An AI spraying system control method capable of autonomous 3D scanning

Abstract

The present invention discloses a control method for an AI spraying system capable of autonomous 3D scanning, comprising using a high-precision 3D scanning device to obtain three-dimensional surface data of a workpiece to be coated, and constructing a surface model of the workpiece based on the data, and extracting surface feature parameters. The coating parameters set by the user, including the viscosity, chemical properties and film thickness requirements of the paint, are received, and the surface feature parameters and coating parameters are input into the spraying optimization model, and the initial spraying trajectory and process parameters are calculated and generated in combination with historical data. Environmental parameters are collected and associated with the initial process parameters, and dynamic environmental compensation is applied to generate adjusted spraying trajectories and process parameters. Through a robot control system, coating operations are performed according to the adjusted parameters, the spraying effect is optimized in real time, and uniform coating of the workpiece surface is ensured. The present invention realizes efficient automation of the spraying process, significantly improves the coating quality and consistency, and is particularly suitable for coating workpieces with complex curved surfaces or variable shapes.

Description

Technical Field

[0001] The present invention relates to the field of control system technology, and in particular to a control method for an AI spraying system capable of autonomous 3D scanning. Background Art

[0002] In the existing technology, automated coating systems are widely used in various industrial production processes, especially when performing high-precision spraying on workpieces with complex geometries. Traditional automatic coating systems usually rely on fixed trajectories or pre-programmed spray paths to achieve uniform coverage of the workpiece. In addition, spraying process parameters (such as spray gun oil output, atomization pressure, and fan pressure) are generally set based on experience, and these systems have difficulty coping with dynamic changes in environmental factors such as temperature, humidity, and wind speed during the coating process.

[0003] However, there are some significant problems with the existing technology. For example, when using an automatic spraying system with a fixed trajectory to process workpieces with complex shapes, it is often difficult to ensure the uniformity of the coating, resulting in unstable coating quality. In addition, the setting of spraying process parameters is usually inflexible and cannot adapt to the characteristic changes of different workpiece surfaces, further reducing coating efficiency and consistency. At the same time, the existing system responds slowly to changes in environmental conditions, causing the coating thickness and quality to change with environmental fluctuations.

[0004] Therefore, there is an urgent need to develop an automated coating method that can dynamically respond to workpiece characteristics and environmental changes to improve coating quality and efficiency. Summary of the invention

[0005] This application provides an AI spraying system control method capable of autonomous 3D scanning to improve painting quality and efficiency.

[0006] The present application provides an AI spraying system control method capable of autonomous 3D scanning, including:

[0007] Using high-precision 3D scanning equipment to obtain three-dimensional surface data of the workpiece to be coated, the three-dimensional surface data including shape and size information of the workpiece;

[0008] Constructing a surface model of the workpiece according to the three-dimensional surface data; analyzing and extracting surface feature parameters of the workpiece to be coated based on the surface model; wherein the surface model is used to represent the overall geometric characteristics of the workpiece; the surface feature parameters include the curvature, concave-convex features, edge position and overall geometric shape of the workpiece surface;

[0009] receiving coating parameters set by a user, wherein the coating parameters include the viscosity of the paint, the chemical properties of the paint, and the required film thickness;

[0010] Input the surface characteristic parameters and the received coating parameters into a pre-established spraying optimization model to obtain an initial spraying trajectory and initial spraying process parameters; wherein the spraying optimization model generates an initial spraying trajectory and initial spraying process parameters by combining the input workpiece surface characteristic parameters and coating parameters for calculation; wherein the initial spraying process parameters include controlling the oil output, atomization pressure and fan pressure of the spray gun to ensure uniformity and appropriate coverage of the coating;

[0011] Collecting coating environment parameters, and associating the coating environment parameters with initial spraying process parameters to generate an adjusted spraying trajectory and adjusted spraying process parameters; wherein the coating environment parameters include temperature, humidity and wind speed;

[0012] The robot is controlled to perform coating operations according to the adjusted spraying trajectory and the adjusted spraying process parameters to optimize the spraying effect and ensure uniform coating on the workpiece surface.

[0013] Furthermore, the high-precision 3D scanning equipment includes multiple laser scanners and a rotational positioning device, the multiple laser scanners are used to simultaneously collect point cloud data of the workpiece surface at different angles, and the rotational positioning device is used to adjust the orientation of the workpiece to ensure complete coverage of the scanning data and reduce scanning errors caused by occlusion.

[0014] Furthermore, constructing a surface model of the workpiece according to the three-dimensional surface data includes:

[0015] Filter the collected point cloud data to remove noise;

[0016] The surface model of the workpiece is reconstructed by a surface fitting algorithm, wherein the surface fitting algorithm optimizes the distribution of the curvature of the workpiece surface based on the least square method to ensure the accuracy of the model.

[0017] Furthermore, the analyzing and extracting the surface characteristic parameters of the workpiece includes:

[0018] Calculate the local curvature of the workpiece surface and concave-convex feature intensity ;

[0019] Use Fourier transform to analyze the frequency spectrum characteristics of the edge position of the workpiece to accurately identify complex geometric shapes;

[0020] Determine the priority areas for spraying on the workpiece surface based on the overall geometry.

[0021] Furthermore, the receiving of the painting parameters set by the user includes:

[0022] Input the paint's viscosity, chemical properties and target film thickness through the user interface;

[0023] The user interface further includes a parameter verification module, which is used to check the rationality of the parameters input by the user after receiving them, and prompt the user to correct potential parameter setting errors.

[0024] Furthermore, the controlling the robot to perform the painting operation includes:

[0025] Using the robot controller to receive the adjusted spraying trajectory and the adjusted spraying process parameters, and generate corresponding motion instructions;

[0026] The robot controller controls the motion path of the robot arm according to the spray trajectory instruction, and adjusts the oil output, atomization pressure and fan pressure of the spray gun according to the spray process parameters;

[0027] By real-time monitoring of the spraying effect during the robot's execution process, the feedback control system is used to automatically correct the speed of the robotic arm and the spraying angle of the spray gun to ensure the uniformity and stability of the coating on the workpiece surface.

[0028] Furthermore, the spraying optimization model includes a surface feature-trajectory optimization sub-model and a coating parameter optimization sub-model; wherein, the input of the surface feature-trajectory optimization sub-model is the surface feature parameters of the workpiece; the output is an initial spraying trajectory; the surface feature-trajectory optimization sub-model calculates the optimal route of the spraying path based on the surface analysis algorithm, and uses the calculated optimal route as the initial spraying trajectory; the input of the coating parameter optimization sub-model is the coating parameters set by the user and the surface feature parameters of the workpiece; the output of the coating parameter optimization sub-model is the initial spraying process parameters; the coating parameter optimization sub-model adopts a coating optimization algorithm based on a physical model, predicts the effects of different spray parameter combinations on coating thickness and uniformity through numerical simulation, and selects parameter settings that can achieve the best coating effect.

[0029] The beneficial effects of the technical solution provided by this application include:

[0030] (1) By using high-precision 3D scanning equipment to collect the three-dimensional surface data of the workpiece and construct a surface model, the surface feature parameters of the workpiece, such as curvature, concave-convex features and edge position, can be analyzed in detail, thereby providing accurate basic information for the coating process, significantly improving the accuracy of the coating trajectory, and ensuring the uniformity and consistency of the coating. (2) By inputting the user-set coating parameters and the workpiece surface feature parameters into the spray optimization model for calculation, the initial spray trajectory and spray process parameters, such as the oil output of the spray gun, atomization pressure and fan pressure, can be dynamically generated. This optimization calculation can effectively adjust the spray settings, optimize the coating coverage effect to the greatest extent, avoid over- or under-spraying, and reduce paint waste. (3) The system collects coating environment parameters such as temperature, humidity and wind speed in real time, associates them with the initial spray process parameters, and adjusts the spray trajectory and process parameters through dynamic environmental compensation. This dynamic adaptability ensures the consistency of the coating effect under various environmental conditions, further improving the quality and stability of the coating. (4) By automatically controlling the robot to perform the adjusted spraying operation, human intervention is reduced, ensuring the automation and efficiency of the coating process. Combined with the optimized spraying trajectory and process parameters, the system can quickly complete the coating task, significantly improve production efficiency, and at the same time ensure highly consistent product coating quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a flow chart of an AI spraying system control method capable of autonomous 3D scanning provided in the first embodiment of the present application. DETAILED DESCRIPTION

[0032] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0033] The first embodiment of the present application provides an AI spraying system control method capable of autonomous 3D scanning. Figure 1 , which is a schematic diagram of the first embodiment of the present application. Figure 1 The first embodiment of the present application provides a detailed description of an AI spraying system control method capable of autonomous 3D scanning.

