Control optimization method for hardware spraying device

Abstract

The invention discloses a control optimization method for a hardware spraying device, and relates to the technical field of spraying control. The method comprises the steps that structural data and spraying requirements of hardware in a target spraying task are extracted; adjusting parameters of the spraying device according to the initial control scheme to obtain a configured initial spraying device; the initial spraying device is used for sequentially spraying the K hardware pieces, spraying quality detection is conducted on the M hardware piece finished products, and M spraying quality detection results are generated; performing quality situation analysis on the M spraying quality detection results to generate an abnormal quality analysis result; and optimizing the control scheme of the initial spraying device to obtain an adjustment control scheme, and adjusting parameters of the initial spraying device to obtain an optimized target spraying device. The technical problem that in the prior art, the spraying quality is reduced due to running loss of a hardware spraying device is solved, and the technical effect of improving the spraying quality is achieved by conducting parameter compensation on the spraying device.

Description

Technical Field

[0001] The invention relates to the technical field of spraying control, and in particular to a control optimization method for a hardware spraying device. Background Art

[0002] With the rapid development of the manufacturing industry and the intensification of market competition, the requirements for the quality of hardware spraying are getting higher and higher. As an indispensable part of industrial production and daily life, the surface spraying treatment of hardware plays a vital role in improving product performance, extending service life and beautifying appearance. However, in the process of hardware spraying, the spraying device often faces problems such as performance degradation and spraying parameter deviation after long-term operation, which directly affects the stability and consistency of the spraying quality. Traditional spraying control methods usually rely on manual experience and regular maintenance, which has many limitations. First, manual experience makes it difficult to accurately judge the subtle changes in spraying parameters, resulting in large fluctuations in spraying quality. Secondly, although regular maintenance can delay the performance degradation of the spraying device to a certain extent, it cannot respond to changes in spraying parameters in real time, and the maintenance cost is high. Summary of the invention

[0003] The embodiment of the present application provides a control optimization method for a hardware spraying device, which solves the technical problem in the prior art that the operating loss of the hardware spraying device leads to reduced spraying quality.

[0004] In view of the above problems, an embodiment of the present application provides a control optimization method for a hardware spraying device.

[0005] The present application embodiment provides a control optimization method for a hardware spraying device, the method comprising: Extract the structural data and spraying requirements of the hardware in the target spraying task; execute the initial control scheme configuration of the spraying device, and adjust the parameters of the spraying device according to the initial control scheme to obtain the configured initial spraying device, wherein the initial control scheme is obtained by searching in the control scheme library based on the structural data and the spraying requirements; respectively perform traceability identification on the K hardware in the target spraying task to generate K traceability identifications, wherein the K traceability identifications are used to record the time when the K hardware executes different spraying processes; use the initial spraying device to spray the K hardware in turn, and extract the traceability information within the first preset detection window. For M finished hardware parts that have been sprayed, perform spraying quality inspection on the M finished hardware parts to generate M spraying quality inspection results; based on the M traceability identifications of the M finished hardware parts, perform quality situation analysis on the M spraying quality inspection results to generate abnormal quality analysis results, wherein the abnormal quality analysis results include Q abnormal quality deviation coefficients and Q abnormal surface defect characteristics; based on the Q abnormal quality deviation coefficients and Q abnormal surface defect characteristics, optimize the control scheme of the initial spraying device to obtain an adjustment control scheme, and adjust the parameters of the initial spraying device according to the adjustment control scheme to obtain an optimized target spraying device.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, extract the structural data and spraying requirements of the hardware in the target spraying task. Then, execute the initial control scheme configuration of the spraying device, and adjust the parameters of the spraying device according to the initial control scheme to obtain the configured initial spraying device, wherein the initial control scheme is obtained by searching in the control scheme library based on the structural data and the spraying requirements. Further, traceability identification is performed on the K hardware in the target spraying task respectively, and K traceability identifications are generated, wherein the K traceability identifications are used to record the time when the K hardware performs different spraying processes. Then, the K hardware are sprayed in sequence using the initial spraying device, and the M hardware finished products sprayed in the first preset detection window are extracted, and the M hardware finished products are sprayed for quality inspection, and M spraying quality inspection results are generated. Based on the M traceability identifications of the M hardware finished products, the quality situation analysis of the M spraying quality inspection results is performed to generate abnormal quality analysis results, wherein the abnormal quality analysis results include Q abnormal quality deviation coefficients and Q abnormal surface defect features. Finally, the control scheme of the initial spraying device is optimized based on Q abnormal quality deviation coefficients and Q abnormal surface defect characteristics, and an adjustment control scheme is obtained. The initial spraying device is adjusted according to the adjustment control scheme to obtain an optimized target spraying device. The technical problem of reduced spraying quality caused by operating loss of the hardware spraying device in the prior art is solved, and the technical effect of improving the spraying quality is achieved by parameter compensation of the spraying device. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0008] Figure 1 A schematic flow chart of a control optimization method for a hardware spraying device provided in an embodiment of the present application; Figure 2 A schematic diagram of a flow chart for spraying quality detection in a control optimization method for a hardware spraying device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0009] The embodiment of the present application solves the technical problem in the prior art that the operating loss of the hardware spraying device leads to reduced spraying quality by providing a control optimization method for the hardware spraying device.

