Automatic electrostatic spraying control system and automatic spraying method

Abstract

The invention discloses an automatic electrostatic spraying control system and an automatic spraying method, and particularly relates to the technical field of automatic spraying, the size, shape and material information of a workpiece is accurately obtained by utilizing a 3D scanning technology, and optimal planning of a spraying track is realized through spraying path search and optimization based on a genetic algorithm; in the spraying execution stage, coating thickness and color difference information is collected in real time through simulation and a global sensor, a spraying quality detection model is constructed, and the spraying state is judged in real time; and the closed-loop control module quickly generates a regulation and control signal according to a detection result and dynamically adjusts spraying parameters, so that real-time compensation and optimization are realized when an abnormality occurs, defect accumulation is prevented, stable and consistent product quality is ensured, and meanwhile, coating waste and environmental pollution are reduced. And comprehensive improvement of production efficiency, quality control and environmental protection benefits is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic spraying, and more specifically, the present invention relates to an automatic electrostatic spraying control system and an automatic spraying method. Background Art

[0002] With the continuous improvement of the requirements for product quality, production efficiency, and environmental protection in the manufacturing industry, traditional spraying technologies are facing an urgent need for technological upgrading. As an efficient, energy-saving, and environmentally friendly coating technology, automatic electrostatic spraying uses the principle of electrostatic adsorption to achieve uniform distribution of paint on the surface of workpieces, which can not only significantly improve the coating quality but also effectively reduce paint waste and environmental pollution.

[0003] Currently, the quality inspection of the electrostatic spraying process mainly relies on post-inspection, such as using an offline thickness gauge, X-ray, or optical microscopy detection, but these methods cannot be adjusted immediately during the spraying process. When spraying abnormalities occur (such as gun clogging, electric field abnormalities, coating thickness exceeding the standard, etc.), the traditional system cannot provide real-time feedback and compensation adjustment, resulting in the accumulation of spraying defects and affecting the quality of the final product. In addition, most of the existing spraying thickness detection technologies are based on point measurement or small-range scanning, which are difficult to meet the requirements of real-time monitoring of the entire surface of the workpiece. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an automatic electrostatic spraying control system and an automatic spraying method to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An automatic electrostatic spraying control system includes the following modules: a workpiece pretreatment module, an intelligent spraying planning module, an electrostatic spraying execution module, and a closed-loop control module;

[0007] The workpiece pretreatment module is used to clean and decontaminate the surface of the workpiece, establish a 3D model of the workpiece through 3D scanning, and extract workpiece parameters, where the workpiece parameters include but are not limited to size, shape distribution, and material distribution;

[0008] The intelligent spraying planning module is used to search for a spraying path on the surface of the workpiece 3D model according to the workpiece parameters, obtain the spraying path, and optimize the spraying path by combining the genetic algorithm;

[0009] The electrostatic spraying execution module is used to control the spray gun to spray the target workpiece according to the spraying path, simulate the spraying, obtain spraying quality information, and construct a spraying quality detection model to detect the quality of the spraying state;

[0010] The closed-loop control module is used to perform closed-loop control on the spraying simulation according to the quality detection result of the spraying state.

[0011] In a preferred embodiment, the genetic algorithm is combined to optimize the spraying path as follows:

[0012] A1: Each obtained initial spraying path is taken as an individual spraying path;

[0013] A2: Calculate the fitness: where FS represents the fitness, Coverage represents the coverage, Cov1 represents the covered area, Cov2 represents the uncovered area, Time represents the spraying time, and Waste represents the paint waste;

[0014] A3: Select the spraying path and retain the path with the maximum fitness value;

[0015] A4: Perform a crossover operation on the spraying path to exchange part of the spraying trajectory;

[0016] A5: Perform a mutation operation on the spraying path to randomly adjust the spraying path points;

[0017] A6: Preset the iteration time and repeat A2, A3, A4, and A5 for iterative optimization;

[0018] Finally, the optimized spraying path is obtained.

[0019] In a preferred embodiment, the spraying quality information includes the spraying color difference abnormal coefficient, the spraying thickness uniformity abnormal coefficient, and the spraying abnormal response coefficient.