[0034] Step S101: using a high-precision 3D scanning device to obtain three-dimensional surface data of a workpiece to be painted, wherein the three-dimensional surface data includes shape and size information of the workpiece.

[0035] Step S101 involves acquiring three-dimensional surface data of the workpiece to be coated using a high-precision 3D scanning device. The high-precision 3D scanning device may include, but is not limited to, a laser scanner, a structured light scanner, or an optical scanning system, which can accurately capture the geometric features of the workpiece without contacting the workpiece surface. Specifically, the scanning device can be configured to acquire point cloud data of the workpiece from multiple angles to construct a complete three-dimensional image. The point cloud data includes a large number of spatial coordinate points, each of which represents a specific position on the workpiece surface, and its resolution and accuracy depend on the 3D scanning device used.

[0036] In order to obtain comprehensive and accurate three-dimensional data, scanning equipment is usually equipped with a rotary positioning device or a multi-axis robotic arm to flexibly move around the workpiece or rotate the workpiece itself, thereby avoiding scanning blind spots and reducing occlusion caused by complex surface geometric features (such as concave and convex areas and edge parts). During the scanning process, the device emits lasers or light and receives reflected light, and calculates the position of each point based on flight time, reflection angle or phase difference. The scanning results can be formed into a complete three-dimensional model covering the surface of the workpiece through multiple measurements and splicing of point cloud data.

[0037] The acquired 3D surface data not only includes the overall shape of the workpiece, but also accurately reflects the dimensional information of the workpiece, such as length, width, height, and surface contour. These data are crucial in the subsequent steps because they provide the basis for building an accurate workpiece surface model and extracting surface feature parameters. In addition, the acquired point cloud data is preprocessed, including removing noise, smoothing the surface, and adjusting the coordinate system, to ensure the accuracy and consistency of the model data. These preprocessing techniques can be implemented using filtering algorithms or point cloud optimization tools, with the aim of improving the quality of the scanned data, reducing errors, and preparing for subsequent analysis steps.

[0038] Furthermore, the high-precision 3D scanning equipment includes multiple laser scanners and a rotational positioning device, the multiple laser scanners are used to simultaneously collect point cloud data of the workpiece surface at different angles, and the rotational positioning device is used to adjust the orientation of the workpiece to ensure complete coverage of the scanning data and reduce scanning errors caused by occlusion.

[0039] The construction and operation of the high-precision 3D scanning equipment are designed to achieve complete and accurate scanning of the workpiece surface. To this end, the equipment is equipped with multiple laser scanners that can work simultaneously to minimize scanning blind spots and data omissions caused by a single angle. Each laser scanner is set at a different position and angle to capture various areas of the workpiece surface. In this way, even if the workpiece surface has complex geometric shapes, such as concave and convex features, curved surfaces and protrusions, the laser scanner can still obtain detailed point cloud data to ensure that every detail is accurately recorded.

[0040] The large amount of point cloud data generated by the simultaneous operation of these laser scanners is integrated and optimized through a unified scanning data processing module. Point cloud data is composed of a series of three-dimensional coordinate points that represent the specific location on the surface of the workpiece. By integrating data from multiple scanners, the device can generate a complete and accurate three-dimensional point cloud data set that covers all the geometric features of the workpiece and reduces scanning errors caused by occlusion, shadows or uneven light reflection. This process can significantly improve the accuracy and completeness of the data, providing high-quality basic data for subsequent surface modeling and feature extraction.

[0041] In addition, a rotary positioning device is integrated into the device to adjust the orientation of the workpiece. The rotary positioning device can slowly rotate or adjust the workpiece to a specific position through precise angle control, allowing the scanner to capture various surfaces of the workpiece from different angles. This rotation function is particularly suitable for workpieces with complex shapes, such as those with multiple concave and convex or multi-faceted geometric features. In actual operation, the rotary positioning device can dynamically adjust the angle of the workpiece according to a pre-set scanning path or based on real-time scanning data to ensure that all areas are fully covered without missing any important details.

[0042] The selection of laser scanners can be based on specific scanning accuracy requirements, such as using laser scanners with high resolution and high-speed scanning capabilities to obtain high-density point cloud data in a short time. The rotary positioning device can be a multi-axis turntable with precise angle adjustment capabilities that can carry workpieces of different sizes and weights. By coordinating the operation of the laser scanner and the rotary device, the equipment can efficiently and comprehensively complete the three-dimensional scanning of the workpiece surface, providing reliable data support for the automatic coating system.

[0043] Step S102: constructing a surface model of the workpiece according to the three-dimensional surface data; analyzing and extracting surface feature parameters of the workpiece to be coated based on the surface model; wherein the surface model is used to represent the overall geometric characteristics of the workpiece; the surface feature parameters include the curvature, concave-convex features, edge position and overall geometric shape of the workpiece surface.

[0044] Step S102 involves constructing a surface model of the workpiece based on the three-dimensional surface data obtained in step S101, and analyzing and extracting surface feature parameters of the workpiece to be coated based on the model. First, the process of constructing the surface model of the workpiece includes starting from point cloud data and geometrically reconstructing these points to form a surface structure that can represent the overall geometric characteristics of the workpiece. Specifically, a surface reconstruction algorithm, such as Delaunay triangulation, Poisson surface reconstruction, or a polyhedron-based point cloud fitting method, can be used to convert discrete point cloud data into a continuous three-dimensional surface.

[0045] The surface model should accurately capture the geometric features of the workpiece, including its complex curves and edges. To ensure the accuracy of the model, the data can be smoothed during the reconstruction process to reduce noise and errors, and geometric filtering techniques can be used to optimize the details of the model. In some cases, texture mapping and normal vector calculations can also be applied to more accurately describe the physical characteristics of the workpiece surface.

[0046] After the surface model is built, the surface feature parameters of the workpiece need to be extracted based on the model. This process usually includes multi-step analysis, such as calculating the curvature of the surface. Curvature calculation can be divided into local and global analysis, where the local curvature describes the degree of curvature of each point on the model, usually achieved by Gaussian curvature or mean curvature, while the overall geometry represents the overall geometric trend and surface curvature characteristics of the workpiece. In addition, extracting concave and convex features usually involves calculating the rate of change of the normal vector of each point, identifying areas with significant changes on the surface, which may require special coating treatments.

[0047] Edge position extraction can use gradient analysis and edge detection algorithms, such as edge recognition methods based on surface gradients or morphological operators, to determine the exact position of the edge on the model. This process is very important because the edge area may require different spray trajectories to ensure that the coating does not produce paint accumulation or uncovered phenomena. By identifying and marking these critical areas, accurate information can be provided for subsequent spray optimization.

[0048] The analysis of the overall geometry is used to understand the global features of the workpiece and help optimize the spray path planning so that the spray gun maintains the appropriate angle and distance on the complex geometric surface to ensure the uniformity of the coating. This feature analysis may also include partitioning the model to identify different feature areas and assign appropriate spray strategies to each area.

[0049] Through these steps, the construction of the surface model and the extraction of characteristic parameters provide an accurate geometric and physical basis for the entire coating system.

[0050] Furthermore, constructing a surface model of the workpiece according to the three-dimensional surface data includes:

[0051] Filter the collected point cloud data to remove noise;

[0052] The surface model of the workpiece is reconstructed by a surface fitting algorithm, wherein the surface fitting algorithm optimizes the distribution of the curvature of the workpiece surface based on the least square method to ensure the accuracy of the model.

[0053] The step of constructing a surface model of the workpiece based on the three-dimensional surface data involves a series of precise processing and reconstruction of the collected point cloud data to generate a surface model that can accurately represent the overall geometric characteristics of the workpiece. First, the preliminary processing of the point cloud data includes filtering processing, the purpose of which is to remove the inevitable noise data during the scanning process. Since some inaccurate points may appear due to changes in ambient light, surface reflections and limitations of scanner hardware when collecting three-dimensional surface data, these noise data will affect the accuracy of the surface model. Therefore, filtering processing effectively eliminates outliers and smoothes data by applying mathematical filters (such as Gaussian filtering or median filtering) while retaining important geometric features. The point cloud data processed in this way can provide a more stable and accurate basis for subsequent model reconstruction.

