A method for optimizing the painting path of an automated painting robot

Abstract

The invention discloses a method for optimizing the painting path of an automated painting robot, which relates to the field of automation technology, and comprises the following steps: obtaining a three-dimensional geometric model of a hull through a laser scanning device, and performing curvature analysis to generate partition data of curvature information of each hull area; performing preliminary path planning according to the partition data to obtain a preliminary painting path; executing a painting task based on the preliminary painting path, and detecting coating thickness data of the painting area in real time; correcting the preliminary painting path in real time according to the detected coating thickness data to generate a new painting path; detecting the paint coverage rate of the painting area in real time, judging the coverage uniformity of the painting area, and marking the unevenly covered painting area; adjusting the painting path again through the coverage rate detection data to generate a corrected final painting path, and using the final painting path to execute the painting task on the next hull; adjusting the painting path in real time to make the painting process more flexible and efficient, and improve the stability of the painting quality.

Description

Technical Field

[0001] The invention relates to the field of automation technology, and in particular to a method for optimizing a painting path of an automated painting robot. Background Art

[0002] With the continuous development of hull manufacturing and maintenance technology, automated painting technology has gradually been widely used, with the aim of improving painting efficiency, reducing manual operations and improving coating quality. The current hull painting system mainly relies on pre-planned paths and parameters for operation. However, due to the complex hull structure and large changes in surface curvature, conventional path planning methods are difficult to adapt to complex geometric shapes, resulting in uneven coating thickness, insufficient coverage and other problems. This situation not only reduces the quality of painting, but also increases the waste of materials and time.

[0003] In the prior art, most painting robots fail to fully consider the curvature changes of the hull surface when planning the path, and lack a real-time feedback mechanism, making it impossible to detect the coating thickness and coverage during the painting process. This method is prone to uneven painting, overspray or missed spraying when facing complex surfaces. In addition, the prior art has limited ability to optimize the painting path, and cannot dynamically adjust the path based on real-time detection data, thus affecting the overall painting effect. Therefore, there is an urgent need for a method that can detect and dynamically adjust the painting path in real time to ensure the quality and efficiency of painting. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for optimizing the painting path of an automated painting robot, which solves the problem of being unable to monitor the paint thickness and coverage in real time and dynamically adjust the paint path.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for optimizing a painting path of an automated painting robot, comprising:

[0008] The three-dimensional geometric model of the hull is obtained through laser scanning equipment, and curvature analysis is performed to generate partition data of curvature information of each hull area;

[0009] According to the partition data, preliminary path planning is carried out to obtain the preliminary painting path;

[0010] Based on the preliminary painting path, execute the painting task and detect the coating thickness data of the painting area in real time;

[0011] According to the detected coating thickness data, the preliminary painting path is corrected in real time to generate a new painting path;

[0012] Real-time detection of the paint coverage rate of the painting area, judgment of the uniformity of the painting area, and marking of unevenly covered painting areas;

[0013] The paint path is adjusted again based on the coverage detection data to generate a corrected final paint path, which is then used to perform the painting task on the next ship hull.

[0014] As a preferred solution of the method for optimizing the painting path of the automatic painting robot of the present invention, the three-dimensional geometric model of the hull is obtained by a laser scanning device, and a curvature analysis is performed to generate partition data of the curvature information of each hull area, including the following steps:

[0015] The laser scanning equipment performs an all-round scan of the hull surface to generate high-density three-dimensional point cloud data;

[0016] Remove noise points and redundant points from high-density 3D point cloud data;

[0017] Apply triangulation algorithm to convert point cloud into polygonal mesh and construct continuous surface;

[0018] Smooth the edges and depressions of the surface to generate a complete 3D geometric model;

[0019] Discretize the 3D geometric model and divide the surface into N triangular patches;

[0020] Calculate the normal vector of each triangular patch, and find the average curvature value of each vertex by changing the normal vectors of adjacent patches;

[0021] The calculated average curvature value of each vertex is plotted into a curvature distribution graph;

[0022] The average curvature value of each vertex is extracted from the curvature distribution map, and the curvature threshold is set to divide the hull surface into different curvature levels;

[0023] Using the region growing algorithm, adjacent points with similar average curvature values ​​are grouped into the same hull region;

[0024] Each hull region is numbered, a partition data file is generated, and the curvature region to which each point belongs is identified.