[0020] In a preferred embodiment, the acquisition logic of the spraying color difference abnormal coefficient is as follows:

[0021] Use an RGB camera to collect the spraying area image tx(x, y), and perform a fast Fourier transform on the image channels of the spraying area image tx(x, y): where F(u, v) is the Fourier transform result, (u, v) represents the frequency domain coordinates, M and N respectively represent the width and height of the spraying area image, and sx represents the imaginary unit; calculate the amplitude spectrum: A(u, v) = log(1 + |F(u, v)|), where A(u, v) is the amplitude spectrum; calculate the total energy of the amplitude spectrum: where Etotal represents the total energy of the amplitude spectrum; calculate the distance from the frequency component to the spectrum center: where DJ(u, v) represents the distance from the frequency component to the spectrum center, Denote the center of the frequency spectrum; compare the distance from the frequency component to the center of the frequency spectrum with a preset high-frequency radius threshold. If the distance from the frequency component to the center of the frequency spectrum is greater than the high-frequency radius threshold, it indicates that the point (u, v) belongs to the high-frequency region;

[0022] Calculate the abnormal coefficient of spraying color difference: where ηcolor represents the abnormal coefficient of spraying color difference, and HighFreq represents the high-frequency region;

[0023] Compare the abnormal coefficient of spraying color difference with a preset threshold of the abnormal coefficient of spraying color difference. If the abnormal coefficient of spraying color difference is greater than the threshold of the abnormal coefficient of spraying color difference, it indicates that there is an abnormality in the spraying color difference of the spraying area.

[0024] In a preferred embodiment, the acquisition logic of the abnormal coefficient of spraying thickness uniformity is as follows:

[0025] Use a laser thickness gauge to obtain the spraying thickness data on the surface of the workpiece to form a thickness matrix: T(x1, y1), where (x1, y1) represents the pixel coordinates on the surface of the workpiece, and T(x1, y1) represents the spraying thickness at the point (x1, y1);

[0026] Calculate the global thickness uniformity abnormality: where Kglobal represents the global thickness uniformity abnormality, represents the global average thickness, H and K respectively represent the width and length of the thickness matrix;

[0027] Use dilation and erosion operations to calculate the spraying thickness gradient: Gmor(x1, y1) = Tdil(x1, y1) - Tero(x1, y1), where Gmor(x1, y1) represents the spraying thickness gradient, Tdil(x1, y1) represents the dilation operation, and Tero(x1, y1) represents the erosion operation. The implementation methods of the dilation and erosion operations are as follows: where SS represents the neighborhood region with the coordinate (x1, y1) as the center and radius RR, and (x2, y2) represents the coordinates within the neighborhood region;

[0028] Calculate the abnormal coefficient of spraying thickness uniformity: where KT represents the abnormal coefficient of spraying thickness uniformity;

[0029] Compare the abnormal coefficient of spraying thickness uniformity with a preset threshold of the abnormal coefficient of spraying thickness uniformity. If the abnormal coefficient of spraying thickness uniformity is greater than the threshold of the abnormal coefficient of spraying thickness uniformity, it indicates that there is an abnormal fluctuation in the coating thickness distribution.

[0030] In a preferred embodiment, the acquisition logic of the abnormal response coefficient of spraying is as follows:

[0031] Mark the abnormal spray color difference and abnormal fluctuation of the coating thickness distribution in the spraying area as abnormal events, and record the time when the event occurs whenever an abnormal event occurs;

[0032] Calculate the system feedback delay: tdel = max(tadj - teven, tmin), where tdel represents the system feedback delay, tadj represents the time point when the system adjusts the spraying parameters, teven represents the time when the abnormal event occurs, and tmin represents the minimum feedback time threshold;

[0033] Calculate the spray abnormality response coefficient: where Kres represents the spray abnormality response coefficient, ρres represents the feedback rate, and tdel b represents the system feedback delay calculated when the b-th abnormal event occurs, b = {1, 2,..., B}, and B is a positive integer.

[0034] In a preferred embodiment, construct a spray quality detection model based on the spray color difference abnormality coefficient, the spray thickness uniformity abnormality coefficient, and the spray abnormality response coefficient, and output the spray quality detection index sqi. The formula on which the model is based is as follows: sqi = w1 * ηcolor + w2 * KT + w3 * Kres, where w1, w2, and w3 respectively represent the preset proportionality coefficients of the spray color difference abnormality coefficient, the spray thickness uniformity abnormality coefficient, and the spray abnormality response coefficient, and w1, w2, and w3 are all greater than 0.

[0035] In a preferred embodiment, compare the spray quality detection index with the preset spray quality detection index threshold to perform quality detection on the spray state, specifically as follows:

[0036] If the spray quality detection index is greater than the spray quality detection index threshold, generate a control signal;

[0037] If the spray quality detection index is less than or equal to the spray quality detection index threshold, there is no need to generate a control signal.

[0038] In a preferred embodiment, adjust the spraying parameters according to the spray quality detection index, specifically as follows: where represents the q-th spraying parameter after adjustment, represents the q-th spraying parameter before adjustment, and sqi z represents the spray quality detection index threshold, represents the adjustment constant.

