Intelligent surface spraying method and device based on coating quality and spraying robot

Abstract

The invention relates to the technical field of surface spraying, in particular to an intelligent surface spraying method and device based on coating quality and a spraying robot. The intelligent surface spraying method based on the coating quality comprises the steps that the coating actually-measured thicknesses of a plurality of detection points in a spraying width area are monitored in real time, and an actually-measured thickness distribution field is obtained; according to the actually measured thickness distribution field and the target thickness of the coating, a thickness deviation mean value is calculated, and whether the thickness deviation mean value is out of an allowable range or not is judged; if yes, calculating a thickness standard deviation according to the actually measured thickness distribution field; calculating a speed correction amount according to the thickness deviation mean value and the speed correction coefficient; and according to the thickness deviation mean value, the thickness standard deviation and the spraying width correction coefficient, the spraying width correction amount is calculated. According to the intelligent surface spraying method and device based on the coating quality and the spraying robot, the product surface coating spraying effect standard reaching rate is high, the secondary machining number can be greatly reduced, and the productivity is high.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of surface spraying technology, in particular to an intelligent surface spraying method and device based on coating quality and a spraying robot. BACKGROUND

[0002] In the field of manufacturing industrial products such as automobiles and ships, the quality of the coating on the surface of a workpiece directly affects the protection and aesthetics of the product.

[0003] Existing spraying robots mainly use fixed trajectories and constant spraying widths for spraying operations, and rely on manual experience to set parameters. This static trajectory control method has low intelligence and flexibility, and cannot adjust control instructions according to differences in workpiece surfaces and spraying environments, which can easily result in uneven coating thickness, missed spraying, or over-spraying, leading to poor spraying effects on the surface coating of the product, especially in the case of complex curvature on the surface of the workpiece, where spraying width distortion and thickness deviation are more prominent. In addition, if the spraying effect is found to be substandard upon detection, secondary processing is required, resulting in low productivity. SUMMARY

[0004] The present application aims to provide an intelligent surface spraying method and device based on coating quality and a spraying robot to improve the technical problems of poor spraying effect and low productivity of existing spraying robots.

[0005] The intelligent surface spraying method based on coating quality provided by the present application comprises: real-time monitoring of the actual coating thickness of a plurality of detection points in the spraying area to obtain an actual thickness distribution field; calculating the mean thickness deviation based on the actual thickness distribution field and the target thickness of the coating, and determining whether the mean thickness deviation is outside the allowable range; If yes, then calculating the thickness standard deviation based on the actual thickness distribution field, calculating the speed correction amount based on the mean thickness deviation and the speed correction coefficient, and calculating the spraying width correction amount based on the mean thickness deviation, the thickness standard deviation, and the spraying width correction coefficient; wherein the speed correction amount is positively correlated with the mean thickness deviation, and the spraying width correction amount is positively correlated with the thickness deviation and negatively correlated with the thickness standard deviation.

[0006] As an implementable manner, the method further comprises: If the posture adjustment condition is met, then calculating the thickness deviation distribution field based on the actual thickness distribution field and the target thickness; calculating the normal micro-shift vector based on the thickness deviation distribution field and the trajectory fine-tuning sensitivity; calculating the posture correction vector based on the normal micro-shift vector and the posture correction coefficient.

[0007] As one possible implementation, the attitude adjustment conditions include any one of the following conditions: Condition A: After several consecutive adjustments to the moving speed and spray width of the spray gun, the average thickness deviation is still outside the allowable deviation range; Condition B: During the continuous process of adjusting the moving speed and the spray width several times, the moving speed is maintained at the speed threshold or the spray width is maintained at the spray width threshold throughout the entire process.

[0008] As one possible implementation method, the formula for calculating the normal micro-shift vector is: ,in, The thickness deviation distribution field, Fine-tune the sensitivity of the trajectory; The formula for calculating the attitude correction vector is: ,in, The attitude correction coefficient is denoted as .

[0009] As one possible implementation method, the formula for calculating the average thickness deviation is: ,in, This is the set of effective detection points within the spray area. The number of effective detection points within the spray area. For testing points The measured thickness at that location The target thickness; The formula for calculating the speed correction is: ,in, This is the speed correction coefficient.