[0010] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0011] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0012] Examples, such as Figure 1 As shown, the embodiment of the present application provides a control optimization method for a hardware spraying device, wherein the method includes: Extract the structural data and spraying requirements of the hardware in the target spraying task.

[0013] The structural data and spraying requirements of the hardware are extracted from the target spraying task, where the structural data includes the size and shape of the hardware, and the spraying requirements include the color of the spraying, the thickness of the coating, etc.

[0014] Execute the initial control scheme configuration of the spray device, and adjust the parameters of the spray device according to the initial control scheme to obtain a configured initial spray device, wherein the initial control scheme is obtained by searching in a control scheme library based on the structural data and the spraying requirements.

[0015] According to the structural data and spraying requirements of the hardware, search in the preset control scheme library, which contains preset control schemes for different hardware structures and spraying requirements. By comparing the structural data of the hardware (such as size, shape, material, etc.) and the spraying requirements (such as color, coating thickness, spraying speed, etc.), find the control scheme that best matches or is similar to the current task as the initial control scheme. Load the initial control scheme into the spraying device, and configure the spraying device according to the parameter settings in the initial control scheme, including the adjustment of the spray gun's position, angle, spraying pressure, flow, speed and other parameters. After the configuration is completed, the initial spraying device is obtained.

[0016] Further, including: Extract historical spraying record data of the spraying device within a historical time, wherein the historical spraying record data includes historical structure data, historical spraying requirements and historical spraying control schemes; perform data similarity authentication on the historical spraying record data to obtain historical similarity; if the historical similarity is greater than or equal to a preset similarity threshold, generate a cloud supplementary instruction; according to the cloud supplementary instruction, retrieve the cloud spraying record data, and store the cloud spraying record data and the historical spraying record data in the control scheme library.

[0017] Extract historical spraying record data within a historical time from the storage system of the spraying device, the historical spraying record data including historical structural data (such as size, shape, material, etc.), historical spraying requirements (such as color, coating thickness, spraying speed, etc.) and historical spraying control schemes (i.e., specific parameter settings used to perform spraying tasks in the past); perform data similarity authentication on the historical spraying record data, and obtain historical similarity by calculating the similarity between multiple spraying records in the historical spraying record data; if the historical similarity is greater than or equal to a preset similarity threshold, it means that the spraying record data is too single and needs to be supplemented from a cloud database, and at this time, a cloud supplement instruction can be generated; according to the cloud supplement instruction, retrieve the cloud spraying record data from the cloud database, and store the cloud spraying record data together with the historical spraying record data in the control scheme library, so as to optimize the control scheme library.

[0018] Further, including: The historical spraying record data are subjected to pairwise similarity calculation using a cosine similarity calculation formula to generate a plurality of historical cosine similarities; the plurality of historical cosine similarities are subjected to variance calculation, and the inverse of the calculation result is used as the historical similarity.