[0025] As a preferred solution of the method for optimizing the painting path of the automatic painting robot of the present invention, wherein: performing preliminary path planning according to the partition data to obtain the preliminary painting path includes the following steps:

[0026] Read the partition data file and define the basic parameters of the robot spray head;

[0027] Generate different path plans based on the relationship between different curvature levels and path planning;

[0028] The low curvature area has a flat surface, which directly generates parallel straight paint paths and sprays paint at a higher speed;

[0029] The surface of the medium curvature area is curved, with the center point of the area as the reference, generating spiral and wavy paths and moving at a medium speed;

[0030] The high curvature areas are located at the edges, corners and sharply changing areas of the hull. According to the geometric characteristics of the high curvature areas, arc trajectories are generated to enable the robot spray paint head to move at a lower speed along the contours of the edges and corners.

[0031] The preliminary path data of low curvature, medium curvature and high curvature areas are integrated to generate a complete preliminary painting path file.

[0032] As a preferred solution of the method for optimizing the painting path of the automatic painting robot of the present invention, the following steps are included: based on the preliminary painting path, executing the painting task and detecting the coating thickness data of the painting area in real time:

[0033] Read the planned preliminary painting path data. According to the path data in the preliminary path file, the robot starts to move along the planned path.

[0034] The robot adjusts the painting speed and path type according to the curvature characteristics of each hull area;

[0035] During the painting process, the acoustic sensor emits sound waves at a fixed frequency to the coating surface;

[0036] When the sound wave passes through the coating, it is reflected back to the sensor at the interface between the coating and the substrate. The acoustic sensor receives the reflected sound wave signal and records the round-trip time of the sound wave.

[0037] Collect coating thickness data based on the propagation speed of sound waves in the coating and the round-trip time of sound waves;

[0038] The coating thickness of each test and the corresponding test point coordinates are recorded in real time to generate a thickness test data file.

[0039] As a preferred solution of the method for optimizing the painting path of the automatic painting robot of the present invention, wherein: according to the detected coating thickness data, the preliminary painting path is corrected in real time to generate a new painting path, including the following steps:

[0040] Compare the coating thickness data detected in real time with the target thickness data and calculate the thickness deviation of each detection point;

[0041] The detected thickness data is divided into multiple detection areas according to the painting path, and statistical analysis is performed on multiple detection points in each detection area to calculate the average thickness and thickness uniformity of the detection area;

[0042] When the average thickness of a certain inspection area is less than the target thickness, it means that the coating in the inspection area is too thin. Reduce the painting speed, increase the number of painting times and path overlap rate, and make up for the insufficient coating through additional painting coverage;

[0043] When the average thickness of a certain detection area is greater than the target thickness, it means that the coating in the detection area is too thick. Increase the painting speed and reduce the number of painting times and path overlap rate in the detection area.

[0044] Based on the real-time thickness data, the speed correction coefficient of each detection area is calculated, and the robot's painting speed in the detection area is corrected according to the correction coefficient to generate a new painting path.

[0045] As a preferred solution of the method for optimizing the painting path of the automatic painting robot of the present invention, the following steps are included: real-time detection of the paint coverage rate of the painting area, determination of the coverage uniformity of the painting area, and marking of the unevenly covered painting area:

[0046] During the painting process, the status and coordinates of each detection point are collected in real time through optical sensors and electromagnetic sensors;

[0047] The entire painting area is divided into multiple coverage detection areas, and for each coverage detection area, the local coverage rate is calculated according to the coverage status of the detection points;

[0048] A minimum coverage threshold is set. When the local coverage of each coverage detection area is less than the minimum coverage threshold, the coverage detection area is marked as an uncovered area.

[0049] For the uncovered area, the status of each detection point is further analyzed, the coordinates of the uncovered detection points are recorded, and the area composed of these detection points is marked as the uncovered detection point area.

[0050] After marking all uncovered inspection point areas, the global coverage of the entire painting area is calculated based on the status of all inspection points on the hull;

[0051] When the global coverage reaches the target coverage, the painting task is considered to be basically completed;

[0052] When the global coverage rate does not reach the target coverage rate, the painting task is considered unfinished, and a second painting is performed on the uncovered detection point area.

[0053] As a preferred solution of the method for optimizing the painting path of the automatic painting robot of the present invention, the following steps are included: adjusting the painting path again through the coverage detection data to generate a corrected final painting path, and using the final painting path to perform the painting task on the next ship hull:

[0054] According to the coverage data, the entire painted surface is divided into uncovered areas and normal coverage areas;

[0055] In uncovered areas, the robot shortens the spacing of the painting paths, increases the density of the paint and reduces the speed of the paint;

[0056] In the normal coverage area, the robot maintains the original path and continues to perform the painting task according to the planned painting parameters;

[0057] Divide the uncovered area into multiple areas to be planned, and determine the key path points of each area to be planned;

[0058] Treat path points as graph nodes and path segments as graph edges to build a graph structure;

[0059] Set the starting point as the starting position of the painting task and the end point as the final position of the task;

[0060] Run the shortest path algorithm to find the shortest path from the starting point to the end point in the graph structure;

[0061] Check adjacent uncovered areas and normally covered areas to identify whether their paths have overlapping parts;

[0062] When the paths of the uncovered area and the normally covered area overlap, the paths of the overlapping parts are merged;

[0063] According to the shortest path algorithm and the merged path results, the painting task is performed with the painting parameters of the uncovered area to generate a final painting path, and the final painting path is used to perform the painting task on the next hull.

