Visual guidance self-adaptive robot intelligent spraying system and ship block bottom spraying method

Abstract

The invention discloses a visual guidance self-adaptive robot intelligent spraying system and a ship section bottom spraying method. The system comprises an AGV chassis, a visual system, a lifting mechanism and a top spray gun. The visual system and the lifting mechanism are fixed on the AGV chassis; and the top spray gun is fixed at the top end of the lifting mechanism. According to the automatic spraying system special for the segmented bottoms, the lifting device is installed on the AGV chassis, the spray gun is fixedly installed at the top end of the lifting device, spraying of the segmented bottoms can be achieved when the AGV chassis moves, and automation and intelligentization of segmented bottom spraying operation are achieved.

Description

Technical Field

[0001] The present invention relates to the field of ship painting, and in particular to a vision-guided adaptive robot intelligent spraying system and a method for spraying the bottom of a ship section. Background Art

[0002] Ship section painting refers to the rust removal and painting treatment of the surface of the ship section. As an important part of ship painting and even shipbuilding, ship sections can be classified into flat sections, curved sections, semi-solid sections, solid sections, and large solid sections according to their types. For any type of section, its painting operation can be roughly divided into three parts: the top and side elevations, the interior, and the bottom. Section painting is a key process to ensure the anti-corrosion performance of the hull. Traditional painting operations mainly rely on manual operation. Workers need to spray upwards with their heads raised in a narrow space for a long time, which not only has a high labor intensity and low efficiency, but also has quality problems such as uneven coating thickness and missed spraying. More seriously, the harmful substances volatilized in the painting operation environment pose a threat to the health of workers, and working at heights also poses safety hazards. In recent years, with the development of automation technology, robotic arm spraying and AGV mobile spraying systems have been gradually applied to the painting of the top and side elevations of ship sections, significantly improving the operation efficiency and quality. However, there are still many technical problems in the automated painting of the bottom of ship sections: the space at the bottom of the section is narrow and the height changes greatly, making it difficult for conventional equipment to adapt flexibly; the environment in the painting workshop is complex, and the existing laser navigation technology cannot accurately identify the suspended section contour; the lack of coordination between the spraying trajectory planning and the equipment motion control makes it difficult to ensure the coating uniformity. These technical bottlenecks have severely restricted the automation process of the bottom painting of ship sections, making this link still highly dependent on manual operation so far and becoming a key factor restricting the improvement of shipbuilding efficiency.

[0003] Therefore, those skilled in the art are committed to developing a system for automated painting equipment for the bottom of ship sections. Summary of the Invention

[0004] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is how to achieve automated painting of the bottom of ship sections.

[0005] To achieve the above object, the present invention provides a vision-guided adaptive robot intelligent spraying system, which is characterized by comprising an AGV chassis, a vision system, a lifting mechanism, and a top spray gun;

[0006] The vision system and the lifting mechanism are fixed to the AGV chassis;

[0007] The top spray gun is fixed to the top of the lifting mechanism.

[0008] The present invention designs an automatic spraying system dedicated to the bottom of a section. By installing a lifting device on an AGV chassis and installing a fixed spray gun at the top of the lifting device, when the AGV chassis moves, spraying on the bottom of the section can be achieved, realizing the automation and intelligence of the spraying operation on the bottom of the section.

[0009] Further, a controller is placed in the center of the AGV chassis to receive instructions for remote control;

[0010] The AGV chassis is used to enable the system to move on the ground.

[0011] Further, the vision system includes a 3D camera installed at the front end of the lifting mechanism and a 2D lidar on the AGV chassis, which are used to jointly generate a painting workshop map and guide the robot path planning;

[0012] The 3D camera is installed at an inclined angle to the horizontal plane to optimize the point cloud acquisition range at the bottom of the section.

[0013] The existing mapping methods of mobile robots have problems of low efficiency and resource waste when mapping a painting workshop. The present invention designs a method of collaborative mapping by lidar and 3D camera. The initial map (incomplete) obtained by the laser SLAM algorithm is fused with the edge contour of the bottom of the ship section obtained by the 3D camera, so as to obtain a complete painting workshop map and improve the mapping efficiency of the painting workshop.

[0014] Further, the lifting mechanism includes two independent electric cylinders, and each electric cylinder includes a two-stage lifting structure;

[0015] The lifting mechanism is used to lift the top spray gun to a height of 1.15 - 2.5 m from the ground.