[0039] In a preferred embodiment, an automatic spraying method includes the following steps: cleaning and decontaminating the surface of the workpiece; establishing a 3D model of the workpiece through 3D scanning; extracting workpiece parameters, where the workpiece parameters include but are not limited to dimensions, shape distribution, and material distribution; searching for a spraying path on the surface of the workpiece 3D model according to the workpiece parameters to obtain a spraying path; optimizing the spraying path by combining with a genetic algorithm; controlling a spray gun to spray the target workpiece according to the spraying path, simulating the spraying process and obtaining spraying quality information; constructing a spraying quality detection model to detect the quality of the spraying state; and performing closed-loop control on the spraying simulation according to the quality detection result of the spraying state.

[0040] Technical effects and advantages of the present invention:

[0041] 1. By constructing an automatic electrostatic spraying control system integrating workpiece pre-treatment, intelligent spraying planning, electrostatic spraying execution, and closed-loop control, the present invention realizes the whole-process automated management from workpiece surface cleaning, 3D modeling, intelligent optimization of spraying paths, to real-time simulation of the spraying process, global quality detection, and closed-loop feedback regulation, effectively improving the spraying quality and production efficiency. Using 3D scanning technology to accurately obtain workpiece size, shape, and material information, and through spraying path search and optimization based on a genetic algorithm, the optimal planning of spraying trajectories is achieved; in the spraying execution stage, by simulating and using global sensors to collect coating thickness and color difference information in real time, a spraying quality detection model is constructed to realize the immediate judgment of the spraying state; the closed-loop control module quickly generates a regulation signal according to the detection result and dynamically adjusts the spraying parameters, so as to achieve real-time compensation and optimization when an abnormality occurs, prevent defect accumulation, ensure stable and consistent product quality, and at the same time reduce paint waste and environmental pollution. The present invention greatly improves the intelligent and automated level of the spraying process, achieving an overall improvement in production efficiency, quality control, and environmental protection benefits. Description of the drawings

[0042] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings;

[0043] Figure 1 It is a flowchart of the method of Embodiment 1 of the present invention;

[0044] Figure 2 It is a flowchart of the system of Embodiment 2 of the present invention. Detailed implementation manners

[0045] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0046] Example 1: Figure 1 An automatic electrostatic spraying control system of the present invention is provided, including the following modules: a workpiece pretreatment module, an intelligent spraying planning module, an electrostatic spraying execution module, and a closed-loop control module;

[0047] The workpiece pretreatment module is used to clean and decontaminate the surface of the workpiece, establish a 3D model of the workpiece through 3D scanning, and extract workpiece parameters, where the workpiece parameters include but are not limited to dimensions, shape distribution, and material distribution;

[0048] The intelligent spraying planning module is used to search for a spraying path on the surface of the workpiece 3D model according to the workpiece parameters, obtain the spraying path, and optimize the path by combining the genetic algorithm;

[0049] The electrostatic spraying execution module is used to control the spray gun to spray the target workpiece according to the spraying path, simulate the spraying, obtain spraying quality information, construct a spraying quality detection model, and detect the quality of the spraying state;

[0050] The closed-loop control module is used to perform closed-loop control on the spraying simulation according to the quality detection result of the spraying state;

[0051] The workpiece pretreatment module is used to clean and decontaminate the surface of the workpiece, establish a 3D model of the workpiece through 3D scanning, and extract workpiece parameters, where the workpiece parameters include but are not limited to dimensions, shape distribution, and material distribution;

[0052] High-pressure air flow (≥0.5 MPa) is used and combined with an electrostatic adsorption device to remove large-particle dust on the surface of the workpiece. The workpiece is immersed in an ultrasonic cleaning tank, and oil stains and microparticles are removed by bubble impact, and then dried to obtain a clean and decontaminated workpiece;

[0053] Laser scanning is used to perform 3D scanning on the workpiece to collect workpiece surface point cloud data: P(x, y, z) = {p i} = {p1, p2,..., p I}, where p i (x i , y i , z i ) are discrete points on the surface of the workpiece. Based on the obtained point cloud data, Poisson reconstruction method is used to perform 3D reconstruction on the workpiece to obtain a workpiece 3D model;

[0054] In an alternative example, Poisson reconstruction method is used to perform 3D reconstruction on the workpiece, specifically as follows:

[0055] For each discrete point, a neighborhood point set is obtained within the search radius BJ, and the covariance matrix XF is calculated according to the discrete points in the neighborhood point set; where p jdenotes the discrete points within the neighborhood point set, denotes the mean value of the neighborhood point set, denotes the transpose of, where j = {1, 2,..., J} and J is a positive integer; perform eigenvalue decomposition on the covariance matrix XF, and denote the eigenvector corresponding to the minimum eigenvalue as the normal vector fx of the discrete points i ;