[0064] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for optimizing the painting path of an automated painting robot as described in the first aspect of the present invention is implemented.

[0065] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for optimizing the painting path of an automated painting robot as described in the first aspect of the present invention is implemented.

[0066] The beneficial effects of the present invention are as follows: by using laser scanning equipment to obtain a three-dimensional geometric model of the hull, and combining curvature analysis to generate partition data, the planning of the paint path can adapt to the curvature changes in different areas. During the painting process, the coating thickness and coverage are detected in real time, and the paint path is dynamically corrected based on these data to ensure that the paint thickness and coverage meet the expected standards. Through such a method, the invention can effectively reduce the phenomenon of uneven paint spraying, avoid spray leakage and overspray problems, especially in edge areas and corners with large curvature changes. In addition, the ability to adjust the paint path in real time makes the painting process more flexible and efficient, reduces rework and material waste, and significantly improves the stability and consistency of the paint quality. Finally, the invented automated painting robot can ensure that the coating in each area is uniform and meets the standards, greatly improving the degree of automation and production efficiency of the painting process. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0068] Figure 1 This is a flow chart of the method for optimizing the painting path of the automated painting robot in Example 1.

[0069] Figure 2 This is a schematic diagram of the preliminary painting path generation in Example 1. DETAILED DESCRIPTION

[0070] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0071] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0072] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0073] Example 1, reference Figure 1 and Figure 2, which is the first embodiment of the present invention, and provides a method for optimizing the painting path of an automated painting robot, comprising the following steps:

[0074] S1. Obtain the three-dimensional geometric model of the hull through a laser scanning device, perform curvature analysis, and generate partition data of the curvature information of each hull area.

[0075] S1.1. The laser scanning equipment performs an all-round scan on the hull surface to generate high-density three-dimensional point cloud data; the high-density three-dimensional point cloud data is processed to remove noise points and redundant points.

[0076] Specifically, remove noise points: use a statistical filtering algorithm to count the number of other points in the local neighborhood of each point. If a point has too few neighboring points, the point is considered a noise point. Set a neighborhood point count threshold. When the number of points in the neighborhood of a point is less than the neighborhood point count threshold, it is marked as a noise point and removed from the point cloud.

[0077] Remove redundant points: Downsample the point cloud through voxel filtering. Set the voxel size (such as 1 mm), divide the point cloud into several voxels, and retain only one representative point in each voxel, usually the centroid of the points in the voxel, to reduce redundant data and simplify the point cloud structure.

[0078] S1.2. Use triangulation algorithm to convert point cloud into polygonal mesh and construct continuous surface.

[0079] Specifically, applying the triangulation algorithm to generate a polygonal mesh includes the following steps:

[0080] According to the spatial position of each point in the point cloud, use the nearest neighbor algorithm (such as the K nearest neighbor algorithm) to find the neighborhood of each point and set the neighborhood parameters. , each point and its neighbors Points are connected to form a local neighborhood. The Delaunay triangulation algorithm is used to connect adjacent points in the point cloud into non-overlapping triangular patches. The rule of Delaunay triangulation is that the circumscribed circle of any triangle does not contain any other points. This algorithm can ensure the generation of a stable triangular mesh and avoid the generation of long and thin triangles. For point clouds in three-dimensional space, three-dimensional Delaunay triangulation is applied to generate tetrahedrons composed of three-dimensional points, and then the outer surfaces of these tetrahedrons are extracted to form a triangular mesh. The triangular patches generated after triangulation are saved as polygonal mesh files (such as STL or OBJ format). The mesh file contains a continuous surface model of the hull surface. Each patch consists of 3 vertices, and the coordinates of the vertices come from the point cloud data.

[0081] S1.3. Smooth the edges and depressions of the surface to generate a complete three-dimensional geometric model.