[0019] When evaluating the similarity between historical spraying record data and the target spraying task, the cosine similarity calculation formula can be used to calculate the similarity between historical spraying record data. For example, the two spraying records in the historical spraying record data are A and B, where A and B are both feature vectors (a combination of structural data and spraying requirements). Perform cosine similarity calculations between all historical record data to generate multiple historical cosine similarities; in order to obtain an overall historical similarity, multiple historical cosine similarities can be aggregated by calculating the average of all historical cosine similarities, and then calculating the variance of all historical cosine similarities and the mean, and taking the inverse of the variance as the historical similarity. Among them, if the variance is larger, the similarity is smaller, indicating that the data quality is better and includes a variety of application situations; if the variance is smaller, the similarity is higher, indicating that the data is too single, and data needs to be supplemented from the cloud.

[0020] The K hardware parts in the target spraying task are respectively traced to generate K traceability marks, wherein the K traceability marks are used to record the time when the K hardware parts perform different spraying processes.

[0021] During the spraying process, the hardware is traced to track the status, time and any possible quality problems of each hardware in the entire spraying process. Specifically, a unique traceability mark, such as a barcode, QR code, or RFID tag, is assigned to each of the K hardware in the target spraying task; when the hardware goes through different spraying processes, a recording system (such as a scanning device, RFID reader, etc.) is used to read the traceability mark of each hardware and record the start and end time of the hardware in the process. By generating traceability marks for the K hardware in the target spraying task and recording their time information when performing different spraying processes, if there is a quality problem with a certain hardware, it is possible to quickly locate which process the hardware has a problem in.

[0022] The K hardware parts are sprayed in sequence using the initial spraying device, and the M finished hardware parts sprayed in the first preset detection window are extracted, and the spraying quality of the M finished hardware parts is inspected to generate M spraying quality inspection results.

[0023] Use the initial spraying device to spray K hardware parts in sequence. After a period of time after the spraying operation is completed (for example, waiting for the coating to dry and solidify), extract the M hardware parts that have been sprayed in the first preset detection window, where the first preset detection window is a time range used to determine which hardware parts have been sprayed and can be quality tested. Perform spraying quality inspection on the extracted M hardware parts, including the appearance of the coating (such as color, glossiness, uniformity, etc.), coating thickness, coating hardness, corrosion resistance, etc., and generate M spraying quality inspection results.

[0024] Furthermore, if Figure 2 As shown, the spraying quality test is performed on the M finished hardware parts to generate M spraying quality test results, including: A surface acquisition device is used to acquire images of the M hardware products to generate M surface image sets; a surface defect identifier is used to identify defect features of the M surface image sets to generate M surface defect feature value sets and M surface defect feature sets, wherein surface defect features correspond one to one with surface defect feature values; the M surface defect feature sets and the M surface defect feature value sets are used as the M spraying quality inspection results.

[0025] Preferably, a surface acquisition device (such as a high-resolution camera, image sensor, etc.) is used to acquire multi-angle surface images of M finished hardware products to obtain M surface image sets; the surface defect identifier is a deep learning model trained based on historical defect feature data, which is used to detect defects in images and extract feature information of defects; the M surface image sets are input into the surface defect identifier, which will perform defect feature recognition on the surface image of each finished hardware product, and output M surface defect feature value sets and M surface defect feature sets, wherein the surface defect features correspond to the surface defect feature values ​​one by one, that is, each defect feature has a corresponding feature value to describe its specific situation; the M surface defect feature sets and the M surface defect feature value sets are used as M spraying quality inspection results. The surface acquisition device and the surface defect identifier are used to acquire surface images and recognize defect features of the finished hardware products after spraying, so as to more accurately evaluate the spraying quality.

[0026] Based on the M traceability identifications of the M hardware finished products, a quality situation analysis is performed on the M spraying quality inspection results to generate abnormal quality analysis results, wherein the abnormal quality analysis results include Q abnormal quality deviation coefficients and Q abnormal surface defect features.