[0056] Embed the point cloud data into an octree structure to construct an octree. Consider the point cloud as a divergence field source and solve the Poisson equation: where denotes the Laplace operator of the scalar field χ, denotes the divergence of the point cloud normal vector field ; Discretize the Poisson equation at the octree nodes, extract the isosurface of χ = 0, and generate a triangular mesh on the workpiece surface to obtain the 3D model of the workpiece;

[0057] It should be noted that the above formulas are all dimensionless and take their numerical values for calculation. Common methods for removing dimensions include Min - Max normalization, Z - Score standardization, etc., which will not be elaborated here; d1, d2, and d3 are set according to the actual situation;

[0058] The intelligent spraying planning module is used to search for the spraying path on the surface of the workpiece 3D model according to the workpiece parameters and obtain the spraying path. Combine the genetic algorithm to optimize the spraying path;

[0059] Take each triangular mesh point on the workpiece surface as a candidate point for the spray gun path, set the starting point and ending point of the spraying path, and traverse the workpiece surface based on the spraying path cost function to obtain the initial spraying path with the minimum value of the spraying path cost function. The spraying path cost function is: F(L) = G(L)+H(L), where G(L) represents the known path cost from the starting point to the current point, and H(L) represents the estimated shortest path cost from the current point to the ending point;

[0060] The described path cost is obtained by weighted summation of the spraying uniformity cost, spraying time cost, and spraying direction change cost;

[0061] It should be noted that the spraying uniformity cost is quantified by the difference between the spraying thickness and the target thickness, the spraying time cost is quantified by the spraying time, and the spraying direction change cost is quantified by the change value of the spraying angle of the path;

[0062] Preset spraying parameters for each initial spraying path. The described spraying parameters include electrostatic voltage, spraying angle, and spray gun flow rate;

[0063] Combine the genetic algorithm to optimize the spraying path, specifically as follows:

[0064] A1: Take each obtained initial spraying path as an individual spraying path;

[0065] A2: Calculate the fitness: where FS represents the fitness, Coverage represents the coverage, Cov1 represents the covered area, Cov2 represents the uncovered area, Time represents the spraying time, and Waste represents the paint waste;

[0066] A3: Select the spraying path and retain the path with the maximum fitness value;

[0067] A4: Perform a crossover operation on the spraying path to exchange part of the spraying trajectory;

[0068] A5: Perform a mutation operation on the spraying path to randomly adjust the spraying path points;

[0069] A6: Preset the iteration time and repeat A2, A3, A4, and A5 for iterative optimization;

[0070] Finally, obtain the optimized spraying path;

[0071] It should be noted that the above formulas are all dimensionless and take their numerical values for calculation. Commonly used methods for removing dimensions include Min-Max normalization, Z-Score standardization, etc., which will not be elaborated here; they are set according to the actual situation.

[0072] The electrostatic spraying execution module is used to control the spray gun to perform spraying simulation on the target workpiece according to the spraying path, obtain spraying quality information, construct a spraying quality detection model, and perform quality detection on the spraying state;

[0073] The said spraying quality information includes spraying color difference abnormal coefficient, spraying thickness uniformity abnormal coefficient, and spraying abnormal response coefficient;

[0074] In the present invention, the spraying color difference abnormal coefficient is used to measure the uniformity and consistency of color distribution during the spraying process, and its value reflects the deviation degree between the coating color and the expected target color. When the spraying color difference abnormal coefficient is large, it indicates that there are obvious color deviations or local color unevenness in the coating, which may be caused by improper parameter control, unreasonable spraying path, or environmental factor interference during the spraying process; while when this coefficient is small, it indicates that the color distribution of the coating during the spraying process is relatively uniform and basically meets the design requirements. Based on the spraying color difference abnormal coefficient for quality detection, the spraying state can be evaluated in real time and accurately, so as to dynamically optimize and adjust the spraying state, effectively improve the spraying quality, reduce the defect rate, and realize the intelligent control and high-quality production of the automatic spraying system.

[0075] The acquisition logic of the spraying color difference abnormal coefficient is as follows:

[0076] Use an RGB camera to collect the image tx(x, y) of the spraying area, and perform a fast Fourier transform on the image channels of the spraying area image tx(x, y): Where F(u, v) is the result of the Fourier transform, (u, v) represents the frequency domain coordinates, M and N respectively represent the width and height of the spraying area image, and sx represents the imaginary unit; Amplitude spectrum calculation: A(u, v) = log(1 + |F(u, v)|), where A(u, v) is the amplitude spectrum; Calculate the total energy of the amplitude spectrum: Where Etotal represents the total energy of the amplitude spectrum; Calculate the distance from the frequency component to the center of the frequency spectrum: Where DJ(u, v) represents the distance from the frequency component to the center of the frequency spectrum, represents the center of the frequency spectrum; Compare the distance from the frequency component to the center of the frequency spectrum with a preset high-frequency radius threshold. If the distance from the frequency component to the center of the frequency spectrum is greater than the high-frequency radius threshold, it means that the point (u, v) belongs to the high-frequency region;