[0054] Next, the filtered point cloud data will be reconstructed through a surface fitting algorithm to generate a continuous workpiece surface model. The surface fitting algorithm converts discrete point cloud data into a smooth surface. Such a conversion requires optimizing the distribution of point cloud data so that the generated surface reflects the actual geometry of the workpiece as realistically as possible. To this end, the surface fitting algorithm used is based on the least squares method, which is a commonly used mathematical optimization method used to minimize the error between the surface and the point cloud data. The core idea of ​​the least squares method is to adjust the fitting surface so that the sum of the squares of the vertical distances from all data points to the surface is minimized, thereby obtaining an optimal fitting result.

[0055] In the specific implementation process, the least squares method is used to optimize the curvature distribution of the workpiece surface. The purpose of curvature distribution optimization is to ensure that the surface model can accurately capture the bending features and geometric changes of the workpiece without ignoring important details due to excessive smoothness. For workpieces with complex geometric features (such as multiple surfaces or structures with concave and convex changes), the surface fitting algorithm can perform local optimization based on the curvature of different areas to ensure the accuracy of the model. The generated surface model will be a continuous mathematical representation that can provide a smooth surface description while retaining the necessary geometric details.

[0056] Furthermore, the analyzing and extracting the surface characteristic parameters of the workpiece includes:

[0057] Calculate the local curvature of the workpiece surface and concave-convex feature intensity ;

[0058] Use Fourier transform to analyze the frequency spectrum characteristics of the edge position of the workpiece to accurately identify complex geometric shapes;

[0059] Determine the priority areas for spraying on the workpiece surface based on the overall geometry.

[0060] The step of analyzing and extracting the surface characteristic parameters of the workpiece is intended to obtain geometric information that is critical to the coating process from the constructed three-dimensional surface model in order to perform precise spraying control. First, the local curvature of the workpiece surface is calculated. and concave-convex feature intensity This is the key content of this step. Local curvature It is a mathematical quantity that describes the curvature of the workpiece surface. By analyzing the curvature of each point on the surface, the system can identify the convex and concave areas on the workpiece surface. The calculation method can be based on differential geometry or use a fitting method to estimate the local curvature value. In this way, the curvature characteristics of each point on the workpiece surface can be accurately described, providing a basis for optimizing the spraying angle and distance.

[0061] Concave and convex feature strength It further describes the severity of the surface undulations. By analyzing the changes in the normal vector of the workpiece surface, the system can calculate the intensity of the concave and convex features and distinguish between smooth areas and irregular areas. Values ​​indicate that the surface changes are more dramatic and require special attention in these areas to avoid uneven spraying or paint accumulation. This precise feature extraction can be achieved through mathematical operations and vector analysis to ensure that the surface characteristics of each area are fully considered.

[0062] Next, using Fourier transform to analyze the spectral characteristics of the edge position of the workpiece is an important method for identifying complex geometric shapes in the present invention. Fourier transform is a method of converting spatial domain signals to frequency domain, which can decompose the edge information of the surface and reveal its spectral characteristics. By analyzing these spectral characteristics, the edges and other complex geometric shapes of the workpiece surface can be accurately identified. Fourier transform is particularly suitable for processing edge areas with high-frequency changes because it can separate and detect subtle changes in the edges, thereby helping to determine the special treatment required for these areas during the spraying process.

[0063] Finally, the priority areas for spraying on the workpiece surface are determined based on the overall geometry. The overall geometry refers to a comprehensive analysis of the general outline and surface features of the workpiece. Combining the results of local curvature and concave-convex features, the system can determine which areas need to be sprayed first to ensure the uniformity of the coating. For example, areas with drastic surface changes or obvious concave-convex features may require adjustment of the spray path or increase in coating thickness to achieve uniform coverage. Through this identification of priority areas, the system is able to optimize the spraying process, reduce spraying time and material waste, while improving coating quality.

[0064] In the above description, and Represents two spatial coordinates in the local coordinate system of the workpiece surface model. Specifically, the workpiece surface can be regarded as a two-dimensional surface embedded in a three-dimensional space, where and It is a coordinate variable used to describe the position of each point on this surface.

[0065] and Function: They are used to define the location on the workpiece surface in order to describe the local characteristics of each point, such as curvature and concave-convex feature intensity In other words, the two coordinates help mark and calculate the geometric characteristics of different points on the workpiece surface, allowing the system to identify which areas require special treatment or adjustment of the coating strategy.

[0066] By using and To represent the position of points, the entire surface can be accurately mathematically described and analyzed, thereby achieving detailed calculation of surface features.

[0067] Step S103: receiving the painting parameters set by the user, wherein the painting parameters include the viscosity of the paint, the chemical properties of the paint and the required film thickness.

[0068] Step S103 involves receiving the coating parameters set by the user in order to provide the required data input for the subsequent spray optimization model to optimize the spray effect. Specifically, these coating parameters include the viscosity of the paint, the chemical properties of the paint, and the required film thickness. These three key variables have a direct impact on the coating quality and uniformity.

[0069] The viscosity of a paint refers to the flow characteristics of the paint, usually measured by the internal friction coefficient or flow resistance of the paint at a certain temperature. High viscosity paints are more difficult to distribute evenly during the coating process and may result in inconsistent coating thickness, while low viscosity paints may produce sagging. Therefore, users need to accurately set the viscosity value according to the specific needs of the workpiece or the coating environment to ensure that the paint can be sprayed smoothly from the spray gun and evenly covered on the workpiece surface. This viscosity value can be entered into the system through the user interface, and the system then passes this parameter to the spray optimization model to adjust the oil output and atomization settings of the spray gun.

[0070] The chemical properties of paint involve the composition and reaction characteristics of the paint, which may include the composition of the paint (such as solvent content, solid particle ratio, etc.) and the curing or drying speed of the paint under specific conditions. This parameter is particularly important because different chemical properties may require different spraying strategies. For example, some paint components may dry quickly in high temperature or high humidity environments, resulting in uneven coatings, while other components may require specific spraying pressures or flow rates to achieve optimal coating results. Users can set corresponding values ​​based on the specific chemical properties of the paint. This setting is also completed through the user interface and transmitted to the spray optimization model for appropriate adjustments.

[0071] The required film thickness refers to the desired coating thickness on the workpiece surface. This parameter is a key factor in determining the functionality and appearance of the coating. The setting of the film thickness needs to take into account the use requirements of the workpiece and the physical properties of the paint. For example, for anti-corrosion coatings, a thicker film layer may be required to provide adequate protection, while coatings for decorative purposes may require thinner and more uniform coverage. Users can set the required film thickness value based on the specific application scenario of the workpiece. After receiving this parameter, the system will adjust the oil output and spray trajectory of the spray gun according to the film thickness requirements to ensure uniform coating distribution on the entire workpiece surface.

[0072] By providing precise coating parameter settings, the system can optimize the coating process based on user input information to ensure that the coating of each workpiece meets the expected quality standards.

[0073] Furthermore, the receiving of the painting parameters set by the user includes:

[0074] Input the paint's viscosity, chemical properties and target film thickness through the user interface;

[0075] The user interface further includes a parameter verification module, which is used to check the rationality of the parameters input by the user after receiving them, and prompt the user to correct potential parameter setting errors.

[0076] The step of receiving the coating parameters set by the user involves a user-friendly interface specially designed for inputting and managing the key parameters required in the coating process. The user interface provides an intuitive input method, allowing the operator to accurately set the viscosity, chemical property parameters and target film thickness of the paint. These parameters are the basis for achieving accurate and efficient coating and must be adjusted according to the actual coating needs and the specific characteristics of the workpiece surface.

[0077] The user first enters the viscosity value of the paint in the interface. Viscosity directly affects the way the paint flows and distributes during the spraying process, so it needs to be set according to the coating environment and the type of paint. The interface may include a slider or text box that allows the user to enter a specific viscosity value or select a predefined viscosity option to simplify the operation. In addition, the user can enter the chemical properties of the paint. These parameters may include the composition of the paint, drying time, volatility, and other physical and chemical properties related to the performance of the coating. The options provided by the user interface may include drop-down menus or check boxes to help users quickly select the most appropriate chemical properties settings.