[0027] The quality problems of hardware spraying usually include paint shrinkage, floating wrinkles, sagging, pinholes, contaminated blistering, wet blistering, and uneven color. Among them, paint shrinkage refers to wrinkles or shrinkage deformation on the paint surface during the spraying process or the drying process of the paint film; floating wrinkles refer to bulges formed in some areas due to the expansion of the paint surface during the spraying process or the drying process of the paint film; sagging refers to the local thickening of the coating, and the vertical flow state due to gravity; pinholes refer to a concave and transparent pinhole phenomenon on the surface of the paint film; contaminated blistering refers to irregular blistering on the surface of the paint layer; wet blistering refers to evenly distributed pockmarked small bubbles of various sizes, which are easy to appear under very humid and hot conditions. Different spraying quality problems of hardware are related to different processes. The M traceability marks of M hardware finished products are associated with their respective spraying quality test results to trace back to the specific production process and conditions of each hardware. A quality situation analysis is performed on M spraying quality inspection results, that is, the quality problems are traced back to the specific process flow to determine the quality problems, and then the abnormal quality analysis results are obtained. The abnormal quality analysis results include Q abnormal quality deviation coefficients and Q abnormal surface defect characteristics.

[0028] Further, including: The surface defect features of the M surface defect feature sets in the M spraying quality inspection results are aggregated across finished products to generate L aggregated surface defect feature sets, each aggregated surface defect feature corresponds to a hardware finished product, L is the total number of types of surface defect features in the M surface defect feature sets, and L is an integer greater than or equal to 1; based on the one-to-one correspondence between the surface defect features and the surface defect feature values, feature value matching is performed on the L aggregated surface defect feature sets to generate L aggregated surface defect feature value sets; quality situation analysis is performed based on the M traceability identifiers and the L aggregated surface defect feature value sets to generate the abnormal quality analysis result.

[0029] Preferably, the M surface defect feature sets of M hardware finished products are clustered across finished products, that is, the hardware finished products with the same or similar surface defect features are classified into one category, and by comparing the surface defect features of different hardware finished products, the same or similar features are grouped together to form L clustered surface defect feature sets, wherein L is the total number of types of surface defect features in the M surface defect feature sets, and is an integer greater than or equal to 1; based on the one-to-one correspondence between surface defect features and surface defect feature values, for each clustered surface defect feature set, the surface defect feature values ​​of all hardware finished products belonging to the set are searched, and these feature values ​​are clustered together to form corresponding L clustered surface defect feature value sets; quality situation analysis is performed based on the M traceability identifications and the L clustered surface defect feature value sets, each clustered surface defect feature value set is analyzed, and the severity and distribution of the corresponding clustered surface defect features are evaluated, and based on the traceability identifications of the hardware finished products, the process flows in which quality defects occur are further identified, and abnormal quality analysis results are generated.

[0030] Further, including: Using L surface defect tolerance values, the L aggregated surface defect feature value sets are screened for abnormality to generate L abnormal aggregated surface defect feature value sets; According to the M traceability identifiers, the L abnormal aggregated surface defect feature value sets are serialized respectively, and L abnormal feature value curves are generated according to the processing results, wherein the abscissa of the abnormal feature value curve is time, the ordinate is the abnormal aggregated surface defect feature value, and the L abnormal feature value curves include L abnormal coordinate point sets; Extract L center points of the L abnormal coordinate point sets, perform quality situation analysis based on the L center points and the L abnormal coordinate point sets, and generate the abnormal quality analysis result.