[0016] Further, the top spray gun includes a spray gun and a hose, which are used to spray the bottom of the ship section;

[0017] The spray gun is connected to an external paint supply system through a hose, and the head and tail of the hose are respectively fixed to the spray gun and the lifting mechanism.

[0018] Further, the vision system generates a painting workshop map through the following steps:

[0019] (1) Generate an initial environment map through a 2D lidar and the SLAM algorithm;

[0020] (2) Collect the point cloud data of the bottom of the ship section by the 3D camera multiple times, and extract the edge contour after splicing;

[0021] (3) Fuse the edge contour with the initial map to form a complete two-dimensional painting workshop map.

[0022] Further, the edge contour extraction includes:

[0023] Slice the segmented bottom point cloud along the Z-axis to extract the bottommost point cloud thin slice;

[0024] Obtain the XY-plane edge contour of the segmented bottom through projection and contour extraction algorithms.

[0025] Further, during the process of fusing the edge contour with the initial map in step (3), there is also a reference object matching, and the specific steps are:

[0026] Place a triangular prism reference object at the segmented bottom;

[0027] Collect the reference object features through lidar and 3D camera and match them to determine the segmented position information.

[0028] Further, the spraying path planning of the system is realized through the following steps:

[0029] (1) Import the painting workshop map into the full-coverage path algorithm to generate a rasterized path;

[0030] (2) Control the spray gun spacing so that the overlapping spray width is consistent with the AGV chassis width to achieve the unification of the path and the spraying trajectory.

[0031] In a second aspect, the present invention provides a method for spraying the bottom of a ship segment using the visual guidance adaptive robot intelligent spraying system described in the first aspect. The method includes

[0032] Build a map and plan a path through the vision system;

[0033] Control the AGV chassis to move along the path, and at the same time lift the spray gun to the height of the segmented bottom for spraying.

[0034] Technical effects

[0035] The visual guidance adaptive robot intelligent spraying system provided by the present invention has remarkable technical effects:

[0036] First of all, through the coordinated cooperation of the AGV chassis and the adjustable lifting mechanism, precise spraying of the bottom of the ship segment within the height range of 1.15 - 2.5 m is achieved, filling the technical gap in the field of automated painting equipment;

[0037] Secondly, an innovative mapping method that combines lidar and 3D camera is adopted to intelligently fuse the static environment map generated by laser SLAM with the dynamically obtained segmented bottom contour information, which not only greatly improves the integrity and accuracy of the painting workshop map, but also increases the traditional manual mapping efficiency by more than 60%;

[0038] Furthermore, through the optimized matching of the spray gun spacing and the width of the AGV chassis, the complete synchronization of the spraying trajectory and the moving path is achieved, enabling the coating uniformity to reach the industrial precision standard of ±0.05 mm, while reducing paint waste by approximately 35%.

[0039] On the premise of ensuring the spraying quality, the system shortens the traditional manual painting operation time by 80%, effectively solving the industry pain points such as low efficiency, unstable quality, and high operation safety risks in the bottom painting of ship sections during shipbuilding, and providing reliable technical support for ship intelligent manufacturing.

[0040] The concept, specific structure, and technical effects of the present invention will be further described below in conjunction with the drawings to fully understand the purpose, features, and effects of the present invention. Brief Description of the Drawings

[0041] Figure 1 It is a schematic structural diagram of a vision-guided adaptive robot intelligent spraying system according to a preferred embodiment of the present invention;

[0042] Figure 2 It is a schematic structural diagram of the top spray gun according to a preferred embodiment of the present invention;

[0043] Figure 3 It is a schematic structural diagram of the lifting mechanism according to a preferred embodiment of the present invention;

[0044] Figure 4 It is a schematic structural diagram of the vision system according to a preferred embodiment of the present invention;

[0045] Figure 5 It is a map generated by the laser SLAM algorithm according to a preferred embodiment of the present invention;

[0046] Figure 6 It is a schematic diagram of the 3D camera trigger software according to a preferred embodiment of the present invention;

[0047] Figure 7 It is a schematic diagram of point cloud stitching according to a preferred embodiment of the present invention;

[0048] Figure 8 It is a schematic diagram of point cloud slicing and contour extraction according to a preferred embodiment of the present invention;

[0049] Figure 9 It is a schematic diagram of feature point matching according to a preferred embodiment of the present invention;

[0050] Figure 10 It is a schematic diagram of spray gun spacing calculation according to a preferred embodiment of the present invention;

[0051] Figure 11It is a schematic diagram of a grid map and full-coverage path planning of a preferred embodiment of the present invention.