[0078] Target film thickness is another key parameter that determines the thickness of the sprayed coating to meet specific quality and functional requirements. Users can directly enter the desired film thickness value in the interface, or automatically generate recommended film thickness by selecting the material and application type. The entire input process is designed to provide a high degree of flexibility while ensuring accuracy of operation.

[0079] In order to ensure that the parameters entered by the user are reasonable, a parameter validation module is integrated into the user interface. The function of this module is to automatically check all input parameters to verify whether these parameters comply with the system's predefined rules or industry standards. Specifically, the parameter validation module can determine the validity of the input values ​​through a series of mathematical and logical rules. For example, if the entered viscosity value exceeds the acceptable range, or the chemical properties of the paint are incompatible with the set target film thickness, the system will immediately issue a warning to prompt the user to correct these potential errors.

[0080] The verification module can also provide detailed prompt information, explain each error or inconsistency, and suggest appropriate correction solutions. This design greatly reduces the risk of human error and ensures that the input parameters can be used correctly by the system to achieve stable and high-quality spraying results.

[0081] Step S104: Input the surface feature parameters and the received coating parameters into a pre-established spraying optimization model to obtain an initial spraying trajectory and initial spraying process parameters; wherein the spraying optimization model calculates by combining the input workpiece surface feature parameters and coating parameters to generate an initial spraying trajectory and initial spraying process parameters; wherein the initial spraying process parameters include controlling the oil output, atomization pressure and fan pressure of the spray gun to ensure uniformity and appropriate coverage of the coating.

[0082] Step S104 involves inputting the previously extracted surface feature parameters and the received user-set coating parameters into a pre-established spray optimization model to generate an initial spray trajectory and initial spray process parameters. The key to this process is to use the optimization model for accurate calculation to provide the best process guidance for the spray operation.

[0083] First, surface feature parameters and coating parameters are input into the spray optimization model. Surface feature parameters include the curvature, concave-convex features, edge position and overall geometry of the workpiece surface, while coating parameters include the viscosity, chemical properties and target film thickness of the paint. Together, these input parameters provide the model with a complete description of the workpiece's geometric properties and coating requirements. The spray optimization model performs complex calculations based on these input data to ensure that the spray trajectory and process parameters can best meet the coating requirements.

[0084] The optimization model uses a multi-objective optimization algorithm and machine learning technology, combined with a large amount of historical coating data and actual coating effect feedback to perform calculations. The model first analyzes the changes in the surface shape of the workpiece based on the curvature and concave-convex features of the workpiece to determine the angle and distance that the spray gun needs to maintain in different surface areas. Then, the model evaluates the edge position and overall geometry, and adjusts the spray trajectory so that the spray gun can move smoothly along the surface of the workpiece, while ensuring that there is no coating accumulation or insufficient coating in the edge area.

[0085] For example, suppose a multi-objective optimization algorithm is used in conjunction with machine learning techniques to precisely control the spray trajectory and spray process parameters. The core goal of this optimization model is to ensure that the spray gun sprays at the optimal angle and distance on the workpiece surface, while adjusting the path to avoid coating accumulation or uneven coverage.

[0086] The model is implemented using a gradient descent-based optimization algorithm, and the training process is continuously improved with the help of a large amount of historical coating data. First, the model is analyzed based on the curvature data of the workpiece surface. For example, if a certain area is detected with high curvature (i.e., the surface is sharply curved), the spray gun will automatically adjust the distance to bring it slightly closer to the workpiece surface to ensure a consistent coating thickness. For flat areas, the spray gun can be kept at a farther distance to achieve fast and efficient spray coverage.

[0087] The model then evaluates the uneven features of the workpiece. If a surface area has large uneven variations, the model adjusts the spray angle based on these features so that the paint can adequately cover these complex areas. For example, if the uneven area has a large inclination, the spray gun will be tilted to a position close to the surface normal to maximize the uniformity of coating adhesion.

[0088] For edge areas, the model uses edge detection algorithms to identify the boundaries of the workpiece and slows down the speed of the spray gun or reduces the amount of oil near the edge to prevent excessive coating accumulation. The overall geometry is used to determine the movement path of the spray gun to ensure that it moves smoothly on the surface, avoiding sharp turns or sudden changes in direction, which can prevent discontinuous spraying trajectories or excessive spraying overlap areas.

[0089] The optimization model is implemented through simple mathematical relationships. For example, if the curvature of a surface is , the model calculates the optimal distance from the spray gun to the surface and angle , which can be expressed by a simple linear relationship: ,in is the reference distance, is the adjustment factor. Similarly, the angle of the spray gun It can be adjusted according to the concave and convex features ,in is the base angle, represents the concave-convex feature strength, is the adjustment parameter.

[0090] Through this specific optimization model, existing data and machine learning tools can be used to achieve automatic optimization of the spraying process, ensuring efficient and high-quality painting results.

[0091] While calculating the spray trajectory, the optimization model also adjusts the spray process parameters. Specifically, the oil output of the spray gun is optimized by the model based on the paint viscosity and target film thickness to ensure that the paint can evenly cover the surface of the workpiece without dripping or uneven spraying. The calculation of the atomization pressure is based on the chemical properties of the paint to ensure that the paint particles are fully atomized, forming a uniform spray and accurately attached to the surface of the workpiece. The fan pressure is optimized according to the geometric characteristics of the workpiece surface and the coating requirements to adjust the size and shape of the spray coverage area to achieve the best coating distribution on the entire workpiece surface.

[0092] Finally, the initial spraying trajectory and process parameters generated by the spraying optimization model are output to guide subsequent spraying operations. This optimization calculation can significantly improve the coating quality, reduce paint waste, and improve production efficiency.

[0093] Furthermore, the spraying optimization model includes a surface feature-trajectory optimization sub-model and a coating parameter optimization sub-model; wherein, the input of the surface feature-trajectory optimization sub-model is the surface feature parameters of the workpiece; the output is an initial spraying trajectory; the surface feature-trajectory optimization sub-model calculates the optimal route of the spraying path based on the surface analysis algorithm, and uses the calculated optimal route as the initial spraying trajectory; the input of the coating parameter optimization sub-model is the coating parameters set by the user and the surface feature parameters of the workpiece; the output of the coating parameter optimization sub-model is the initial spraying process parameters; the coating parameter optimization sub-model adopts a coating optimization algorithm based on a physical model, predicts the effects of different spray parameter combinations on coating thickness and uniformity through numerical simulation, and selects parameter settings that can achieve the best coating effect.

[0094] The spray optimization model plays a key role in the entire coating system. It consists of two main sub-models: surface feature-trajectory optimization sub-model and coating parameter optimization sub-model. Through the collaborative work of these two sub-models, the system can accurately calculate the spray path and process parameters to achieve efficient and high-quality coating.

[0095] First, the input of the surface feature-trajectory optimization sub-model is the surface feature parameters of the workpiece, which may include curvature, concave and convex features, edge position and geometry. Using this data, the sub-model uses a surface analysis algorithm to analyze the workpiece surface and calculate the optimal route for the spray path. The surface analysis algorithm analyzes the changes in surface features to find a path that can ensure coating uniformity while reducing the complexity of spray gun movement. For example, the algorithm adjusts the distance and angle between the spray gun and the surface according to the changes in surface curvature to optimize the spray coverage. The output initial spray trajectory provides a smooth and continuous path, ensuring that the spray gun can effectively coat the entire workpiece surface without missing critical areas or generating unnecessary overlaps.

[0096] The inputs of the coating parameter optimization submodel include user-defined coating parameters (such as paint viscosity, chemical properties, and target film thickness) and the surface characteristic parameters of the workpiece. This submodel uses a coating optimization algorithm based on a physical model to predict the impact of different spray parameter combinations on coating thickness and uniformity through numerical simulation. The physical model can simulate the flow characteristics of the paint, the atomization process, and the coating distribution after spraying. For example, numerical simulation can predict how a specific atomization pressure and spray gun oil output affect the adhesion of the coating in areas with high curvature.