[0077] Calculate the spraying color difference abnormal coefficient: Where ηcolor represents the spraying color difference abnormal coefficient, and HighFreq represents the high-frequency region;

[0078] It should be noted that the above formulas are all dimensionless and take their numerical values for calculation. Common methods for removing dimensions include Min-Max normalization, Z-Score standardization, etc.;

[0079] Compare the spraying color difference abnormal coefficient with a preset spraying color difference abnormal coefficient threshold. If the spraying color difference abnormal coefficient is greater than the spraying color difference abnormal coefficient threshold, it means that there is an abnormality in the spraying color difference of the spraying area;

[0080] In the present invention, the spraying thickness uniformity abnormal coefficient is used to comprehensively measure the uniformity of the coating thickness during the spraying process, and its value reflects the fluctuation degree of the coating thickness distribution. A larger spraying thickness uniformity abnormal coefficient indicates that there is a significant non-uniformity in the coating thickness, indicating that there may be problems such as over-thickness or under-thickness, overlapping spraying, or missed spraying in some areas, thus affecting the adhesion and appearance quality of the final product; while a smaller spraying thickness uniformity abnormal coefficient indicates that the coating thickness distribution is relatively uniform, indicating that the spraying process is stable and the parameter control is appropriate, which can effectively ensure the consistency of product quality. Based on the spraying thickness uniformity abnormal coefficient for spraying state quality detection, abnormal situations during the spraying process can be identified and corrected in a timely manner, so as to achieve the beneficial effects of automatically adjusting spraying parameters, optimizing the coating thickness distribution, improving production efficiency, and reducing material waste.

[0081] The acquisition logic of the spraying thickness uniformity abnormal coefficient is as follows:

[0082] The laser thickness gauge is used to obtain the spray coating thickness data on the surface of the workpiece, forming a thickness matrix: T(x1, y1), where (x1, y1) represents the pixel coordinates on the surface of the workpiece, and T(x1, y1) represents the spray coating thickness at the point (x1, y1);

[0083] Calculate the global thickness uniformity anomaly degree: where Kglobal represents the global thickness uniformity anomaly degree, represents the global average thickness, H and K respectively represent the width and length of the thickness matrix;

[0084] The global thickness uniformity anomaly degree is used to provide the overall spray coating uniformity information;

[0085] The dilation and erosion operations are used to calculate the spray coating thickness gradient: Gmor(x1, y1) = Tdil(x1, y1) - Tero(x1, y1), where Gmor(x1, y1) represents the spray coating thickness gradient, Tdil(x1, y1) represents the dilation operation, and Tero(x1, y1) represents the erosion operation. The implementation methods of the dilation and erosion operations are as follows: where SS represents the neighborhood area with the coordinate (x1, y1) as the center and radius RR, and (x2, y2) represents the coordinates within the neighborhood area;

[0086] The spray coating thickness gradient reflects the local non-uniformity degree;

[0087] Calculate the spray coating thickness uniformity anomaly coefficient: where KT represents the spray coating thickness uniformity anomaly coefficient;

[0088] It should be noted that the above formulas are all dimensionless and take their numerical values for calculation. Common methods for removing dimensions include Min-Max normalization, Z-Score standardization, etc.;

[0089] It should be noted that by the denominator dynamically scale Kglobal, so that the global anomaly degree is weighted down where the local gradient is large, strengthening the influence of the local anomaly area.

[0090] Compare the spray coating thickness uniformity anomaly coefficient with the preset spray coating thickness uniformity anomaly coefficient threshold. If the spray coating thickness uniformity anomaly coefficient is greater than the spray coating thickness uniformity anomaly coefficient threshold, it indicates that there are abnormal fluctuations in the coating thickness distribution;

[0091] In the present invention, the spray abnormality response coefficient is used to measure the sensitivity of the system to abnormal responses when there are abnormalities in the spray color difference in the spray area or abnormal fluctuations in the coating thickness distribution; a larger spray abnormality response coefficient indicates that the system is highly sensitive to abnormal changes in the spray state, can quickly capture abnormal situations of color difference and thickness fluctuations, thus indicating that the spray state has deviated significantly from the ideal state, which may lead to a decline in product quality; while a smaller spray abnormality response coefficient indicates that the system has a weak response to abnormalities, indicating that the spray process is relatively stable, and the color difference and thickness fluctuations are within the controllable range, thus ensuring the consistency and overall quality of the product. Based on the spray abnormality response coefficient, quality inspection of the spray state can be carried out to timely detect and adjust spray process parameters, reduce the rejection rate, improve production efficiency, and achieve high-precision control and intelligent management of the spray process.