[0010] As one possible implementation method, the formula for calculating the thickness standard deviation is: ,in, The mean measured thickness of the coating within the sprayed area; The formula for calculating the spray width correction amount is: ,in, is the correction factor for the spray width.

[0011] As one possible implementation, the method further includes: Record the monitoring and control data for each spraying process to form a dataset: After a certain number of spraying operations are completed, the spraying quality index is calculated based on the dataset. Based on the coating quality index, the control parameter vector is updated using an iterative optimization method; wherein, the control parameter vector includes the speed correction coefficient, the spray width correction coefficient, and the attitude correction coefficient; The updated control parameter vector is stored in a curvature-parameter mapping table as an initial setting for the next spraying process.

[0012] As an implementable manner, the data set is: , wherein, is the measured thickness distribution field in the i-th spraying process, is a control instruction in the i-th spraying process, the control instruction including the moving speed, the spraying width and the posture, is the thickness deviation distribution field in the i-th spraying process.

[0013] The update formula of the control parameter vector is: , wherein, is a cost function targeting the coating quality index.

[0014] The intelligent surface spraying device based on coating quality provided by the application comprises: a monitoring module for monitoring the measured thickness of the coating at multiple detection points in the spraying area in real time to obtain a measured thickness distribution field; a judging module for calculating a thickness deviation mean value according to the measured thickness distribution field and the target thickness of the coating and judging whether the thickness deviation mean value is outside an allowable range; a calculating module for, when the judging result of the judging module is yes, calculating a thickness standard deviation according to the measured thickness distribution field, calculating a speed correction amount according to the thickness deviation mean value and a speed correction coefficient, calculating a spraying width correction amount according to the thickness deviation mean value, the thickness standard deviation and a spraying width correction coefficient, wherein the speed correction amount is positively correlated with the thickness deviation mean value, and the spraying width correction amount is positively correlated with the thickness deviation and negatively correlated with the thickness standard deviation.

[0015] The spraying robot provided by the application comprises a spraying gun, a coating thickness monitor, a computer readable storage medium storing a computer program and a processor, the coating thickness monitor is fixedly connected with the spraying gun and is used for monitoring the measured thickness of the coating at multiple detection points in the spraying area, the coating thickness monitor and the spraying gun are both electrically connected with the processor, and the computer program is read and run by the processor to implement the above method.

[0016] Compared with the prior art, the application has the following beneficial effects: The intelligent surface spraying method, device and spraying robot based on coating quality provided by the application directly introduce coating quality feedback into spraying control, and adjust control instructions (moving speed and amplitude of the spray gun) in real time according to the sensing result, realize the effect of adjusting while spraying, realize dynamic control closed loop, optimize control instructions in the spraying process, improve coating quality, flexibly adapt to differences in workpiece surface and differences in spraying environment, and the problems of uneven coating thickness, missing spraying or over-spraying are not prone to occur, the product surface coating spraying effect compliance rate is high, the number of secondary processing can be greatly reduced, and the production capacity is improved. It is especially suitable for workpiece surfaces with complex curvature, and can significantly improve the problems of large spraying amplitude distortion and thickness deviation. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, below the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the provided drawings.

[0018] Figure 1 The schematic flow chart of the intelligent surface spraying method based on coating quality provided by the application is provided. Figure 2 The structural schematic diagram of the intelligent surface spraying device based on coating quality provided by the application is provided. DETAILED DESCRIPTION

[0019] Related technology one, geometric scanning driving route: obtain the workpiece surface topography through 3D scanning, and optimize the track combined with modeling. This method optimizes the track through geometric coverage, does not consider the coating quality (thickness, uniformity), and cannot guarantee the closed loop consistency of the spraying result, and the spraying stability is insufficient.

[0020] Related technology two, spray head array regulation route: improve the overall uniformity through the spatial layout, coupling interference and parameter joint regulation of the spray head array. This method is limited in the multi-spray head scene, and also does not consider the coating quality, and the local quality driving compensation ability of the single spray head on the complex curved surface is insufficient, and the closed loop consistency of the spraying result cannot be guaranteed.