[0031] Preferably, L surface defect tolerance values ​​are set according to historical data and industry standards, and these tolerance values ​​correspond to L different surface defect characteristics. Each value in the L aggregated surface defect feature value sets is compared with the corresponding surface defect tolerance value. If a certain feature value exceeds its corresponding tolerance value, the feature value is considered abnormal. The above comparison is performed on each aggregated surface defect feature value set to screen out abnormal feature values ​​and generate L abnormal aggregated surface defect feature value sets; the L abnormal aggregated surface defect feature value sets are serialized according to M traceability identifiers, that is, each abnormal aggregated surface defect feature value set is arranged in chronological order (production process flow), and for each abnormal aggregated surface defect feature value set, an abnormal feature value curve is generated, the horizontal axis of this curve represents time, and the vertical axis represents the abnormal aggregated surface defect feature value, thereby generating L abnormal feature value curves, each curve containing a series of abnormal coordinate point sets, and each coordinate point corresponds to an abnormal aggregated surface defect feature value; L center points (such as the average value of each set) are extracted from the L abnormal coordinate point sets, and quality situation analysis is performed based on the L center points and the L abnormal coordinate point sets to generate abnormal quality analysis results.

[0032] Further, including: Determine L first straight lines passing through the L center points, move the L first straight lines according to a preset moving angle to generate L second straight lines; determine whether the L first clustering densities of the L first straight lines are greater than or equal to the L second clustering densities of the L second straight lines, if not, move the L second straight lines according to the preset moving angle to generate L third straight lines; iteratively update the L second straight lines based on the L third straight lines until a preset number of iterations is met, and take the straight lines corresponding to the maximum clustering density as L target straight lines; take the slopes of the L target straight lines as L mass deviation coefficients; determine whether the L mass deviation coefficients are greater than or equal to the preset deviation coefficient, if so, add an abnormal mass deviation coefficient set, wherein the abnormal mass deviation coefficient set includes Q abnormal mass deviation coefficients, Q is a positive integer less than or equal to L; take the surface defect features corresponding to the Q abnormal mass deviation coefficients as Q abnormal surface defect features.

[0033] Preferably, L first straight lines passing through L center points are determined, which can be obtained by a linear fitting method (such as the least squares method), and they respectively represent the trend of the change of the characteristic value sets of L abnormal aggregated surface defects over time; the L first straight lines are moved according to a preset moving angle (such as a fixed angle increment, such as 1°, 5°, etc.) to generate L second straight lines; the L first clustering densities of the L first straight lines are calculated, that is, the density of the abnormal coordinate points on each first straight line. Similarly, the L second clustering densities of the L second straight lines are also calculated. If any one of the L first clustering densities is not less than the corresponding second clustering density, then the linear movement is stopped, that is, the first straight line has provided a better fit. If the clustering density of the first straight line does not meet the conditions, then the L second straight lines are moved according to the preset moving angle to generate L third straight lines; repeat the above steps of judging the clustering density, compare the clustering density of the L second straight lines and the L third straight lines, and select the one with a larger clustering density as the new reference straight line; perform iterative update until the preset number of iterations is met. After the iteration, the straight line corresponding to the maximum value of the clustering density is taken as L target straight lines; the slopes of the L target straight lines are calculated, and these slopes are taken as L quality deviation coefficients, which represent the deviation trend of the spraying quality over time; a preset deviation coefficient is set as a threshold to determine whether the L quality deviation coefficients are greater than or equal to the preset deviation coefficient. If a certain quality deviation coefficient is greater than or equal to the preset deviation coefficient, it is added to the abnormal quality deviation coefficient set, and the abnormal quality deviation coefficient set will contain Q abnormal quality deviation coefficients, where Q is a positive integer less than or equal to L; the surface defect features corresponding to the Q abnormal quality deviation coefficients are taken as Q abnormal surface defect features, which are the main reasons for the abnormal deviation of the spraying quality; the Q abnormal quality deviation coefficients and the Q abnormal surface defect features are taken as abnormal quality analysis results.

[0034] The control scheme of the initial spraying device is optimized based on the Q abnormal mass deviation coefficients and the Q abnormal surface defect characteristics to obtain an adjustment control scheme, and the parameters of the initial spraying device are adjusted according to the adjustment control scheme to obtain an optimized target spraying device.

[0035] Based on Q abnormal quality deviation coefficients, the trend and degree of spray quality deviation are obtained. At the same time, according to the characteristics of Q abnormal surface defects, the specific impact of these defects on the spray quality is determined. According to the analysis results, the control scheme of the initial spray device is optimized to obtain an adjustment control scheme. According to the adjustment control scheme, the initial spray device is adjusted to obtain an optimized target spray device. In short, the control scheme of the initial spray device is optimized and adjusted based on the abnormal quality deviation coefficient and the characteristics of abnormal surface defects, so as to obtain an optimized target spray device and improve the spray quality and production efficiency.