[0052] Wherein:

[0053] 1 - top spray gun, 2 - lifting mechanism, 3 - vision system, 4 - AGV chassis, 5 - spray gun, 6 - hose head, 7 - hose tail, 8 - electric cylinder, 9 - electric cylinder, 10 - battery, 11 - controller, 12 - 3D camera, 13 - camera bracket. Detailed implementation manners

[0054] The following introduces multiple preferred embodiments of the present invention with reference to the accompanying drawings of the specification to make its technical content clearer and easier to understand. The present invention can be embodied in many different forms of embodiments, and the protection scope of the present invention is not limited to the embodiments mentioned in the text.

[0055] In the drawings, components with the same structure are denoted by the same numerical labels, and components with similar structures or functions are denoted by similar numerical labels. The size and thickness of each component shown in the drawings are arbitrarily shown, and the present invention does not limit the size and thickness of each component. To make the illustration clearer, the thickness of some components in the drawings is appropriately exaggerated.

[0056] As Figure 1 shown, the present invention provides a vision-guided adaptive robot intelligent spraying system, including a top spray gun 1, fixed on the top of the lifting mechanism, for spraying the bottom of the ship section; a lifting mechanism 2, installed on the AGV chassis 4, composed of two independent electric cylinders, for lifting the spray gun to a height of 1.15 - 2.5 m; a vision system 3, for jointly generating a coating workshop map and guiding the robot path planning, and an AGV chassis 4, for realizing the walking of the system on the ground.

[0057] As Figure 2 shown, the top spray gun 1 and the spray gun 5 are connected to an external paint supply system through a hose, and the hose head 6 and the hose tail 7 are respectively fixed to the spray gun 5 and the lifting mechanism.

[0058] As Figure 3 shown, the lifting mechanism 2 is composed of two independent electric cylinders 8 and 9, and also includes a battery 10 for power supply and a controller 11 for control.

[0059] As Figure 4 shown, the vision system 3 includes a 3D camera 12 arranged at the front end of the lifting mechanism 2, supported and fixed by a camera bracket, and also includes a 2D lidar on the AGV chassis 4.

[0060] As Figures 5 - 10As shown in the figure, it is a schematic diagram of the system provided by the present invention to implement the vision guidance function. The core content of vision guidance is to create a complete two-dimensional map of the painting workshop. Specifically, it is achieved through a basis and a key piece of information. The basis is the initial environment of the workshop generated by the SLAM algorithm. This environment is basically static and will not change much, so mapping only needs to be done once, and subsequent replacement of sections will not have an impact. The key information is the edge contour information and position information of the sections, which change as the sections are replaced, so it is necessary to re-acquire them before each painting operation.

[0061] The specific process is as follows:

[0062] (1) Basis

[0063] The remote PC controls the AGV chassis to slowly traverse the entire painting workshop. Through the 2D lidar installed on the AGV chassis, the initial map of the painting workshop is generated using the laser SLAM algorithm. Since the 2D lidar cannot scan the suspended ship sections, the sections will not appear on the generated initial map.

[0064] (2) Key Information

[0065] First, the vision system scans the bottom of the ship section. Since the volume of the ship section is large, the 3D camera cannot obtain the complete bottom point cloud of the section in one acquisition and needs to acquire it multiple times. Then, the point clouds acquired multiple times are stitched together into a complete bottom point cloud of the section through the point cloud stitching algorithm.

[0066] Secondly, the obtained complete bottom point cloud of the section is segmented into thin slices of point cloud along the Z-axis through the point cloud slicing algorithm, and the bottommost thin slice of point cloud is extracted. This thin slice of point cloud is projected onto the XY plane through the point cloud projection algorithm, and then the contour of the figure on the XY plane is extracted through the contour extraction algorithm to obtain the edge contour of the bottom of the section.

[0067] Finally, a clearly shaped triangular prism is selected as a reference object to obtain the position information of the section. Ensure that both the lidar and the 3D camera can acquire the shape information of the reference object. The two are feature-matched through the feature matching algorithm, and then based on the matched features, the edge contour of the bottom of the section is displayed on the initial map in the correct size and position through the two-dimensional image stitching algorithm to obtain a complete two-dimensional map of the painting workshop. Since the top spray gun is fixed at the top of the system, the movement path of the trolley basically coincides with the spraying trajectory of the spray gun.