[0021] The application provides an intelligent surface spraying method based on coating quality, which realizes dynamic compensation of spraying track and parameters by real-time sensing of coating thickness and uniformity, and realizes closed loop control of spraying quality. It has strong real-time performance, can adapt to complex surfaces, has strong spraying stability, needs less secondary processing, and has high production capacity.

[0022] The technical solutions of the present application will be described clearly and completely below in conjunction with the drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0023] The present application will be described in further detail below through specific examples and in conjunction with the drawings.

[0024] Figure 1 An exemplary flow chart of an intelligent surface spraying method based on coating quality is provided for an embodiment of the present application, which comprises: S102, real-time monitoring of the measured thickness of the coating at a plurality of detection points in the spraying area to obtain a measured thickness distribution field; S104, calculating the mean thickness deviation according to the measured thickness distribution field and the target thickness of the coating, and determining whether the mean thickness deviation is outside the allowed range; The mean thickness deviation can reflect whether the coating in the current spraying area is too thin or too thick and the degree of deviation. If the calculation result is positive, it indicates that the coating is too thick. If the calculation result is negative, the surface coating is too thin. The greater the absolute value of the calculation result, the greater the degree of deviation.

[0025] S106, if yes, calculating the thickness standard deviation according to the measured thickness distribution field, calculating the speed correction amount according to the mean thickness deviation and the speed correction coefficient, and calculating the spraying width correction amount according to the mean thickness deviation, the thickness standard deviation and the spraying width correction coefficient. The speed correction amount is positively correlated with the mean thickness deviation, and the spraying width correction amount is positively correlated with the mean thickness deviation and negatively correlated with the thickness standard deviation.

[0026] The thickness standard deviation can reflect the uniformity of the coating thickness in the spraying area. The greater the value of the calculation result, the worse the uniformity.

[0027] Before spraying, the target thickness of the coating and the allowed deviation range, the speed correction coefficient and the spraying width correction coefficient are set in advance as needed.

[0028] In the spraying process, the thickness deviation mean value can be calculated by using the measured thickness distribution field and the target thickness, and it is judged whether the calculated thickness deviation mean value is within the allowable deviation range. Once the thickness deviation mean value exceeds the allowable deviation range, it is determined that the coating in the spraying area is ultra-thin or ultra-thin. At this time, the speed correction amount is calculated according to the thickness deviation mean value and the speed correction coefficient, and the speed correction amount is superimposed on the basis of the current speed as the new moving speed of the spray gun, so that the spray gun moves at the new moving speed. It should be noted that because the speed correction amount is positively correlated with the thickness deviation mean value, when the thickness deviation mean value is positive, the speed correction amount is positive, and the greater the thickness deviation mean value (i.e. the thicker the measured thickness), the greater the speed correction amount. After updating, the spray gun moving speed is increased, the deposition amount per unit area is reduced, and the faster the spray gun moving speed increases with the increase of the thickness deviation, so that the coating thickness can be thinned as soon as possible, and the coating thickness can be thinned as soon as possible. The thickness deviation is reduced; when the thickness deviation mean value is negative, the speed correction amount is negative, and the greater the absolute value of the thickness deviation mean value (i.e. the thinner the measured thickness), the greater the absolute value of the speed correction amount. After updating, the spray gun moving speed is reduced, the deposition amount per unit area is increased, and the slower the spray gun moving speed decreases with the increase of the thickness deviation, so that the coating thickness can be thickened, the coating thickness can be thinned as soon as possible. The thickness deviation is reduced; by adjusting the moving speed of the spray gun, the effect of "thickening fast and thinning slow" is realized, and dynamic balance deposition is realized, so that the coating thickness is maintained near the target thickness, and over-thickness or over-thin is avoided.

[0029] Because the spraying width of the spray gun determines the coverage width and the overlap rate between adjacent tracks, which has a significant impact on uniformity, the thickness standard deviation can also be calculated by using the measured thickness distribution field during spraying. Once the thickness deviation mean value exceeds the allowable deviation range, the spraying width correction amount is calculated according to the thickness deviation mean value, the thickness standard deviation and the spraying width correction coefficient, and the spraying width correction amount is superimposed on the basis of the current spraying width as the new spraying width of the spray gun, so that the spray gun sprays at the new spraying width. It should be noted that because the spraying width correction amount is positively correlated with the thickness deviation mean value and negatively correlated with the thickness standard deviation, the thickness deviation mean value and the thickness standard deviation will jointly affect the spraying width correction amount. When the local area is overall thin, the spraying width is narrowed to concentrate the spraying to the weak area and increase the deposition amount per unit area in the weak area; when the local area is overall thick, the spraying width is appropriately widened to expand the coverage area and reduce the deposition amount per unit area, so as to improve the coating uniformity as much as possible while maintaining the coating thickness near the target thickness.