[0036] Further, including: A control scheme optimizer is constructed, and the control scheme optimizer is used to identify the Q abnormal quality deviation coefficients, the Q abnormal surface defect features and the initial control scheme to generate the adjustment control scheme.

[0037] Preferably, in order to effectively optimize the control scheme of the initial spraying device, a control scheme optimizer can be constructed based on optimization algorithms such as genetic algorithms, particle swarm optimization algorithms, etc. The control scheme optimizer will use Q abnormal mass deviation coefficients, Q abnormal surface defect characteristics and the initial control scheme as inputs, and find the optimal control scheme through iterative search. In each iteration, the pros and cons of the current control scheme are evaluated according to the fitness function, and a new control scheme candidate set is generated, wherein the fitness function can reflect the requirements of the optimization objective, such as the weighted sum of the mass deviation coefficient and the surface defect characteristics. After multiple iterations, until the preset number of iterations is reached, the adjusted control scheme is output.

[0038] In summary, the embodiments of the present application have at least the following technical effects: First, extract the structural data and spraying requirements of the hardware in the target spraying task. Then, execute the initial control scheme configuration of the spraying device, and adjust the parameters of the spraying device according to the initial control scheme to obtain the configured initial spraying device, wherein the initial control scheme is obtained by searching in the control scheme library based on the structural data and the spraying requirements. Further, traceability identification is performed on the K hardware in the target spraying task respectively, and K traceability identifications are generated, wherein the K traceability identifications are used to record the time when the K hardware performs different spraying processes. Then, the K hardware are sprayed in sequence using the initial spraying device, and the M hardware finished products sprayed in the first preset detection window are extracted, and the M hardware finished products are sprayed for quality inspection, and M spraying quality inspection results are generated. Based on the M traceability identifications of the M hardware finished products, the quality situation analysis of the M spraying quality inspection results is performed to generate abnormal quality analysis results, wherein the abnormal quality analysis results include Q abnormal quality deviation coefficients and Q abnormal surface defect features. Finally, the control scheme of the initial spraying device is optimized based on Q abnormal quality deviation coefficients and Q abnormal surface defect characteristics, and an adjustment control scheme is obtained. The initial spraying device is adjusted according to the adjustment control scheme to obtain an optimized target spraying device. The technical problem of reduced spraying quality caused by operating loss of the hardware spraying device in the prior art is solved, and the technical effect of improving the spraying quality is achieved by parameter compensation of the spraying device.

[0039] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0040] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0041] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A control optimization method for a hardware spraying device, characterized in that: The method comprises: Extract the structural data and spraying requirements of the hardware in the target spraying task; Execute the initial control scheme configuration of the spraying device, and adjust the parameters of the spraying device according to the initial control scheme to obtain a configured initial spraying device, wherein the initial control scheme is obtained by searching in a control scheme library based on the structural data and the spraying requirements; Performing traceability identification on K hardware parts in the target spraying task respectively to generate K traceability identifications, wherein the K traceability identifications are used to record the time when the K hardware parts perform different spraying processes; Using the initial spraying device to spray the K hardware parts in sequence, extracting the M finished hardware parts sprayed in the first preset detection window, performing spraying quality inspection on the M finished hardware parts, and generating M spraying quality inspection results; Based on the M traceability marks of the M hardware finished products, the M spraying quality inspection results are analyzed for quality status, and abnormal quality analysis results are generated, wherein the abnormal quality analysis results include Q abnormal quality deviation coefficients and Q abnormal surface defect features; The control scheme of the initial spraying device is optimized based on the Q abnormal mass deviation coefficients and the Q abnormal surface defect characteristics to obtain an adjustment control scheme, and the parameters of the initial spraying device are adjusted according to the adjustment control scheme to obtain an optimized target spraying device.