[0092] The acquisition logic of the spray abnormality response coefficient is as follows:

[0093] Mark the abnormalities in the spray color difference in the spray area and the abnormal fluctuations in the coating thickness distribution as abnormal events, and record the time when each abnormal event occurs.

[0094] Calculate the system feedback delay: tdel = max(tadj - teven, tmin), where tdel represents the system feedback delay, tadj represents the time point when the system adjusts the spray parameters, teven represents the time when the abnormal event occurs, and tmin represents the minimum feedback time threshold.

[0095] Calculate the spray abnormality response coefficient: where Kres represents the spray abnormality response coefficient, ρres represents the feedback rate, tdel b represents the system feedback delay calculated when the b-th abnormal event occurs, b = {1, 2,..., B}, and B is a positive integer.

[0096] It should be noted that the above formulas are all calculated by taking the numerical values after dimensionless processing. Common methods for removing dimensions include Min-Max normalization, Z-Score standardization, etc.

[0097] Construct a spray quality inspection model based on the spray color difference abnormality coefficient, the spray thickness uniformity abnormality coefficient, and the spray abnormality response coefficient, and output the spray quality inspection index sqi. The formula on which the model is based is as follows: sqi = w1 * ηcolor + w2 * KT + w3 * Kres, where w1, w2, and w3 respectively represent the preset proportional coefficients of the spray color difference abnormality coefficient, the spray thickness uniformity abnormality coefficient, and the spray abnormality response coefficient, and w1, w2, and w3 are all greater than 0.

[0098] It should be noted that the above formulas are all calculated by removing the dimension and taking their numerical values. Common methods for removing dimensions include Min-Max normalization, Z-Score standardization, etc., which will not be elaborated here; w1, w2, and w3 are set according to the actual situation. For example, the expert weighting method is adopted, that is, experts in relevant fields are invited to determine the preset proportional coefficients of each index through professional opinion surveys and comprehensive evaluations. For example, w1, w2, and w3 can be 0.3, 0.4, and 0.3;

[0099] As can be seen from the above calculation expressions, the larger the abnormal coefficient of spray color difference, the larger the abnormal coefficient of spray thickness uniformity, and the larger the abnormal response coefficient of spray, the larger the spray quality detection index, indicating that there are significant abnormalities in the spraying process and the spray quality is low. On the contrary, the smaller the abnormal coefficient of spray color difference, the smaller the abnormal coefficient of spray thickness uniformity, and the smaller the abnormal response coefficient of spray, the smaller the spray quality detection index, indicating that the spray quality is relatively stable and meets the process requirements;

[0100] Compare the spray quality detection index with the preset spray quality detection index threshold to conduct quality detection on the spray state, as follows:

[0101] If the spray quality detection index is greater than the spray quality detection index threshold, it indicates that there are obvious abnormalities in the spraying process and the overall spray quality is poor. It is necessary to adjust the spray process parameters in time or take remedial measures to improve the spray effect and generate a control signal;

[0102] If the spray quality detection index is less than or equal to the spray quality detection index threshold, it indicates that the spray state is within the normal range, the process is stable and the product quality meets the requirements, and there is no need to generate a control signal;

[0103] The closed-loop control module is used to perform closed-loop control on the spray simulation according to the quality detection results of the spray state;

[0104] When a control signal is generated, the spray parameters are adjusted according to the spray quality detection index, as follows: where represents the q-th spray parameter after regulation, represents the q-th spray parameter before regulation, sqi z represents the spray quality detection index threshold, represents the adjustment constant, which is used to control the influence of the spray quality detection index on the spray parameters;

[0105] It should be noted that the above formulas are all calculated by removing the dimension and taking their numerical values. Common methods for removing dimensions include Min-Max normalization, Z-Score standardization, etc., which will not be elaborated here;

[0106] The present invention realizes the full - process automatic management from workpiece surface cleaning, 3D modeling, intelligent optimization of spraying paths, to real - time simulation of the spraying process, global quality inspection, and closed - loop feedback regulation by constructing an automatic electrostatic spraying control system integrating workpiece pre - treatment, intelligent spraying planning, electrostatic spraying execution, and closed - loop control. It effectively improves the spraying quality and production efficiency. The 3D scanning technology is used to accurately obtain the size, shape, and material information of the workpiece. Through the spraying path search and optimization based on the genetic algorithm, the optimal planning of the spraying trajectory is realized. During the spraying execution stage, the coating thickness and color difference information are collected in real - time through simulation and global sensors, and a spraying quality detection model is constructed to realize the immediate judgment of the spraying state. The closed - loop control module quickly generates regulation signals according to the detection results and dynamically adjusts the spraying parameters, so as to achieve real - time compensation and optimization when abnormalities occur, prevent defect accumulation, ensure stable and consistent product quality, and at the same time reduce paint waste and environmental pollution. The present invention greatly improves the intelligent and automatic level of the spraying process, and realizes the comprehensive improvement of production efficiency, quality control, and environmental protection benefits.