[0082] It should be noted that the smoothing process uses Laplace smoothing, which is a common surface smoothing algorithm. Its basic idea is to adjust the position of each vertex to the weighted average of its neighboring vertices, thereby smoothing the mesh surface. , its new location Calculated as:

[0083] ;

[0084] in, Represents the index of the current vertex, Represents the current vertex after smoothing The new location, Indicates the current vertex The original position of Represents the smoothing coefficient, which controls the degree of smoothing. represents the number of points in the neighborhood, Indicate point the indices of neighboring points in its neighborhood, Represents the first neighboring points.

[0085] S1.4. Discretize the three-dimensional geometric model and divide the surface into N triangular patches.

[0086] Specifically, the triangulated mesh data is imported from the three-dimensional geometric model. The result of the triangulation is to divide the surface into N triangular patches, each patch consists of three vertices, and for each triangular patch, the coordinates of its three vertices are recorded.

[0087] S1.5. Calculate the normal vector of each triangular face, and find the average curvature value of each vertex by changing the normal vectors of adjacent faces.

[0088] Specifically, the expression of the normal vector of each triangle patch is:

[0089] ;

[0090] in, represents the normal vector, Represents the coordinates of the first vertex in three-dimensional space, respectively. , , Position in direction, Represents the coordinates of the second vertex in three-dimensional space, respectively. , , Position in direction, Represents the coordinates of the third vertex in three-dimensional space, respectively. , , Position in direction;

[0091] For each vertex, the average curvature is calculated by taking the weighted average of the angle differences between the normal vectors of adjacent patches. The expression is:

[0092] ;

[0093] in, Indicates Vertices The mean curvature of represents the total area of ​​all faces in the vertex neighborhood, Indicates The area of ​​a patch, Representation and Vertex The associated normal vector, Representation and Vertex The adjacent The normal vector of each face, express The normal vector of the current face The angle between.

[0094] S1.6. Plot the calculated average curvature value of each vertex into a curvature distribution graph.

[0095] Specifically, the curvature value of each vertex is mapped to a color value. Usually, a color gradient is used to represent different curvature ranges. The following color mapping rules can be set:

[0096] Low curvature (close to zero): Use blue to represent flat areas;

[0097] Medium curvature: Use green or yellow to indicate curved areas;

[0098] High Curvature: Use red to indicate edges or corner areas of the hull surface.

[0099] Use a visualization tool (such as OpenGL or MeshLab) to apply the color mapped by the curvature value to the triangle mesh to generate a curvature map. The color of each vertex is assigned according to its curvature value, and the color of each area on the surface can clearly show the curvature change.

[0100] S1.7. Extract the average curvature value of each vertex from the curvature distribution map, set the curvature threshold, and divide the hull surface into different curvature levels; use the region growing algorithm to classify adjacent points with similar average curvature values ​​into the same hull region; number each hull region, generate a partition data file, and identify the curvature region to which each point belongs.

[0101] Specifically, according to the distribution of curvature values, the curvature of the hull surface is divided into three levels: low curvature, medium curvature and high curvature. Two curvature thresholds are set and As a dividing point:

[0102] Low curvature area: Curvature value , representing the flat hull surface.

[0103] Medium curvature area: Curvature value , representing the smooth curved part of the hull.

[0104] High curvature area: Curvature value , representing the edge or corner area of ​​the hull.

[0105] S2. Perform preliminary path planning based on the partition data to obtain a preliminary painting path, including the following steps:

[0106] Read the partition data file and define the parameters of the robot spray paint head; generate different path plans according to the relationship between different curvature levels and path planning; the surface of the low curvature area is flat, and a parallel straight painting path is directly generated and the paint is sprayed at a higher speed; the surface of the medium curvature area is curved, and the spiral and wavy paths are generated with the center point of the area as the reference and move at a medium speed; the high curvature area is located at the edge, corners and sharply changing areas of the hull. According to the geometric characteristics of the high curvature area, an arc trajectory is generated, so that the robot spray paint head moves at a lower speed along the contour of the edges and corners; the preliminary path data of the low curvature, medium curvature and high curvature areas are integrated to generate a complete preliminary painting path file.

[0107] Specifically, the parameters of the robot include spraying pressure, spraying speed, spraying angle, spraying flow rate, spraying pattern and spraying path overlap rate.

[0108] Specifically, the relationship between curvature and path planning:

[0109] Low curvature area: The curvature is low and the surface is flat or nearly flat. It is suitable for a straight path and the painting speed is fast.

[0110] Medium curvature area: The surface is somewhat curved, suitable for spiral or wavy paths, ensuring that the trajectory is close to the curved surface and the painting speed is medium.

[0111] High curvature areas: Surfaces that are sharply curved, usually at edges or corners. A circular path and slower painting speed are required to ensure even painting without missing any spots.