2. The control optimization method for a hardware spraying device according to claim 1, characterized in that: include: Extracting historical spraying record data of the spraying device in historical time, wherein the historical spraying record data includes historical structure data, historical spraying requirements and historical spraying control schemes; Performing data similarity authentication on the historical spraying record data to obtain historical similarity; If the historical similarity is greater than or equal to a preset similarity threshold, generating a cloud supplementary instruction; According to the cloud supplementary instruction, the cloud spray record data is retrieved, and the cloud spray record data and the historical spray record data are stored in the control solution library.

3. The control optimization method for a hardware spraying device according to claim 1, characterized in that: include: Using a surface acquisition device to acquire images of the M hardware finished products to generate M surface image sets; Using a surface defect identifier to perform defect feature identification on the M surface image sets, generating M surface defect feature value sets and M surface defect feature sets, wherein the surface defect features correspond to the surface defect feature values ​​one by one; The M surface defect feature sets and the M surface defect feature value sets are used as the M spraying quality detection results.

4. The control optimization method for a hardware spraying device according to claim 3, characterized in that: include: Aggregate the surface defect features across finished products for the M surface defect feature sets in the M spraying quality inspection results to generate L aggregated surface defect feature sets, each aggregated surface defect feature corresponds to a hardware finished product, L is the total number of types of surface defect features in the M surface defect feature sets, and L is an integer greater than or equal to 1; Based on the one-to-one correspondence between the surface defect features and the surface defect feature values, feature value matching is performed on the L aggregated surface defect feature sets to generate L aggregated surface defect feature value sets; A quality situation analysis is performed based on the M traceability identifiers and the L sets of aggregated surface defect feature values ​​to generate the abnormal quality analysis result.

5. The control optimization method for a hardware spraying device according to claim 4, characterized in that: include: Using L surface defect tolerance values, the L aggregated surface defect feature value sets are screened for abnormality to generate L abnormal aggregated surface defect feature value sets; According to the M traceability identifiers, the L abnormal aggregated surface defect feature value sets are serialized respectively, and L abnormal feature value curves are generated according to the processing results, wherein the abscissa of the abnormal feature value curve is time, the ordinate is the abnormal aggregated surface defect feature value, and the L abnormal feature value curves include L abnormal coordinate point sets; Extract L center points of the L abnormal coordinate point sets, perform quality situation analysis based on the L center points and the L abnormal coordinate point sets, and generate the abnormal quality analysis result.

6. The control optimization method for a hardware spraying device according to claim 5, characterized in that: include: Determine L first straight lines passing through the L center points, and move the L first straight lines according to a preset movement angle to generate L second straight lines; Determine whether the L first clustering densities of the L first straight lines are greater than or equal to the L second clustering densities of the L second straight lines; if not, move the L second straight lines according to the preset moving angle to generate L third straight lines; Iteratively update the L second straight lines based on the L third straight lines until a preset number of iterations is met, and take the straight line corresponding to the maximum value of the clustering density as the L target straight lines; The slopes of the L target straight lines are taken as L quality deviation coefficients; Determine whether the L mass deviation coefficients are greater than or equal to a preset deviation coefficient, and if so, add an abnormal mass deviation coefficient set, wherein the abnormal mass deviation coefficient set includes Q abnormal mass deviation coefficients, where Q is a positive integer less than or equal to L; The surface defect features corresponding to the Q abnormal mass deviation coefficients are taken as Q abnormal surface defect features.

7. The control optimization method for a hardware spraying device according to claim 1, characterized in that: include: A control scheme optimizer is constructed, and the control scheme optimizer is used to identify the Q abnormal quality deviation coefficients, the Q abnormal surface defect features and the initial control scheme to generate the adjustment control scheme.

8. The control optimization method for a hardware spraying device according to claim 2, characterized in that: include: Performing pairwise similarity calculation on the historical spraying record data using a cosine similarity calculation formula to generate multiple historical cosine similarities; The variance calculation is performed on the multiple historical cosine similarities, and the inverse of the calculation result is used as the historical similarity.

Images