[0097] In order to achieve the best coating effect, the coating parameter optimization sub-model will evaluate multiple parameter combinations to find the best settings that can satisfy both thickness uniformity and coating adhesion quality. When selecting these parameters, the model not only takes into account physical properties, but also dynamically adjusts to adapt to different workpiece surface features. For example, if the curvature of a certain area on the workpiece surface is particularly large, the model may adjust the oil output or atomization pressure of the spray gun to ensure that the coating thickness of the paint in this area meets the set standard.

[0098] The output initial spraying process parameters include the oil output, atomization pressure and fan pressure of the spray gun. These parameters, combined with the initial spraying trajectory, form a complete spraying plan, providing precise guidance for the entire coating operation.

[0099] Furthermore, the surface analysis algorithm comprises the following steps:

[0100] Obtain and analyze surface feature parameters, including curvature, from the surface model of the workpiece , concave-convex feature intensity and edge locations , where the curvature Used to measure the curvature of the surface and the strength of the concave and convex features Indicates the severity of surface fluctuations and edge positions Identify the boundaries of the artifact;

[0101] According to the following formula 1, the main direction field of the surface is calculated :

[0102]

[0103] in, represents the surface height distribution;

[0104] According to the concave-convex feature strength , divide the workpiece surface into different spray density areas; calculate the spray density distribution according to the following formula 2 :

[0105]

[0106] in, and To adjust the parameters;

[0107] The path boundary constraint function provided by the following formula 3 is used Combined edge position , optimize the path boundary to ensure that the spraying trajectory does not cross the boundary and has a smooth transition:

[0108]

[0109] in, To control the parameters;

[0110] The global trajectory optimization objective function provided by Formula 4 is: Solve and use numerical optimization methods to determine the optimal path point sequence ;

[0111]

[0112] in, is the path length parameter;

[0113] For the determined optimal path point sequence Interpolation and smoothing are performed to generate the initial spraying trajectory.

[0114] The surface analysis algorithm is designed to optimize the coating path for the spray system to ensure uniform coating coverage and efficient spraying operation on complex workpiece surfaces. First, key surface feature parameters, including curvature, are extracted and analyzed from the surface model of the workpiece. , concave-convex feature intensity and edge position These parameters provide the necessary geometric and physical information for path planning.

[0115] Curvature is a parameter that measures the curvature of a surface and is used to describe the local shape characteristics of the surface. At larger values, the surface will appear significantly curved, which means that the angle and distance of the spray gun may need to be adjusted when spraying to ensure a uniform coating. The curvature is usually calculated by taking higher-order derivatives of the surface model.

[0116] Concave and convex feature strength Indicates the severity of surface undulations. A value of 0 indicates that the surface changes rapidly and more intensive spraying may be needed to cover concave and convex areas. This parameter is derived by analyzing the rate of change of the surface normal vector, ensuring that high relief areas can be accurately identified.

[0117] Edge Location Identify the boundary of the workpiece and use it to optimize the spray path to avoid the spray trajectory exceeding the boundary of the workpiece. This parameter is extracted from the surface model through an edge detection algorithm, usually calculated using gradient or morphological operations.

[0118] Next, the main direction field of the surface is calculated according to Formula 1 , used to guide the direction of the spray path. Formula 1 is:

[0119]

[0120] in, Represents the height distribution of the workpiece surface. Formula 1 obtains the main direction of the surface by calculating the second-order partial derivative, represents the mixed second-order partial derivative of the height distribution, describing the surface and The interactive change of coordinate direction, and Respectively and The second-order partial derivatives of the directions reflect the local curvature in the respective directions.

[0121] Using concave and convex feature strength , the workpiece surface is divided into different spray density areas to distribute the paint more accurately. Formula 2 is:

[0122]

[0123] in, and It is an adjustment parameter used to control the range and baseline of spray density distribution. Adjust the rate of change of spray density with the intensity of concave and convex features, and It is an offset that ensures the minimum spray density still meets coverage requirements in flatter areas.

[0124] In order to optimize the spray path and prevent the spray from going out of bounds, the path boundary constraint function is used To optimize the boundary, ensure that the trajectory is smooth and does not exceed the workpiece boundary. Formula 3 is:

[0125]

[0126] in, To control the parameters, define the strength of the boundary constraints. When the value is 1, it indicates the boundary. Being zero at the boundaries ensures that the path is tightly constrained near the edges and prevented from going beyond the boundaries.

[0127] Global trajectory optimization objective function Calculate the optimal path point sequence by combining the spray density distribution and path direction for optimization Formula 4 is:

[0128]

[0129] in, is the path length parameter. The integral term represents the total cost on the path, and the spray density Weighing the paint coverage on the path, while the angle component Ensure that the path direction is consistent with the main direction field. Numerical optimization methods are used to solve this objective function and find a set of optimal path points. .

[0130] Finally, the calculated optimal path point sequence Interpolation and smoothing are performed to generate the initial spraying trajectory, ensuring that the robot arm moves smoothly when performing the spraying operation and can accurately cover the surface of the workpiece. In this way, those skilled in the art can implement the surface analysis algorithm based on the above detailed description and formula to provide efficient and accurate path optimization for the automatic spraying system.

[0131] In the above description, and Refers to the local coordinates on the workpiece surface model, which are used to describe and identify each position point on the workpiece surface. These coordinates are defined in a two-dimensional coordinate system and are usually used to describe the geometric characteristics and distribution of three-dimensional surface models. Specifically, the workpiece surface is considered to be a two-dimensional surface embedded in a two-dimensional space, and and Represents two lateral coordinates on a surface.

[0132] and Used to determine the position of each point on the workpiece surface to calculate and analyze curvature , concave-convex feature intensity , edge position These coordinates allow the system to perform mathematical analysis and path optimization accurately across the entire surface, ensuring that the spray trajectory achieves a uniform coating effect on every surface area.

[0133] Furthermore, the coating optimization algorithm based on the physical model includes the following steps:

[0134] Receive user-defined painting parameters, including paint viscosity , chemical properties and required film thickness ; Obtain the surface characteristic parameters of the workpiece, including surface roughness and curvature distribution ;

[0135] According to the viscosity of the paint , Required film thickness , Spraying coverage area , Spraying duration , Paint density and surface roughness , use the following formula 5 to calculate the oil output of the spray gun :

[0136]

[0137] in, is the roughness adjustment factor; is the fluid viscosity compensation coefficient;

[0138] Combining the chemical properties of paint , Viscosity and surface curvature , use the following formula 6 to calculate the atomization pressure of the spray gun :

[0139]

[0140] in, is the atomization pressure constant; Adjustment factor for chemical properties; is the target atomized particle size; is the curvature adjustment coefficient;

[0141] Binding viscosity , surface roughness and the average surface curvature , use the following formula 7 to calculate the fan pressure :

[0142]

[0143] in, is the fan pressure adjustment constant; Roughness and curvature coupling coefficient; To prevent a small constant with a zero denominator;

[0144] Based on the calculation results of the above models, the initial spraying process parameters are generated, including the oil output of the spray gun. , atomization pressure and fan pressure .

[0145] The coating optimization algorithm based on the physical model receives the coating parameters set by the user and obtains the surface characteristic parameters of the workpiece, calculates the oil output of the spray gun, the atomization pressure and the fan pressure, so as to achieve accurate coating control. The following is a detailed description of each step and the parameters in the formula. Indicates the fluidity of the paint, higher viscosity slows the flow of the paint, while lower viscosity makes it easier to disperse. Chemical properties Involves the composition of the paint and its effect on atomization and adhesion, including properties such as volatility and curing speed. It refers to the thickness of the coating that is expected to be formed on the surface of the workpiece after spraying, which is directly related to the protective effect or aesthetic effect.

[0146] The system also obtains the surface characteristic parameters of the workpiece, including surface roughness and curvature distribution Surface roughness Reflects the subtle undulations on the workpiece surface. The larger the value, the rougher the surface. It is used to describe the degree of curvature of the workpiece surface at different locations. For example, if the curvature value of a certain surface area is large, the surface in that area is severely curved, and the spray pressure usually needs to be adjusted to ensure uniform coverage.

[0147] According to the viscosity of the paint , target film thickness , Spraying coverage area , Spraying duration , Paint density And surface roughness , the system uses the following formula to calculate the oil output of the spray gun :

[0148]

[0149] In the above formula:

[0150] It is the target film thickness, which controls the thickness of the sprayed layer.

[0151] To determine spray coverage, determine the surface area that needs to be covered.