[0112] S3, based on the preliminary painting path, executing the painting task and detecting the coating thickness data of the painting area in real time includes the following steps:

[0113] The planned preliminary painting path data is read, and according to the path data in the preliminary path file, the robot starts to move along the planned path; the robot adjusts the painting speed and path type according to the curvature characteristics of each hull area; during the painting process, the acoustic sensor emits sound waves to the coating surface at a fixed frequency; when the sound waves pass through the coating, they are reflected back to the sensor at the interface between the coating and the substrate, and the acoustic sensor receives the reflected sound wave signal and records the round-trip time of the sound wave; according to the propagation speed of the sound wave in the coating and the round-trip time of the sound wave, the coating thickness data is collected; the coating thickness of each test and the corresponding test point coordinates are recorded in real time to generate a thickness test data file.

[0114] It should be noted that before the painting task begins, the system reads the planned path file to ensure that the robot performs the painting operation according to the pre-optimized path. This method avoids potential errors in manual path planning and ensures the accuracy and repeatability of the path; the robot moves along the planned path, which can achieve efficient and automated painting operations, reduce manual intervention time, and reduce the complexity of manual operations; by moving along the planned path, it ensures that each hull area can be painted in a predetermined order and angle, greatly improving the uniformity of the coating; by detecting the curvature of different hull areas, the robot can automatically adjust the painting speed and path for areas with larger curvature (such as edges or complex geometric shapes). This adaptive adjustment can ensure uniform coating thickness in complex areas; for areas with larger curvature, slowing down the painting speed can ensure that the paint fully covers the surface, while for flatter areas, normal speed can improve painting efficiency. This ensures that the coating thickness in different areas remains consistent and avoids thin spraying or overspraying.

[0115] S4. According to the detected coating thickness data, the preliminary painting path is corrected in real time, and a new painting path is generated, which includes the following steps:

[0116] The coating thickness data detected in real time is compared with the target thickness data, and the thickness deviation of each detection point is calculated; the detected thickness data is divided into multiple detection areas according to the paint spraying path, and the multiple detection points in each detection area are statistically analyzed to calculate the average thickness and thickness uniformity of the detection area; when the average thickness of a certain detection area is less than the target thickness, it means that the coating of the detection area is too thin, and the painting speed is reduced, the number of painting times and the path overlap rate are increased, and the insufficient coating is compensated by additional paint coverage; when the average thickness of a certain detection area is greater than the target thickness, it means that the coating of the detection area is too thick, and the painting speed is increased, and the number of painting times and the path overlap rate of the detection area are reduced; based on the real-time thickness data, the speed correction coefficient of each detection area is calculated, and the robot's painting speed in the detection area is corrected according to the correction coefficient to generate a new painting path.

[0117] Specifically, the expression of thickness deviation is:

[0118] ;

[0119] in, Indicates thickness deviation, Indicates the coating thickness detected in real time, Indicates target thickness data;

[0120] The expression for average thickness is:

[0121] ;

[0122] in, represents the average thickness, Indicates the number of detection points in the area, Indicates The coating thickness at each test point, Indicates the detection point index;

[0123] Thickness uniformity is expressed by standard deviation, expressed as:

[0124] ;

[0125] in, Indicates the thickness standard deviation.

[0126] The expression of the speed correction coefficient of each detection area is:

[0127] ;

[0128] in, Indicates the speed correction factor;

[0129] According to the correction factor, adjust the robot's painting speed in the detection area as follows:

[0130] when <0, <1, indicates deceleration; when >0, >1, indicating acceleration.

[0131] S5, real-time detection of the paint coverage rate of the paint spraying area, determination of the uniformity of the paint spraying area, and marking of the unevenly covered paint spraying area include the following steps:

[0132] S5.1. During the painting process, the state and coordinates of each detection point are collected in real time by optical sensors and electromagnetic sensors; the entire painting area is divided into multiple coverage detection areas, and for each coverage detection area, the local coverage rate is calculated according to the coverage state of the detection point.

[0133] S5.2. Set a minimum coverage rate threshold. When the local coverage rate of each covered detection area is less than the minimum coverage rate threshold, the covered detection area is marked as an uncovered area. For the uncovered area, further analyze the status of each detection point therein, record the coordinates of the uncovered detection points, and mark the area composed of these detection points as an uncovered detection point area.

[0134] After marking all uncovered inspection point areas, the global coverage of the entire painting area is calculated based on the status of all inspection points on the hull; when the global coverage reaches the target coverage, the painting task is considered completed; when the global coverage does not reach the target coverage, the painting task is considered unfinished, and a second painting can be performed on the uncovered inspection point areas. It should be noted that the global coverage refers to the value calculated after the entire hull is painted.