[0068] As Figure 11 shown, it is a schematic diagram of the system provided by the present invention to implement the trajectory planning function.

[0069] Import the obtained complete workshop map into Matlab, generate a spraying path on the rasterized map through the full-coverage path algorithm, and finally export the planned path as a.CSV file and upload it to the robot. When designing the robot structure, by controlling the spacing between the spray guns, keep the overlapping spray width of the top spray guns consistent with the width of the AGV chassis body, so as to achieve the unity of the robot path planning and the spraying trajectory planning of the spray guns. When the robot travels along the spraying path, turn on the top spray guns to achieve the bottom spraying of the ship section bottom.

[0070] The preferred specific embodiments of the present invention have been described in detail above. It should be understood that those of ordinary skill in the art can make many modifications and variations based on the concept of the present invention without creative labor. Therefore, all technical solutions that can be obtained by those skilled in the art in the technical field of the present invention through logical analysis, reasoning, or limited experiments based on the concept of the present invention on the basis of the prior art should be within the protection scope determined by the claims.

Claims

1. A vision-guided adaptive robot intelligent spraying system, characterized in that It includes an AGV chassis, a vision system, a lifting mechanism, and a top spray gun; The vision system and the lifting mechanism are fixed to the AGV chassis; The top spray gun is fixed to the top of the lifting mechanism.

2. The visual guidance adaptive robot intelligent spraying system according to claim 1, characterized in that, A controller is placed in the center of the AGV chassis to receive instructions for remote control; The AGV chassis is used to enable the system to move on the ground.

3. The visual guidance adaptive robot intelligent spraying system according to claim 1, wherein The vision system includes a 3D camera installed at the front end of the lifting mechanism and a 2D lidar on the AGV chassis, which are used to jointly generate a painting workshop map and guide the robot path planning; The 3D camera is installed at an inclined angle with respect to the horizontal plane to optimize the acquisition range of the segmented bottom point cloud.

4. The visual guidance adaptive robot intelligent spraying system according to claim 1, characterized in that, The lifting mechanism includes two independent electric cylinders, and each electric cylinder includes a two-stage lifting structure; The lifting mechanism is used to lift the top spray gun to a height of 1.15 - 2.5 m from the ground.

5. The visual guidance adaptive robot intelligent spraying system according to claim 1, characterized in that, The top spray gun includes a spray gun and a hose, which are used to spray the bottom of the ship segment; The spray gun is connected to an external paint supply system through a hose, and the head and tail of the hose are respectively fixed to the spray gun and the lifting mechanism.

6. The visual guidance adaptive robot intelligent spraying system according to claim 1, characterized in that, The vision system generates a painting workshop map through the following steps: (1) Generate an initial environment map through the 2D lidar and the SLAM algorithm; (2) Collect the point cloud data of the bottom of the ship segment multiple times through the 3D camera, and extract the edge contour after splicing; (3) Integrate the edge contour with the initial map to form a complete 2D map of the painting workshop.

7. The visual guidance adaptive robot intelligent spraying system according to claim 6, wherein, The edge contour extraction includes: Slice the segmented bottom point cloud along the Z axis to extract the bottommost point cloud thin slice; Obtain the XY plane edge contour of the segmented bottom through the projection and contour extraction algorithm.

8. The visual guidance adaptive robot intelligent spraying system according to claim 6, wherein, During the process of integrating the edge contour with the initial map in step (3), there is also a reference object matching, and the specific steps are: Place a triangular prism reference object at the bottom of the segment; Collect the characteristics of the reference object through the lidar and the 3D camera and match them to determine the segment position information.

9. The visual guidance adaptive robot intelligent spraying system according to claim 1, characterized in that, The system realizes the spray path planning through the following steps: (1) Import the painting workshop map into the full coverage path algorithm to generate a rasterized path; (2) Control the spray gun spacing so that the overlapping spray width is consistent with the width of the AGV chassis to unify the path and the spray trajectory.

10. A method for spray painting the bottom of a ship section using the visual guidance adaptive robot intelligent spray painting system according to any one of claims 1-9, characterized in that, The method includes Constructing a map and planning a path through the vision system; Controlling the AGV chassis to move along the path, and at the same time lifting the spray gun to the height of the bottom of the segment for spraying.

Images