[0152] For surface roughness, use the roughness adjustment factor To amplify the effect of roughness, ensure that enough paint is sprayed on the rough areas.

[0153] It is the spraying duration to ensure that the painting is completed within the set time.

[0154] is the paint density, which represents the mass per unit volume.

[0155] is the fluid viscosity compensation factor, used to adjust the viscosity Impact on spraying.

[0156] For example, if the roughness Higher, the formula The spray volume will be increased to ensure adequate and uniform coverage of the coating on the rough surface.

[0157] Next, the system combines the chemical properties of the paint , Viscosity and surface curvature , calculate the atomization pressure of the spray gun To ensure that the paint particles are evenly dispersed. The formula is as follows:

[0158]

[0159] In the formula:

[0160] It is the atomization pressure constant, which controls the basic magnitude of atomization pressure.

[0161] It is the viscosity of the paint that affects the spraying pressure of the particles.

[0162] Adjust the coefficient for chemical properties to match the chemical properties of the paint Adjust the fog effect.

[0163] It is the target atomization particle size, which defines the size of the sprayed paint particles.

[0164] is the curvature adjustment coefficient, when the curvature When it is larger, the atomization pressure will increase accordingly.

[0165] For example, if the curvature When a certain area reaches a larger value, the formula items will increase, increase the spray pressure to ensure the paint covers the curved area.

[0166] Finally, combined with viscosity , surface roughness and the average surface curvature , calculate the fan pressure To control the width and thickness distribution of the spray. The formula is as follows:

[0167]

[0168] In the formula:

[0169] Adjust the constant for the fan pressure and set the basic width and thickness distribution of the spray.

[0170] It is the basic coefficient of viscosity and rough precision, which affects the basic sector pressure.

[0171] is the coupling coefficient of roughness and curvature, magnified and coupling effect.

[0172] is the mean curvature, which equalizes the effect of the overall surface curvature.

[0173] It is a small constant that prevents the denominator from being zero and ensures stable calculation.

[0174] For example, if the surface roughness Larger, the formula terms will increase, resulting in increased spray pressure and spray coverage over a wider area.

[0175] Based on the calculation results of the above models, the system generates the initial spraying process parameters, including the oil output of the spray gun. , Zero pressure and fan pressure , ensuring spraying uniformity and coverage accuracy.

[0176] Furthermore, the collecting of coating environment parameters and associating the coating environment parameters with initial spraying process parameters to generate an adjusted spraying trajectory and adjusted spraying process parameters include:

[0177] Based on the dynamic environment compensation algorithm, the spraying trajectory and spraying process parameters are adjusted in real time to compensate for the coating deviation caused by environmental changes, and the adjusted spraying trajectory and adjusted spraying process parameters are generated;

[0178] The dynamic environment compensation algorithm comprises the following steps:

[0179] Receive painting environment parameters, including ambient temperature 、 Ambient humidity and ambient wind speed ; Calculate the environmental variation coefficient according to the following formula 8 :

[0180]

[0181] in, and They are standard temperature and standard humidity respectively; and is the environmental adjustment factor;

[0182] Use the following formulas 9-11 to calculate the adjusted spray parameters, including the adjusted spray gun oil output , adjusted atomization pressure And the adjusted fan pressure ;

[0183]

[0184]

[0185]

[0186] in, and is the environmental compensation coefficient; is the ambient temperature; is the ambient humidity; is the ambient wind speed;

[0187] Based on the trajectory perturbation function provided by formula 12 , adjust the initial spraying trajectory and obtain the adjusted spraying trajectory:

[0188]

[0189] in, and is the trajectory adjustment coefficient; is the ambient temperature; is the ambient humidity; is the ambient wind speed; Represents the spraying direction angle. The spraying direction angle 𝜃 is obtained from the initial spraying trajectory generated by the surface feature-trajectory optimization sub-model, which represents the travel angle of the spray gun at each path point.

[0190] The step of collecting and associating the coating environment parameters is intended to dynamically adjust the spraying process to cope with changes in environmental conditions and ensure the spraying quality and coating consistency. In the industrial coating process, environmental factors such as temperature, humidity and wind speed have a significant impact on the coating effect, so a dynamic environmental compensation algorithm is needed to adjust the spraying parameters in real time.

[0191] First, the system receives and collects painting environment parameters, including ambient temperature 、 Ambient humidity and ambient wind speed These parameters are monitored in real time by precision sensors to ensure data accuracy. Temperature Affects the viscosity and evaporation rate of the paint, ambient humidity Will change the drying characteristics of the paint, and the ambient wind speed This will disturb the stability of the spray path. Therefore, these factors need to be considered and compensated.

[0192] Environmental variation coefficient Formula 8 is used to comprehensively evaluate the overall impact of changes in environmental conditions on coating:

[0193]

[0194] in:

[0195] and They are standard temperature and standard humidity, respectively, which are the benchmark values ​​under ideal spraying conditions.

[0196] and is the environmental adjustment factor, which indicates the sensitivity of various environmental factors to the coating process. For example, if the change in temperature has a greater impact on the viscosity of the paint, It will be correspondingly larger, increasing the weight of temperature compensation.

[0197] The calculated environmental variation coefficient , can be used to adjust the spraying parameters to ensure the consistency of the coating. The adjusted spraying parameters include the oil output of the spray gun , atomization pressure and fan pressure , the calculation formulas are:

[0198] Adjusted spray gun oil output :

[0199]

[0200] in, is the initial oil output of the spray gun, is the coefficient of variation with the environment The relevant compensation coefficient. This formula means that if If the temperature or humidity deviates significantly from the standard value, the oil output of the spray gun will be increased to compensate for the potential lack of coating. For example, if the paint evaporation rate decreases due to increased humidity, the oil output can be increased to maintain a uniform film thickness.

[0201] Adjusted atomization pressure :

[0202]

[0203] In this formula, is the initial atomization pressure, and Is a compensation factor related to environmental changes. Humidity pass The atomizing pressure is regulated to ensure that it is increased when humidity is high to avoid paint particles agglomerating. For example, in high humidity conditions, increasing the atomizing pressure can help the paint atomize more evenly.

[0204] Adjusted situation pressure :

[0205]

[0206] here, is the initial fan pressure, and is the compensation coefficient for wind speed and temperature. It directly affects the stability of the spray coverage area. Therefore, when the wind speed is high, the fan pressure will be reduced to prevent the paint mist from being blown away by the wind.

[0207] In addition, in order to compensate for environmental disturbances and optimize the spray path, the system uses a trajectory perturbation function To adjust the initial spray trajectory, the calculation formula is as follows:

[0208]

[0209] In this formula:

[0210] and are trajectory adjustment factors, which are used to compensate for the effects of temperature, humidity, and wind speed. As it increases, the path will change according to Make adjustments to prevent coating shifting.

[0211] is the spray direction angle, obtained from the surface feature-trajectory optimization submodel, which represents the travel angle of the spray gun at each path point. This angle is used to calculate the component of wind speed in the spray direction to ensure accurate and effective trajectory adjustment.

[0212] Using trajectory perturbation function The process of adjusting the initial spray trajectory is to compensate for the coating deviation caused by environmental factors and ensure the consistency and accuracy of the spray effect. Specifically, the trajectory perturbation function is based on the ambient temperature. ,humidity and wind speed The change in path is used to calculate the path offset that needs to be adjusted.

[0213] First, the trajectory perturbation function The environmental parameters are compared with the preset standard values, the change range of temperature and humidity is evaluated, and the influence of wind speed is combined to generate a comprehensive trajectory offset value. This offset value is adjusted by a series of adjustment coefficients (such as and ) to determine the specific impact of each environmental factor on the spray trajectory.

[0214] Spraying direction angle is another key factor, which represents the direction of the gun at each path point. The trajectory perturbation function uses To calculate the wind speed component in the spraying direction, ensure that the trajectory adjustment can effectively offset the lateral disturbance caused by the wind speed. This means that when the wind speed has a greater impact on the spraying path, the system will offset the trajectory of the spray gun and make fine adjustments in the opposite direction of the wind speed to prevent the coating from being blown off by the wind or uneven coating thickness.

[0215] In general, the system perturbs the calculated trajectory by Applied to the initial spray trajectory, the position and travel path of the spray gun are dynamically adjusted. This adjustment is real-time and continuously optimized according to changes in environmental conditions, ensuring that the spraying operation is always accurate and meets the coating quality requirements.