[0030] In conclusion, the intelligent surface spraying method based on coating quality provided in this embodiment directly introduces coating quality feedback into spraying control, and adjusts the control instructions (the moving speed and amplitude of the spray gun) in real time according to the sensing result, so as to realize the effect of adjusting while spraying, realize dynamic control closed loop, and thus, the control instructions can be optimized in the spraying process, the coating quality is improved, the differences in workpiece surface and spraying environment are flexibly adapted, the problems of uneven coating thickness, missed spraying or over-spraying are less likely to occur, the standard rate of the spraying effect of the product surface coating is high, the number of secondary processing can be greatly reduced, and the production capacity is improved. The method is especially suitable for workpiece surfaces with complex curvature, and can significantly improve the problems of large spraying amplitude distortion and large thickness deviation.

[0031] The method provided in this embodiment can further include the following steps: if the posture adjustment condition is met, calculating a thickness deviation distribution field according to the measured thickness distribution field and the target thickness; calculating a normal micro-shift vector according to the thickness deviation distribution field and a trajectory fine-tuning sensitivity; and calculating a posture correction amount according to the normal micro-shift vector and a posture correction coefficient, so as to adjust the posture of the spray gun; wherein the trajectory fine-tuning sensitivity and the posture correction coefficient are both preset values. It should be noted that the posture of the spray gun is adjusted in the three-dimensional space when the posture adjustment condition is met, which can improve the standard rate of the spraying effect, prevent the coating from being too thin, too thick or too uneven, and ensure the coating quality.

[0032] In fact, the moving speed of the spray gun needs to be controlled within the speed allowable range, if the moving speed of the spray gun after correction is lower than the minimum speed threshold, the moving speed of the spray gun is adjusted to the minimum speed threshold; if the moving speed of the spray gun after correction is higher than the maximum speed threshold, the moving speed of the spray gun is adjusted to the maximum speed threshold, so as to ensure that the actual moving speed of the spray gun is always within the speed allowable range. The spraying amplitude of the spray gun needs to be controlled within the spraying amplitude allowable range, if the spraying amplitude of the spray gun after correction is smaller than the minimum spraying amplitude threshold, the spraying amplitude of the spray gun is adjusted to the minimum spraying amplitude threshold; if the spraying amplitude of the spray gun after correction is greater than the maximum spraying amplitude threshold, the spraying amplitude of the spray gun is adjusted to the maximum spraying amplitude threshold, so as to ensure that the actual spraying amplitude of the spray gun is always within the spraying amplitude allowable range. The posture of the spray gun needs to be controlled within the posture allowable range, if the angle of the spray gun in a certain direction after correction is smaller than the minimum angle threshold, the angle of the spray gun in the direction is adjusted to the minimum angle threshold; if the angle of the spray gun in a certain direction after correction is greater than the maximum angle threshold, the angle of the spray gun in the direction is adjusted to the maximum angle threshold.

[0033] The above posture adjustment condition includes any one of the following conditions: Condition A: after the moving speed and the spraying amplitude of the spray gun are adjusted for several times (the number of times can be set as needed), the mean thickness deviation is still outside the allowable deviation range; Condition B, in the continuous process of adjusting the moving speed and the spraying width for several times (the number of times can be set according to requirements), the moving speed is maintained at the speed threshold or the spraying width is maintained at the spraying width threshold.

[0034] If any of the above conditions is met, it indicates that after several adjustments of the moving speed and the spraying width of the spray gun, the coating quality still does not meet the requirements, that is, only adjusting the moving speed and the spraying width of the spray gun is insufficient, at this time, the adjustment of the posture of the spray gun is needed to optimize the coating quality so that the coating quality can meet the requirements.