[0107] Embodiment 2: This embodiment introduces an automatic spraying method. As Figure 2 shown, it includes the following steps: cleaning and decontaminating the surface of the workpiece; establishing a 3D model of the workpiece through 3D scanning; extracting workpiece parameters, where the workpiece parameters include but are not limited to size, shape distribution, and material distribution; searching for spraying paths on the surface of the 3D model of the workpiece according to the workpiece parameters to obtain spraying paths; optimizing the spraying paths in combination with the genetic algorithm; controlling the spray gun to spray the target workpiece according to the spraying paths, simulating and obtaining spraying quality information, constructing a spraying quality detection model, and performing quality detection on the spraying state; performing closed - loop control on the spraying simulation according to the quality detection results of the spraying state.

[0108] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0109] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more sets of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0110] It should be understood that in various embodiments of the present application, the order numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0111] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described system and method can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0112] In several embodiments provided in the present application, it should be understood that the disclosed system and method can be implemented in other ways.

[0113] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An automatic electrostatic spraying control system, characterized in that: It includes the following modules: workpiece pre - treatment module, intelligent spraying planning module, electrostatic spraying execution module, and closed - loop control module; The workpiece pre - treatment module is used to clean and decontaminate the surface of the workpiece, establish a 3D model of the workpiece through 3D scanning, and extract workpiece parameters. The workpiece parameters include, but are not limited to, size, shape distribution, and material distribution; The intelligent spraying planning module is used to search for spraying paths on the surface of the workpiece 3D model according to the workpiece parameters, obtain the spraying paths, and optimize the spraying paths by combining the genetic algorithm; The electrostatic spraying execution module is used to control the spray gun to spray the target workpiece according to the spraying path, simulate the spraying process, obtain spraying quality information, construct a spraying quality detection model, and detect the quality of the spraying state; The closed - loop control module is used to perform closed - loop control on the spraying simulation according to the quality detection results of the spraying state.

2. The automatic electrostatic spraying control system according to claim 1, wherein: The path optimization of the spraying path by combining the genetic algorithm is as follows: A1: Each obtained initial spraying path is regarded as an individual of the spraying path; A2: Calculate fitness: where FS represents fitness, Coverage represents coverage, Cov1 represents the covered area, Cov2 represents the uncovered area, Time represents the spraying time, and Waste represents the amount of paint waste; A3: Select the spraying path and retain the path with the largest fitness value; A4: Perform a crossover operation on the spraying path to exchange part of the spraying trajectory; A5: Perform a mutation operation on the spraying path to randomly adjust the spraying path points; A6: Preset the iteration time, and repeat A2, A3, A4, and A5 for iterative optimization; Finally, the optimized spraying path is obtained.

3. The automatic electrostatic spraying control system according to claim 1, wherein: The spraying quality information includes spraying color difference abnormal coefficient, spraying thickness uniformity abnormal coefficient, and spraying abnormal response coefficient.

4. An automatic electrostatic spraying control system according to claim 3, characterized in that: The acquisition logic of the spraying color difference abnormal coefficient is as follows: Use an RGB camera to collect the image tx(x, y) of the spraying area, and perform a fast Fourier transform on the image channels of the spraying area image tx(x, y): Where F(u, v) is the result of the Fourier transform, (u, v) represents the frequency domain coordinates, M and N respectively represent the width and height of the spraying area image, and sx represents the imaginary unit; amplitude spectrum calculation: A(u, v) = log(1 + |F(u, v)|), where A(u, v) is the amplitude spectrum; calculate the total energy of the amplitude spectrum: Where Etotal represents the total energy of the amplitude spectrum; calculate the distance from the frequency component to the center of the spectrum: Where DJ(u, v) represents the distance from the frequency component to the center of the spectrum, represents the center of the spectrum; compare the distance from the frequency component to the center of the spectrum with a preset high-frequency radius threshold. If the distance from the frequency component to the center of the spectrum is greater than the high-frequency radius threshold, it means that the point (u, v) belongs to the high-frequency region; Calculate the abnormal coefficient of spraying color difference: where ηcolor represents the abnormal coefficient of spraying color difference, and HighFreq represents the high-frequency region; Compare the spraying color difference abnormal coefficient with the preset spraying color difference abnormal coefficient threshold. If the spraying color difference abnormal coefficient is greater than the spraying color difference abnormal coefficient threshold, it indicates that there is an abnormality in the spraying color difference of the spraying area.