[0216] Through these dynamic adjustments, the system generates spraying parameters and optimized spraying paths that adapt to environmental changes.

[0217] Step S105: Collecting painting environment parameters, and associating the painting environment parameters with initial spraying process parameters to generate an adjusted spraying trajectory and adjusted spraying process parameters; wherein the painting environment parameters include temperature, humidity and wind speed.

[0218] Step S105 involves collecting coating environment parameters and associating these parameters with initial spraying process parameters to generate an adjusted spraying trajectory and adjusted spraying process parameters, thereby ensuring that the desired spraying effect can be achieved under changing environmental conditions. The collection of coating environment parameters is very important because environmental factors such as temperature, humidity and wind speed can significantly affect coating quality and uniformity.

[0219] First, the coating system monitors the temperature, humidity, and wind speed in the environment in real time through built-in or external sensors. These sensors are usually placed in key locations in the coating area to capture real-time changes in environmental conditions. For example, temperature sensors measure the temperature of the air to ensure that its impact on the fluidity and curing time of the paint can be tracked in real time. Humidity sensors detect the moisture content in the air because humidity levels affect the evaporation rate and adhesion performance of the paint. Wind speed sensors monitor airflow in the coating area to prevent external airflow from interfering with the spraying trajectory or causing paint particles to deviate during the spraying process.

[0220] Once these environmental parameters are collected, the system associates them with the initial spray process parameters. This association process involves calculations and adjustments to compensate for the potential impact of environmental changes on the spraying effect. The system uses an environmental compensation algorithm to analyze these environmental data and adjust the spraying parameters according to the specific values ​​of temperature, humidity and wind speed. For example, if the ambient temperature increases, the viscosity of the paint may decrease, and the system may reduce the oil output of the spray gun accordingly to avoid excessive flow or dripping of the paint. Similarly, if the humidity is high, the system can adjust the atomization pressure to ensure that the paint particles can be evenly distributed and quickly solidified without forming flow marks or bubbles on the surface. Changes in wind speed may cause spraying deviations, so the system can dynamically adjust the spraying trajectory and fan pressure to compensate for the impact of wind speed on the spray direction.

[0221] Through this real-time adjustment, the system generates new spraying trajectories and process parameters to ensure that the coating effect under different environmental conditions can meet the expected standards. The adjusted parameters and trajectories are transmitted to the spraying control module to provide a basis for subsequent spraying operations.

[0222] Step S106: Control the robot to perform the coating operation according to the adjusted spraying trajectory and the adjusted spraying process parameters to optimize the spraying effect and ensure uniform coating on the workpiece surface.

[0223] Step S106 involves controlling the robot to perform the coating operation according to the adjusted spraying trajectory and spraying process parameters generated in the previous step to achieve an optimized coating effect and ensure uniform coating on the workpiece surface. This step is the core part of the entire automated coating system and requires a combination of precise path control and real-time process parameter adjustment.

[0224] First, after receiving the adjusted spray trajectory and process parameters, the robot interprets these instructions through its motion controller. The motion controller manages the movement of the robot arm, including position, speed, acceleration, etc., to ensure that the robot arm can move accurately along the set trajectory. The robot guides the spray gun point by point or continuously according to the adjusted trajectory to ensure that the appropriate spray angle and distance are maintained on complex geometric surfaces. The angle and distance are dynamically adjusted according to the surface feature parameters to maximize the uniformity of the coating and reduce spray overlap or gaps.

[0225] Control of spraying process parameters is also crucial. The oil output of the spray gun is adjusted by the system in real time to meet the coating requirements of different areas of the workpiece surface. For uneven areas, the system can increase or decrease the oil output according to the set parameters to ensure consistent coating thickness. Atomization pressure affects the size and distribution of paint particles. By adjusting the atomization pressure in real time, the system can control the uniformity and diffusion characteristics of the spray mist to ensure the best spraying effect under different environmental conditions.

[0226] The fan pressure determines the width of the spray coverage area of ​​the spray gun. The system optimizes the spray coverage according to the adjusted process parameters to ensure that the edge areas are fully coated without excess coating accumulation. The coordinated control of all these parameters is monitored and adjusted in real time through a closed-loop feedback system. The closed-loop control system continuously collects feedback information on the spray effect, such as coating thickness and uniformity, and fine-tunes the robot movement and spray parameters based on this data to eliminate deviations.

[0227] To ensure the stability of the coating process, the robot also uses built-in sensors to monitor its own motion accuracy and external interference during the spraying process. For example, if external airflow or a slight deviation of the robotic arm is detected, the system will automatically compensate to ensure the accuracy of the spraying path. Through this precise control, the robot can perform coating operations efficiently, no matter how complex the shape of the workpiece is or how the environmental conditions change, ultimately achieving consistent and high-quality coating results.

[0228] Furthermore, the controlling the robot to perform the painting operation includes:

[0229] Using the robot controller to receive the adjusted spraying trajectory and the adjusted spraying process parameters, and generate corresponding motion instructions;

[0230] The robot controller controls the motion path of the robot arm according to the spray trajectory instruction, and adjusts the oil output, atomization pressure and fan pressure of the spray gun according to the spray process parameters;

[0231] By real-time monitoring of the spraying effect during the robot's execution process, the feedback control system is used to automatically correct the speed of the robotic arm and the spraying angle of the spray gun to ensure the uniformity and stability of the coating on the workpiece surface.

[0232] The step of controlling the robot to perform the coating operation involves precisely coordinating the robot controller and the spraying equipment to achieve uniform and stable coating of the workpiece surface. First, the robot controller receives the adjusted spray trajectory and spray process parameters, which are optimized based on environmental changes and workpiece surface characteristics. The role of the robot controller is to parse this data and generate corresponding motion instructions to ensure that the robot arm can move along the specified trajectory.

[0233] The controller calculates the precise movement of each joint of the robot arm so that the spray gun can be maintained at the proper angle and distance, following an optimized trajectory path. The robot arm's motion path is carefully designed to avoid quick turns or sharp accelerations, which maintains an even distribution of the coating and reduces spray inconsistencies caused by vibration or speed changes of the robot arm.

[0234] At the same time, the robot controller will dynamically adjust the settings of the spray gun according to the input spray process parameters, including oil output, atomization pressure and fan pressure. The oil output determines the flow rate of the paint, which directly affects the thickness of the coating; the atomization pressure controls the particle size and distribution of the sprayed paint to ensure that the paint can be evenly attached to the surface of the workpiece; the fan pressure determines the width of the spray coverage area to adapt to the geometric characteristics of different areas on the workpiece surface. The controller monitors and adjusts these parameters in real time to ensure the best spraying effect.

[0235] In order to further improve the accuracy and stability of coating, the system also uses a feedback control system for real-time monitoring and correction. The feedback control system captures the actual data of the robot arm and the spraying effect through sensors, and monitors key information such as the thickness, uniformity and angle of the coating during the spraying process. If deviations are detected, such as unstable robot arm speed or inaccurate spraying angle, the system will make adjustments immediately. The feedback mechanism can automatically correct the movement speed of the robot arm and the angle of the spray gun to ensure that the spraying trajectory always remains on the optimal path and the coating evenly covers the entire workpiece surface.

[0236] This real-time automatic correction mechanism greatly improves the reliability and accuracy of the coating system, ensuring that the coating is evenly distributed even on complex geometric surfaces, without uncovered areas or paint accumulation.

[0237] A second embodiment of the present application provides an electronic device, the electronic device comprising:

[0238] processor;

[0239] The memory is used to store a program, which, when read and executed by the processor, executes an AI spraying system control method capable of autonomous 3D scanning provided in the first embodiment of the present application.

[0240] The third embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the program executes an AI spraying system control method capable of autonomous 3D scanning provided in the first embodiment of the present application.