[0035] The above normal micro-movement vector can be calculated by the following formula: , wherein, is the thickness deviation distribution field, is the trajectory fine-tuning sensitivity, so that the gradient direction of the thickness deviation distribution field can be used as the normal micro-movement direction; on this basis, the above posture correction amount can be calculated by the following formula: , wherein, is the posture correction coefficient, so that the posture correction vector of the spray gun can be determined, so that the spray gun can be inclined towards the direction of thinner coating to increase the spraying amount of the thinner area of the coating and optimize the coating uniformity.

[0036] The above thickness deviation average can be calculated by the following formula: , wherein, is the set of effective detection points in the spraying width area, is the number of effective detection points in the spraying width area, is the measured thickness at the detection point , and is the target thickness; the speed correction amount can be calculated by the following formula: , wherein, is the speed correction coefficient, so that the speed correction amount of the spray gun can be determined, so that when the coating in the current spraying area is too thick, the speed can be increased to reduce the spraying amount per unit area to thin the coating thickness; and when the coating in the current spraying area is too thin, the speed can be reduced to increase the spraying amount per unit area to thicken the coating thickness.

[0037] The above thickness standard deviation can be calculated by the following formula: , wherein, is the measured thickness average of the coating in the spraying width area; the above spraying width correction amount can be calculated by the following formula: , wherein, is a spray width correction coefficient, thus, the spray width correction amount of the spray gun can be determined, so that when the coating in the current spraying area is too thick, the spray width of the spray gun is increased to reduce the spraying amount per unit area, so as to thin the coating; and when the coating in the current spraying area is too thin, the spray width is reduced to increase the spraying amount per unit area, so as to thicken the coating, and the uniformity is optimized.

[0038] The method provided by the embodiment can further include the following steps: recording the monitoring data and the control data in each spraying process to form a data set; calculating a spraying quality index according to the data set after completing a plurality of spraying processes; updating the control parameter vector based on the spraying quality index using an iterative optimization method; wherein the control parameter vector includes the speed correction coefficient, the spray width correction coefficient and the posture correction coefficient; and storing the updated control parameter vector in the curvature-parameter mapping table as the initial setting of the next spraying process. In this way, the control parameter vector can be updated regularly to adjust the reaction strength of the system when facing thickness deviation, and the "memory adaptive" is realized. In this way, as the spraying task accumulates, the system can gradually form a set of "experience" to automatically adapt to different workpiece shapes and environmental conditions, so that the spraying process has long-term evolution ability, and the coating quality is better optimized, and the spraying is more stable and accurate.

[0039] The data set can be: , wherein, is a measured thickness distribution field in the i th spraying process, is a control instruction in the i th spraying process, the control instruction including a moving speed, a spray width and a posture, is a thickness deviation distribution field in the i th spraying process. The coating quality index can include an average value, a standard deviation and an extreme value difference of the measured thickness. On this basis, the update formula of the control parameter vector can be: , wherein, is a cost function taking the coating quality index as a target, and the coating quality index difference under the control parameter is minimized by gradient descent of the cost function , so as to obtain a new control parameter θ to optimize the coating quality. The coating quality index can include a thickness error and a uniformity index. Specifically, a numerical value can be obtained by analyzing the average value, the standard deviation and the extreme value difference of the measured thickness, and the numerical value is used as the coating quality index.

[0040] As an alternative solution, the compensation mechanism can use fuzzy control or genetic algorithm optimization instead; and the learning mechanism can be based on reinforcement learning or knowledge distillation instead.

[0041] The output interface of the embodiment is unified: the corrected trajectory and parameters are generated to directly drive the spraying robot to execute.

[0042] The embodiment breaks through the traditional mode of decoupling detection and execution by coupling quality perception and trajectory control, dynamically adjusts the spraying width, speed and path in combination, significantly improves the coating consistency, and guarantees that the spraying becomes better and better through self-learning iteration framework, and has obvious technical progress.