5. An automatic electrostatic spraying control system according to claim 3, characterized in that: The acquisition logic of the spraying thickness uniformity abnormal coefficient is as follows: Use a laser thickness gauge to obtain the spraying thickness data on the surface of the workpiece to form a thickness matrix: T(x1,y1), where (x1,y1) represents the pixel coordinates on the surface of the workpiece, and T(x1,y1) represents the spraying thickness at point (x1,y1); Calculate the global thickness uniformity anomaly: where Kglobal represents the global thickness uniformity anomaly, represents the global average thickness, H and K respectively represent the width and length of the thickness matrix; The spraying thickness gradient is calculated using dilation and erosion operations: Gmor(x1, y1) = Tdil(x1, y1) - Tero(x1, y1), where Gmor(x1, y1) represents the spraying thickness gradient, Tdil(x1, y1) represents the dilation operation, and Tero(x1, y1) represents the erosion operation. The specific implementation methods of the dilation and erosion operations are as follows: where SS represents the neighborhood area with the coordinate (x1, y1) as the center and radius RR, and (x2, y2) represents the coordinates within the neighborhood area; Calculate the abnormal coefficient of spray coating thickness uniformity: where KT represents the abnormal coefficient of spray coating thickness uniformity; Compare the spraying thickness uniformity abnormal coefficient with the preset spraying thickness uniformity abnormal coefficient threshold. If the spraying thickness uniformity abnormal coefficient is greater than the spraying thickness uniformity abnormal coefficient threshold, it indicates that there is an abnormal fluctuation in the coating thickness distribution.

6. The automatic electrostatic spraying control system according to claim 3, characterized in that: The acquisition logic of the spraying abnormal response coefficient is as follows: Mark the abnormal spraying color difference in the spraying area and the abnormal fluctuation in the coating thickness distribution as abnormal events. Whenever an abnormal event occurs, record the time when the event occurs; Calculate the system feedback delay: tdel = max(tadj - teven, tmin), where tdel represents the system feedback delay, tadj represents the time point when the system adjusts the spraying parameters, teven represents the time when the abnormal event occurs, and tmin represents the minimum feedback time threshold; Calculate the spray anomaly response coefficient: Where Kres represents the spray anomaly response coefficient, ρres represents the feedback rate, and tdel b represents the system feedback delay calculated at the b-th occurrence of an anomaly event, where b = {1, 2,..., B} and B is a positive integer.

7. An automatic electrostatic spraying control system according to claim 3, characterized in that: A spray quality detection model is constructed based on the spray color difference abnormal coefficient, the spray thickness uniformity abnormal coefficient, and the spray abnormal response coefficient, and the spray quality detection index sqi is output. The formula on which the model is based is as follows: sqi = w1 * ηcolor + w2 * KT + w3 * Kres, where w1, w2, and w3 respectively represent the preset proportional coefficients of the spray color difference abnormal coefficient, the spray thickness uniformity abnormal coefficient, and the spray abnormal response coefficient, and w1, w2, and w3 are all greater than 0.

8. An automatic electrostatic spraying control system according to claim 7, characterized in that: Compare the spray quality detection index with the preset spray quality detection index threshold to perform quality detection on the spray state, specifically as follows: If the spray quality detection index is greater than the spray quality detection index threshold, a control signal is generated; If the spray quality detection index is less than or equal to the spray quality detection index threshold, there is no need to generate a control signal.

9. The automatic electrostatic spraying control system according to claim 8, characterized in that: When generating a control signal, the spraying parameters are adjusted according to the spraying quality detection index, specifically as follows: Among them represents the q-th spraying parameter after adjustment, represents the q-th spraying parameter before adjustment, sqi z represents the threshold of the spraying quality detection index, and θ represents the adjustment constant.

10. An automatic spraying method for implementing an automatic electrostatic spraying control system according to any one of claims 1-9, characterized in that: It includes the following steps: cleaning and decontaminating the surface of the workpiece, establishing a 3D model of the workpiece through 3D scanning, and extracting workpiece parameters. The workpiece parameters include, but are not limited to, dimensions, shape distribution, and material distribution; searching for a spray path on the surface of the workpiece 3D model according to the workpiece parameters to obtain a spray path, and optimizing the spray path in combination with a genetic algorithm; controlling the spray gun to perform spray simulation on the target workpiece according to the spray path and obtaining spray quality information, constructing a spray quality detection model to perform quality detection on the spray state; performing closed-loop control on the spray simulation according to the quality detection result of the spray state.

Images