[0135] Specifically, the expression of global coverage is:

[0136] ;

[0137] in, represents the global coverage, Represents the area of ​​the painted area, that is, the sum of the areas corresponding to all covered detection points. Represents the area of ​​the total target region.

[0138] S6. Adjust the painting path again through the coverage detection data to generate a corrected final painting path. Use the final painting path to perform the painting task on the next ship hull, including the following steps:

[0139] According to the coverage data, the entire painting surface is divided into uncovered areas and normal coverage areas; in the uncovered areas, the robot shortens the spacing of the painting paths, increases the painting density and reduces the painting speed; in the normal coverage areas, the robot maintains the original path and continues to perform the painting task according to the planned painting parameters; the uncovered area is divided into multiple areas to be planned, and the key path points of each area to be planned are determined; the path points are regarded as nodes of the graph, and the path segments are regarded as edges of the graph to construct a graph structure; the starting point is set as the starting position of the painting task, and the end point is set as the final position of the task; the shortest path algorithm is run to find the shortest path from the starting point to the end point in the graph structure; the adjacent uncovered areas and normal coverage areas are checked to identify whether their paths have overlapping parts; when the paths of the uncovered area and the normal coverage area overlap, the paths of the overlapping parts are merged; according to the shortest path algorithm and the merged path results, the painting task is performed with the painting parameters of the uncovered area to generate the final painting path, and the final painting path is used to perform the painting task on the next hull.

[0140] It should be noted that by using coverage data to divide the entire surface into areas with different coverage status, it is possible to accurately identify unpainted and normally painted areas and avoid subjective judgment; by shortening the path spacing and increasing the paint density, it is possible to ensure that the uncovered areas are adequately covered with paint and reduce the possibility of missed spraying; reducing the paint speed helps to increase the thickness of paint deposition in the uncovered areas, ensuring that the coating meets the standard requirements and avoiding thin spraying; subdividing the covered area into multiple small areas allows for more refined management and adjustment of each area to ensure that the paint quality of each small area meets the requirements.

[0141] This embodiment also provides a computer device, which is suitable for the case of a method for optimizing the painting path of an automated painting robot, comprising: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method for optimizing the painting path of an automated painting robot proposed in the above embodiment.

[0142] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0143] The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for optimizing the painting path of an automated painting robot as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage device, a flash memory, a disk or an optical disk.

[0144] In summary, the present invention uses laser scanning equipment to obtain a three-dimensional geometric model of the hull, and combines curvature analysis to generate partition data, so that the planning of the paint path can adapt to the curvature changes in different areas. During the painting process, the coating thickness and coverage are detected in real time, and the paint path is dynamically corrected based on these data to ensure that the paint thickness and coverage meet the expected standards. Through this method, the invention can effectively reduce the uneven painting phenomenon and avoid the problems of leaking and overspraying, especially in edge areas and corners with large curvature changes. In addition, the ability to adjust the paint path in real time makes the painting process more flexible and efficient, reduces rework and material waste, and significantly improves the stability and consistency of the paint quality. Finally, the invented automated painting robot can ensure that the coating in each area is uniform and meets the standards, greatly improving the degree of automation and production efficiency of the painting process.

[0145] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of a method for optimizing the painting path of an automated painting robot are provided.

[0146] Two hulls were selected for the experiment: one used the existing spray painting path planning method (called hull A), and the other used the spray painting path optimization method of the present invention (called hull B). The two hulls were of the same size, structure and material, and the surfaces were pretreated in the same way. The experiment was operated using the same type of laser scanning equipment and spray painting robot to ensure the objectivity of the experiment.

[0147] The first step of the experiment is to perform laser scanning on the two hulls to generate high-density three-dimensional point cloud data. After denoising and processing redundant points of the point cloud data, a continuous surface model of the hull surface is constructed using a triangulation algorithm. Next, the surface is discretized and divided into multiple triangular patches, and the average curvature value of each vertex is obtained by calculating the normal vector of each triangular patch. The method of the present invention further partitions the curvature distribution of hull B, divides different curvature levels into low curvature, medium curvature and high curvature areas, and generates a partition data file.

[0148] The second step is path planning. For hull A, the traditional path planning method is used, that is, a simple straight-line painting path is generated according to the overall shape of the hull, and no special treatment is made for the curvature change. For hull B, based on the partition data, parallel straight-line painting paths are generated for low-curvature areas, spiral and wavy paths are generated for medium-curvature areas, and arc trajectories are generated for high-curvature areas. Through this differentiated path planning, the painting quality in different curvature areas is ensured.

