main body (301), a shovel head (302) and a buffer mechanism (303), wherein the shovel head (302) is installed at one end of the main body (301), and the buffer mechanism (303) is installed at the other end of the main body (301), and the buffer mechanism (303) is connected to the mechanical arm of the industrial robot (200).

3. The automatic rust removal system for the body of an open truck according to claim 1, characterized in that: The camera system (400) comprises two infrared monocular imaging cameras, one color monocular camera and an infrared structured light source, wherein the infrared structured light source is used to form a pattern on the surface of a vehicle body; the infrared monocular imaging camera is used to obtain point cloud data on the surface of the vehicle body; and the color monocular camera is used to collect image information on the surface of the vehicle body.

4. The automatic rust removal system for the body of an open truck according to claim 2, characterized in that: The buffer mechanism (303) comprises any one of a steel spring, an air spring and a hydraulic spring.

5. A method for automatically removing rust from the body of an open truck, characterized in that: The method is implemented based on the automatic rust removal system for the body of an open wagon truck according to any one of claims 1 to 4, comprising: Using a camera system (400) to collect vehicle body surface point cloud data and vehicle body surface images; Based on the image of the vehicle body surface, using a pre-trained corrosion recognition model to identify the rust area in the image; Projecting the corroded area onto the point cloud data of the vehicle body surface to obtain the point cloud data of the corroded area; Based on the point cloud data of the rusted area, an initial rust removal path is generated by modifying the preset rust removal path; By comparing the body surface point cloud data with the coordinates of the initial rust removal path, it is determined whether the initial rust removal path has a collision risk. If so, the rust removal path is regenerated to obtain a target rust removal path.

6. The automatic rust removal method for the body of an open truck according to claim 5, characterized in that: The initial rust removal path is generated by modifying the preset rust removal path based on the point cloud data of the rusted area, including: Performing a sparse sampling process on the point cloud data of the rusted area to obtain sampling points; Acquire a preset rust removal path, wherein the preset rust removal path includes a plurality of rust removal points arranged in rows and columns; According to the coverage area of ​​the sampling points, the shape and / or area of ​​the projection of the preset rust removal path is adjusted by increasing or decreasing the number of rust removal points in rows and columns to obtain an initial rust removal path that matches the coverage area of ​​the sampling points; and the starting point of the initial rust removal path is moved to align with the first sampling point in the upper left corner.

7. The automatic rust removal method for the body of an open truck according to claim 6, characterized in that: The method further comprises: Comparing the size of the rusted area with the area covered by the preset rust removal path, if the length or width of the rusted area is twice or more the length or width of the area covered by the preset rust removal path, dividing the rusted area into at least two partitions; The preset rust removal paths are modified based on the shape and area of ​​each partition.

8. The automatic rust removal method for the body of an open truck according to claim 6, characterized in that: The method further comprises: A rust removal plane is obtained according to the sampling point and its neighborhood fitting, and a normal vector of each sampling point is obtained according to the rust removal plane; The target angle of the manipulator is calculated according to the normal vector of each sampling point, and the preset manipulator arm posture data is updated based on the target angle of the manipulator.

9. The automatic rust removal method for the body of an open truck according to claim 5, characterized in that: The step of comparing the body surface point cloud data with the coordinates of the initial rust removal path to determine whether the initial rust removal path has a collision risk includes: Generate a path coordinate set based on the rust removal points of the initial rust removal path; Based on the vehicle body surface point cloud data and the path coordinate set, calculating the distance from each coordinate in the path coordinate set to the vehicle body surface, and determining whether the distance is less than a preset threshold; If the distance is less than a preset threshold, there is a risk of collision.

10. The automatic rust removal method for the body of an open truck according to claim 5, characterized in that: The method further comprises: Based on the image of the vehicle body surface, a pre-trained rust recognition model is used to identify the rust grade of the rusted area, and the number of rust removal times is generated based on the rust grade.

Images