[0043] Figure 2 A structure schematic diagram of an intelligent surface spraying device based on coating quality is provided for an embodiment of the application, and the device comprises: A monitoring module 21 is configured to monitor the measured thickness of the coating at a plurality of detection points in the spraying area in real time to obtain a measured thickness distribution field. A judgment module 22 is configured to calculate a thickness deviation mean value according to the measured thickness distribution field and the target thickness of the coating, and judge whether the thickness deviation mean value is outside the allowed range. A calculation module 23 is configured to, when the judgment result of the judgment module is yes, calculate a thickness standard deviation according to the measured thickness distribution field, calculate a speed correction amount according to the thickness deviation mean value and a speed correction coefficient, and calculate a spraying width correction amount according to the thickness deviation mean value, the thickness standard deviation and a spraying width correction coefficient, wherein the speed correction amount is positively correlated with the thickness deviation mean value, the spraying width correction amount is positively correlated with the thickness deviation and negatively correlated with the thickness standard deviation.

[0044] The intelligent surface spraying device based on coating quality provided by the embodiment has the same technical features as the intelligent surface spraying method based on coating quality provided by the above-mentioned embodiment, can solve the same technical problems, and produces the same technical effects.

[0045] The calculation module is further configured to, when the posture adjustment condition is met, calculate a thickness deviation distribution field according to the measured thickness distribution field and the target thickness, calculate a normal micro-shift vector according to the thickness deviation distribution field and a trajectory fine-tuning sensitivity, and calculate a posture correction vector according to the normal micro-shift vector and a posture correction coefficient, so as to adjust the posture of the spray gun.

[0046] The device provided by the embodiment further comprises a learning module configured to record the monitoring data and the control data in each spraying process to form a data set, calculate a spraying quality index according to the data set after each spraying is completed, update the control parameter vector using an iterative optimization method based on the spraying quality index, and store the updated control parameter vector into a curvature-parameter mapping table as the initial setting of the next spraying process.

[0047] One embodiment of the present application also provides a spraying robot, comprising a spray gun, a coating thickness monitor, a computer readable storage medium storing a computer program and a processor, the coating thickness monitor is fixed to the spray gun and is used to monitor the actual coating thickness of a plurality of detection points in a spraying area; the coating thickness monitor and the spray gun are both electrically connected to the processor, and the computer program is read and run by the processor to realize the intelligent surface spraying method based on coating quality in any of the above embodiments.

[0048] The spraying robot provided by the embodiment has the same technical features as the intelligent surface spraying method based on coating quality provided by the above embodiments, can solve the same technical problems, and produces the same technical effects.

[0049] Specifically, the coating thickness monitor can be fixed to the spray gun, and can be any one of an optical camera, an ultrasonic thickness sensor, an electromagnetic thickness sensor, a laser thickness gauge and an infrared thermal imager.

[0050] The embodiment also provides a computer readable storage medium, and the computer readable storage medium stores a computer program, the computer program is executed by the processor to realize each process of the intelligent surface spraying method based on coating quality, and the same technical effects can be achieved, and thus details are not described herein again. The computer readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0051] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer degree to instruct a control device, and the program can be stored in a computer readable storage medium. The program can include the processes of the above-mentioned method embodiments when executed, and the storage medium can be a memory, a magnetic disk, an optical disk, etc.

[0052] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application, and thus the protection scope of the present application should be subject to the scope defined by the claims.

[0053] Finally, it needs to be pointed out that in this document, relational terms such as first and second and the like can only be used to distinguish one entity or action from another entity or action, without necessarily requiring or implying any such actual relationship or order between such entities or actions. Moreover, the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article, or apparatus that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0054] Finally, it needs to be pointed out that the above-described embodiments are only specific implementations of the present application, which are used to illustrate the technical solutions of the present application, but not to limit the same. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still make modifications or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features, within the technical scope disclosed by the present application. Such modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within 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. A smart surface spraying method based on coating quality, characterized in that, include: Real-time monitoring of the measured coating thickness at multiple detection points within the spray area yields the measured thickness distribution field. Based on the measured thickness distribution field and the target thickness of the coating, the average thickness deviation is calculated, and it is determined whether the average thickness deviation is outside the allowable range. If so, the thickness standard deviation is calculated based on the measured thickness distribution field; the speed correction is calculated based on the mean thickness deviation and the speed correction coefficient; and the spray width correction is calculated based on the mean thickness deviation, the thickness standard deviation, and the spray width correction coefficient; wherein the speed correction is positively correlated with the mean thickness deviation, and the spray width correction is positively correlated with the thickness deviation and negatively correlated with the thickness standard deviation.