[0149] The third step is the painting experiment. During the painting process, the robot moves along the planned path and detects the coating thickness and coverage in real time. For hull A, since the path planning does not take into account the curvature change, the painting process is not corrected in real time. For hull B, the present invention dynamically adjusts the painting path and painting parameters by real-time detection of thickness and coverage data, ensuring the uniformity of coating thickness and coverage.

[0150] The details are shown in Table 1 below:

[0151] Table 1 Paint spraying path optimization experimental data table

[0152]

[0153] By comparing the above experimental data, it can be clearly seen that the coating thickness of the prior art group varies greatly in different curvature areas on the hull surface, especially in the high curvature area, the coating thickness is only 80μm, which is much lower than the 120μm in the low curvature area. This thickness difference is mainly due to the fact that the prior art fails to adjust the paint path and paint parameters in real time according to the curvature change, resulting in insufficient coating coverage in the high curvature area. In contrast, the coating thickness of the present invention group in each area is more uniform, 130μm in the low curvature area, 125μm in the medium curvature area, and 110μm in the high curvature area, especially in the high curvature area. The coating thickness is significantly improved. This shows that the present invention effectively solves the problem of uneven paint spraying in high curvature areas in the prior art by real-time detection and dynamic adjustment of the paint path.

[0154] Secondly, the standard deviation data of coating thickness further demonstrates the advantage of the present invention in uniformity of painting. The standard deviation of thickness of the prior art group is 15μm, while the standard deviation of the present invention group is only 5μm, indicating that the paint thickness of the present invention is more consistent. This is due to the real-time path correction mechanism of the present invention, which adjusts the painting speed and path overlap rate according to the coating thickness data of each area, thereby achieving a uniform painting effect.

[0155] The data of the paint coverage and quality pass rate also further support the advantages of the present invention. The paint coverage of the prior art group is 85%, and the pass rate is 76%, while the paint coverage of the present invention group reaches 98%, and the pass rate reaches 95%. This shows that the present invention not only improves the uniformity of the coating, but also significantly improves the overall coverage of the paint, so that the paint quality is more in line with the expected standards.

[0156] In summary, by comparing with the prior art, the automatic painting path optimization method of the present invention can significantly improve the painting quality in complex curved surface areas, especially in high curvature areas. The present invention obtains the three-dimensional geometric model of the hull through a laser scanning device, combines curvature analysis and real-time data feedback, and dynamically adjusts the painting path and painting parameters, solving the problem of fixed painting path and uneven painting quality in the prior art.

[0157] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing the painting path of an automated painting robot, characterized in that: include, The three-dimensional geometric model of the hull is obtained through laser scanning equipment, and curvature analysis is performed to generate partition data of curvature information of each hull area; According to the partition data, preliminary path planning is carried out to obtain the preliminary painting path; Based on the preliminary painting path, execute the painting task and detect the coating thickness data of the painting area in real time; According to the detected coating thickness data, the preliminary painting path is corrected in real time to generate a new painting path; Real-time detection of the paint coverage rate of the painting area, judgment of the uniformity of the painting area, and marking of unevenly covered painting areas; The paint path is adjusted again based on the coverage detection data to generate a corrected final paint path, and the final paint path is used to perform the painting task on the next ship hull; According to the detected coating thickness data, the preliminary painting path is corrected in real time, and a new painting path is generated, which includes the following steps: Compare the coating thickness data detected in real time with the target thickness data and calculate the thickness deviation of each detection point; The detected thickness data is divided into multiple detection areas according to the painting path, and statistical analysis is performed on multiple detection points in each detection area to calculate the average thickness and thickness uniformity of the detection area; When the average thickness of a certain inspection area is less than the target thickness, it means that the coating in the inspection area is too thin. Reduce the painting speed, increase the number of painting times and path overlap rate, and make up for the insufficient coating through additional painting coverage; When the average thickness of a certain detection area is greater than the target thickness, it means that the coating in the detection area is too thick. Increase the painting speed and reduce the number of painting times and path overlap rate in the detection area. Based on the real-time thickness data, the speed correction coefficient of each inspection area is calculated, and the robot's painting speed in the inspection area is corrected according to the correction coefficient to generate a new painting path; Real-time detection of the paint coverage rate of the paint spraying area, determination of the uniformity of the paint spraying area, and marking of the unevenly covered paint spraying area include the following steps: During the painting process, the status and coordinates of each detection point are collected in real time through optical sensors and electromagnetic sensors; The entire painting area is divided into multiple coverage detection areas, and for each coverage detection area, the local coverage rate is calculated according to the coverage status of the detection points; A minimum coverage threshold is set. When the local coverage of each coverage detection area is less than the minimum coverage threshold, the coverage detection area is marked as an uncovered area. For the uncovered area, further analyze the status of each detection point therein, record the coordinates of the uncovered detection points, and mark the area composed of these detection points as the uncovered detection point area; After marking all uncovered inspection point areas, the global coverage of the entire painting area is calculated based on the status of all inspection points on the hull; When the global coverage reaches the target coverage, the painting task is considered completed; When the global coverage rate does not reach the target coverage rate, the painting task is considered unfinished, and a second painting is performed on the uncovered detection point area.