[0241] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

Claims

1. A control method for an AI spraying system capable of autonomous 3D scanning, characterized in that: include: Using high-precision 3D scanning equipment to obtain three-dimensional surface data of the workpiece to be coated, the three-dimensional surface data including shape and size information of the workpiece; Constructing a surface model of the workpiece according to the three-dimensional surface data; analyzing and extracting surface feature parameters of the workpiece to be coated based on the surface model; wherein the surface model is used to represent the overall geometric characteristics of the workpiece; the surface feature parameters include the curvature, concave-convex features, edge position and overall geometric shape of the workpiece surface; receiving coating parameters set by a user, wherein the coating parameters include the viscosity of the paint, the chemical properties of the paint, and the required film thickness; Input the surface characteristic parameters and the received coating parameters into a pre-established spraying optimization model to obtain an initial spraying trajectory and initial spraying process parameters; wherein the spraying optimization model generates an initial spraying trajectory and initial spraying process parameters by combining the input workpiece surface characteristic parameters and coating parameters for calculation; wherein the initial spraying process parameters include controlling the oil output, atomization pressure and fan pressure of the spray gun to ensure uniformity and appropriate coverage of the coating; Collecting coating environment parameters, and associating the coating environment parameters with initial spraying process parameters, adjusting the spraying trajectory and spraying process parameters in real time based on a dynamic environment compensation algorithm, compensating for coating deviations caused by environmental changes, and generating adjusted spraying trajectory and adjusted spraying process parameters; wherein the coating environment parameters include temperature, humidity and wind speed; The robot is controlled to perform coating operations according to the adjusted spraying trajectory and the adjusted spraying process parameters to optimize the spraying effect and ensure uniform coating on the workpiece surface.

2. The control method of the AI ​​spraying system capable of autonomous 3D scanning according to claim 1 is characterized in that: The high-precision 3D scanning equipment includes multiple laser scanners and a rotation positioning device. The multiple laser scanners are used to simultaneously collect point cloud data of the workpiece surface at different angles. The rotation positioning device is used to adjust the orientation of the workpiece to ensure complete coverage of the scanning data and reduce scanning errors caused by occlusion.

3. The control method of the AI ​​spraying system capable of autonomous 3D scanning according to claim 1 is characterized in that: The surface model of the workpiece is constructed according to the three-dimensional surface data, comprising: Filter the collected point cloud data to remove noise; The surface model of the workpiece is reconstructed by a surface fitting algorithm, wherein the surface fitting algorithm optimizes the distribution of the curvature of the workpiece surface based on the least square method to ensure the accuracy of the model.

4. The control method of the AI ​​spraying system capable of autonomous 3D scanning according to claim 1 is characterized in that: The analyzing and extracting of the surface characteristic parameters of the workpiece comprises: Calculate the local curvature of the workpiece surface and concave-convex feature intensity ; Use Fourier transform to analyze the frequency spectrum characteristics of the edge position of the workpiece to accurately identify complex geometric shapes; Determine the priority areas for spraying on the workpiece surface based on the overall geometry.

5. The control method of the AI ​​spraying system capable of autonomous 3D scanning according to claim 1 is characterized in that: The receiving of the coating parameters set by the user includes: Input the paint's viscosity, chemical properties and target film thickness through the user interface; The user interface further includes a parameter verification module, which is used to check the rationality of the parameters input by the user after receiving them, and prompt the user to correct potential parameter setting errors.

6. The control method of the AI ​​spraying system capable of autonomous 3D scanning according to claim 1 is characterized in that: The controlling the robot to perform the painting operation comprises: Using the robot controller to receive the adjusted spraying trajectory and the adjusted spraying process parameters, and generate corresponding motion instructions; The robot controller controls the motion path of the robot arm according to the spray trajectory instruction, and adjusts the oil output, atomization pressure and fan pressure of the spray gun according to the spray process parameters; By real-time monitoring of the spraying effect during the robot's execution process, the feedback control system is used to automatically correct the speed of the robotic arm and the spraying angle of the spray gun to ensure the uniformity and stability of the coating on the workpiece surface.

7. The control method of the AI ​​spraying system capable of autonomous 3D scanning according to claim 1 is characterized in that: The spraying optimization model includes a surface feature-trajectory optimization submodel and a coating parameter optimization submodel; wherein, the input of the surface feature-trajectory optimization submodel is the surface feature parameters of the workpiece; the output is the initial spraying trajectory; the surface feature-trajectory optimization submodel calculates the optimal route of the spraying path based on the surface analysis algorithm, and uses the calculated optimal route as the initial spraying trajectory; the input of the coating parameter optimization submodel is the coating parameters set by the user and the surface feature parameters of the workpiece; the output of the coating parameter optimization submodel is the initial spraying process parameters; the coating parameter optimization submodel adopts a coating optimization algorithm based on a physical model, predicts the effects of different spray parameter combinations on coating thickness and uniformity through numerical simulation, and selects parameter settings that can achieve the best coating effect.

8. The control method of the AI ​​spraying system capable of autonomous 3D scanning according to claim 7 is characterized in that: The surface analysis algorithm comprises the following steps: Obtain and analyze surface feature parameters, including curvature, from the surface model of the workpiece , concave-convex feature intensity and edge locations , where the curvature Used to measure the curvature of the surface and the strength of the concave and convex features Indicates the severity of surface fluctuations and edge positions Identify the boundaries of the artifact; According to the following formula 1, the main direction field of the surface is calculated : in, represents the surface height distribution; According to the concave-convex feature strength , divide the workpiece surface into different spray density areas; calculate the spray density distribution according to the following formula 2 : in, and To adjust the parameters; The path boundary constraint function provided by the following formula 3 is used Combined edge position , optimize the path boundary to ensure that the spraying trajectory does not cross the boundary and has a smooth transition: in, To control the parameters; The global trajectory optimization objective function provided by Formula 4 is: Solve and use numerical optimization methods to determine the optimal path point sequence ; in, is the path length parameter; For the determined optimal path point sequence Interpolation and smoothing are performed to generate the initial spraying trajectory.

9. The control method of the AI ​​spraying system capable of autonomous 3D scanning according to claim 8, characterized in that: The coating optimization algorithm based on the physical model includes the following steps: Receive user-defined painting parameters, including paint viscosity , chemical properties and required film thickness ; Obtain the surface characteristic parameters of the workpiece, including surface roughness and curvature distribution ; According to the viscosity of the paint , Required film thickness , Spraying coverage area , Spraying duration , Paint density and surface roughness , use the following formula 5 to calculate the oil output of the spray gun : in, is the roughness adjustment factor; is the fluid viscosity compensation coefficient; Combining the chemical properties of paint , Viscosity and surface curvature , use the following formula 6 to calculate the atomization pressure of the spray gun : in, is the atomization pressure constant; Adjustment factor for chemical properties; is the target atomized particle size; is the curvature adjustment coefficient; Binding viscosity , surface roughness and the average surface curvature , use the following formula 7 to calculate the fan pressure : in, is the fan pressure adjustment constant; Roughness and curvature coupling coefficient; To prevent a small constant with a zero denominator; is the viscosity and rough precision basic coefficient; Based on the calculation results of the above models, the initial spraying process parameters are generated, including the oil output of the spray gun. , atomization pressure and fan pressure .

10. The control method of the AI ​​spraying system capable of autonomous 3D scanning according to claim 9, characterized in that: The collecting of coating environment parameters and associating the coating environment parameters with initial spraying process parameters to generate an adjusted spraying trajectory and adjusted spraying process parameters include: Based on the dynamic environment compensation algorithm, the spraying trajectory and spraying process parameters are adjusted in real time to compensate for the coating deviation caused by environmental changes, and the adjusted spraying trajectory and adjusted spraying process parameters are generated; The dynamic environment compensation algorithm comprises the following steps: Receive painting environment parameters, including ambient temperature , Ambient humidity and ambient wind speed ; Calculate the environmental variation coefficient according to the following formula 8 : in, and They are standard temperature and standard humidity respectively; and is the environmental adjustment factor; Use the following formulas 9-11 to calculate the adjusted spray parameters, including the adjusted spray gun oil output , adjusted atomization pressure And the adjusted fan pressure ; in, and is the environmental compensation coefficient; is the ambient temperature; is the ambient humidity; is the ambient wind speed; Based on the trajectory perturbation function provided by formula 12 , adjust the initial spraying trajectory and obtain the adjusted spraying trajectory: in, and is the trajectory adjustment coefficient; is the ambient temperature; is the ambient humidity; is the ambient wind speed; Indicates the spraying direction angle, spraying direction angle Obtained from the initial spray trajectory generated by the surface feature-trajectory optimization submodel, representing the travel angle of the spray gun at each path point.

Images