2. The intelligent surface spraying method based on coating quality according to claim 1, characterized in that, The method further includes: If the attitude adjustment conditions are met, then the thickness deviation distribution field is calculated based on the measured thickness distribution field and the target thickness. Based on the thickness deviation distribution field and trajectory fine-tuning sensitivity, calculate the normal micro-shift vector; The attitude correction vector is calculated based on the normal micro-shift vector and the attitude correction coefficient.

3. The intelligent surface spraying method based on coating quality according to claim 2, characterized in that, The attitude adjustment conditions include any one of the following conditions: Condition A: After several consecutive adjustments to the moving speed and spray width of the spray gun, the average thickness deviation is still outside the allowable deviation range; Condition B: During the continuous process of adjusting the moving speed and the spray width several times, the moving speed is maintained at the speed threshold or the spray width is maintained at the spray width threshold throughout the entire process.

4. The intelligent surface spraying method based on coating quality according to claim 2, characterized in that, The formula for calculating the normal micro-shift vector is: ,in, The thickness deviation distribution field, Fine-tune the sensitivity of the trajectory; The formula for calculating the attitude correction vector is: ,in, The attitude correction coefficient is denoted as .

5. The intelligent surface spraying method based on coating quality according to claim 1, characterized in that, The formula for calculating the average thickness deviation is: ,in, This is the set of effective detection points within the spray area. The number of effective detection points within the spray area. For testing points The measured thickness at that location The target thickness; The formula for calculating the speed correction is: ,in, This is the speed correction coefficient.

6. The intelligent surface spraying method based on coating quality according to claim 5, characterized in that, The formula for calculating the standard deviation of the thickness is: ,in, The mean measured thickness of the coating within the sprayed area; The formula for calculating the spray width correction amount is: ,in, is the correction factor for the spray width.

7. The intelligent surface spraying method based on coating quality according to any one of claims 2-6, characterized in that, The method further includes: Record the monitoring and control data for each spraying process to form a dataset: After a certain number of spraying operations are completed, the spraying quality index is calculated based on the dataset. Based on the coating quality index, the control parameter vector is updated using an iterative optimization method; wherein, the control parameter vector includes the speed correction coefficient, the spray width correction coefficient, and the attitude correction coefficient; The updated control parameter vector is stored in the curvature-parameter mapping table as the initial setting for the next spraying process.

8. The intelligent surface spraying method based on coating quality according to claim 7, characterized in that, The dataset is as follows: ,in, The measured thickness distribution field during the i-th spraying process is shown. This refers to the control commands during the i-th spraying process, which include the moving speed, the spray width, and the posture. Let be the thickness deviation distribution field during the i-th spraying process; The update formula for the control parameter vector is: ,in, Let be the cost function with the coating quality index as the objective.

9. An intelligent surface spraying device based on coating quality, characterized in that, include: The monitoring module is used to monitor the measured coating thickness at multiple detection points within the spray area in real time, and obtain the measured thickness distribution field. The judgment module is used to calculate the average thickness deviation based on the measured thickness distribution field and the target thickness of the coating, and to determine whether the average thickness deviation is outside the allowable range. The calculation module is used to calculate the thickness standard deviation based on the measured thickness distribution field when the judgment result of the judgment module is yes; and to calculate the speed correction amount based on the mean thickness deviation and the speed correction coefficient; and to calculate the spray width correction amount based on the mean thickness deviation, the standard thickness deviation, and the spray width correction coefficient; wherein the speed correction amount is positively correlated with the mean thickness deviation, and the spray width correction amount is positively correlated with the thickness deviation and negatively correlated with the standard thickness deviation.

10. A painting robot, characterized in that, The method includes a spray gun, a coating thickness monitor, a computer-readable storage medium storing a computer program, and a processor. The coating thickness monitor is fixedly connected to the spray gun and is used to monitor the measured coating thickness at multiple detection points within the spray area. Both the coating thickness monitor and the spray gun are electrically connected to the processor. The computer program is read and executed by the processor to implement the method described in any one of claims 1-8.

Images