2. The method for optimizing the painting path of an automated painting robot according to claim 1, wherein: The three-dimensional geometric model of the hull is obtained by laser scanning equipment, and curvature analysis is performed to generate partition data of curvature information of each hull area, including the following steps: The laser scanning equipment performs an all-round scan of the hull surface to generate high-density three-dimensional point cloud data; Remove noise points and redundant points from high-density 3D point cloud data; Apply triangulation algorithm to convert point cloud into polygonal mesh and construct continuous surface; Smooth the edges and depressions of the surface to generate a complete 3D geometric model; Discretize the 3D geometric model and divide the surface into N triangular patches; Calculate the normal vector of each triangular patch, and find the average curvature value of each vertex by changing the normal vectors of adjacent patches; The calculated average curvature value of each vertex is plotted into a curvature distribution graph; The average curvature value of each vertex is extracted from the curvature distribution map, and the curvature threshold is set to divide the hull surface into different curvature levels; Using the region growing algorithm, adjacent points with similar average curvature values ​​are grouped into the same hull region; Each hull region is numbered, a partition data file is generated, and the curvature region to which each point belongs is identified.

3. The method for optimizing the painting path of an automated painting robot according to claim 2, wherein: According to the partition data, preliminary path planning is carried out to obtain the preliminary painting path, which includes the following steps: Read the partition data file and define the parameters of the robot spray head; Generate different path plans based on the relationship between different curvature levels and path planning; The low curvature area has a flat surface, which directly generates parallel straight paint paths and sprays paint at a higher speed; The surface of the medium curvature area is curved, with the center point of the area as the reference, generating spiral and wavy paths and moving at a medium speed; The high curvature areas are located at the edges, corners and sharply changing areas of the hull. According to the geometric characteristics of the high curvature areas, arc trajectories are generated to enable the robot spray paint head to move at a lower speed along the contours of the edges and corners. The preliminary path data of low curvature, medium curvature and high curvature areas are integrated to generate a complete preliminary painting path file.

4. The method for optimizing the painting path of an automated painting robot according to claim 3, characterized in that: Based on the preliminary painting path, executing the painting task and detecting the coating thickness data of the painting area in real time includes the following steps: Read the planned preliminary painting path data. According to the path data in the preliminary path file, the robot starts to move along the planned path. The robot adjusts the painting speed and path type according to the curvature characteristics of each hull area; During the painting process, the acoustic sensor emits sound waves at a fixed frequency to the coating surface; When the sound wave passes through the coating, it is reflected back to the sensor at the interface between the coating and the substrate. The acoustic sensor receives the reflected sound wave signal and records the round-trip time of the sound wave. Collect coating thickness data based on the propagation speed of sound waves in the coating and the round-trip time of sound waves; The coating thickness of each test and the corresponding test point coordinates are recorded in real time to generate a thickness test data file.

5. The method for optimizing the painting path of an automated painting robot according to claim 4, characterized in that: Through the coverage detection data, the painting path is adjusted again to generate a corrected final painting path. The painting task of the next ship hull using the final painting path includes the following steps: According to the coverage data, the entire painted surface is divided into uncovered areas and normal coverage areas; In uncovered areas, the robot shortens the spacing of the painting paths, increases the density of the paint and reduces the speed of the paint; In the normal coverage area, the robot maintains the original path and continues to perform the painting task according to the planned painting parameters; Divide the uncovered area into multiple areas to be planned, and determine the key path points of each area to be planned; Treat path points as graph nodes and path segments as graph edges to build a graph structure; Set the starting point as the starting position of the painting task and the end point as the final position of the task; Run the shortest path algorithm to find the shortest path from the starting point to the end point in the graph structure; Check adjacent uncovered areas and normally covered areas to identify whether their paths have overlapping parts; When the paths of the uncovered area and the normally covered area overlap, the paths of the overlapping parts are merged; According to the shortest path algorithm and the merged path results, the painting task is performed with the painting parameters of the uncovered area to generate a final painting path, and the final painting path is used to perform the painting task on the next hull.

Images