Real-time monitoring system for thickness of photovoltaic glass coating

Abstract

The invention discloses a real-time monitoring system for the thickness of a photovoltaic glass coating, and relates to the technical field of real-time monitoring, and the real-time monitoring system comprises the steps: obtaining first and second spraying subtasks of a photovoltaic glass coating task and task information thereof, and determining first and second preset coating thickness real-time monitoring parameters; first spraying equipment is configured to complete spraying of a first coating, the coating thickness is monitored in real time, and a first thickness monitoring result set is obtained; performing longitudinal compliance analysis and transverse correlation analysis on the result set, and calculating a first longitudinal influence coefficient and a first transverse correlation influence coefficient; a first preset monitoring parameter is adjusted, and first spraying task monitoring is optimized; second preset monitoring parameters are adjusted, and second spraying task monitoring configuration is optimized; and spraying the second layer, and monitoring the thickness of the photovoltaic glass coating in real time. The technical problem that the coating thickness distribution cannot be accurately monitored in the prior art is solved, and the technical effect of accurately monitoring the thickness of the photovoltaic glass coating is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of real-time monitoring, and in particular to a real-time monitoring system for the thickness of a photovoltaic glass coating. Background Art

[0002] In the field of photovoltaic glass manufacturing, with the advancement of industrialization and the continuous improvement of product quality requirements, the demand for quality control of photovoltaic glass coatings is also increasing rapidly. These coatings usually include anti-reflective coatings, anti-reflective coatings, etc., with various layers and complex characteristics, and often require high uniformity and precise thickness control during the spraying process. If the coating thickness cannot be effectively monitored and adjusted, it will not only affect the optical properties of the photovoltaic glass, but may also lead to a decline in product performance and increase production costs. Traditional coating thickness monitoring methods mainly rely on offline measurement and fixed parameter spraying, which lacks real-time performance and is difficult to meet the needs of high-precision coating quality monitoring. Summary of the invention

[0003] The present application provides a real-time monitoring system for photovoltaic glass coating thickness, which is used to solve the technical problem that the existing technology cannot accurately monitor the coating thickness distribution.

[0004] In view of the above problems, the present application provides a real-time monitoring system for photovoltaic glass coating thickness.

[0005] In a first aspect of the present application, a real-time monitoring system for photovoltaic glass coating thickness is provided, the system comprising: A task acquisition module, wherein the task acquisition module acquires the first spraying subtask and the second spraying subtask of the target photovoltaic glass coating task, and the corresponding first spraying subtask information and the second spraying subtask information, wherein each spraying subtask information in the first spraying subtask information and the second spraying subtask information includes a coating type, an average coating thickness information, and a coating thickness uniformity information; a retrieval module, wherein the retrieval module uses the first spraying subtask information and the second spraying subtask information as indexes, respectively, to search in a preset coating monitoring space, and acquires a first preset coating thickness real-time monitoring parameter and a second preset coating thickness real-time monitoring parameter; a first thickness monitoring module, wherein the first thickness monitoring module configures parameters of a first spraying device according to the first spraying subtask information of the first spraying subtask, and uses the configured first spraying device to spray a coating on the surface of the photovoltaic glass, and monitors the coating thickness according to the first preset coating thickness real-time monitoring parameter within a first preset monitoring window, and obtains a first thickness monitoring result set; a horizontal and vertical analysis module, wherein the horizontal and vertical analysis module performs parameter configuration on the first thickness monitoring device according to the first spraying subtask information of the first spraying subtask, and performs a coating thickness monitoring on the surface of the photovoltaic glass according to the first preset coating thickness real-time monitoring parameter within a first preset monitoring window, and acquires a first thickness monitoring result set. A longitudinal compliance analysis and a transverse correlation analysis are performed on the measurement result set to determine the first longitudinal influence coefficient and the first transverse correlation influence coefficient; a second thickness monitoring module, wherein the second thickness monitoring module adjusts the first preset coating thickness real-time monitoring parameter according to the size of the first longitudinal influence coefficient to obtain the first adjusted coating thickness real-time monitoring parameter, and monitors the photovoltaic glass coating thickness of the first spraying subtask in the next preset monitoring window in real time according to the first adjusted coating thickness real-time monitoring parameter; a monitoring parameter adjustment module, wherein the monitoring parameter adjustment module adjusts the second preset coating thickness real-time monitoring parameter according to the size of the first transverse correlation influence coefficient to obtain the second real-time monitoring parameter affecting the coating thickness; a coating spraying module, wherein the coating spraying module configures the parameters of the second spraying equipment according to the second spraying subtask information of the second spraying subtask, and uses the configured second spraying equipment to spray the coating on the photovoltaic glass surface that completes the first spraying subtask in the first preset monitoring window, and monitors the photovoltaic glass coating thickness in real time according to the second real-time monitoring parameter affecting the coating thickness.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application obtains the first spraying subtask and the second spraying subtask of the target photovoltaic glass coating task, and the corresponding first spraying subtask information and the second spraying subtask information, wherein each spraying subtask information in the first spraying subtask information and the second spraying subtask information includes the coating type, the coating average thickness information, and the coating thickness uniformity information; respectively uses the first spraying subtask information and the second spraying subtask information as indexes to search in the preset coating monitoring space to obtain the first preset coating thickness real-time monitoring parameters and the second preset coating thickness real-time monitoring parameters; configures the parameters of the first spraying equipment according to the first spraying subtask information of the first spraying subtask, sprays the coating on the surface of the photovoltaic glass using the configured first spraying equipment, and monitors the coating thickness according to the first preset coating thickness real-time monitoring parameters within the first preset monitoring window to obtain a first thickness monitoring result set; and performs a first thickness monitoring The result set is subjected to vertical compliance analysis and horizontal correlation analysis to determine the first vertical influence coefficient and the first horizontal correlation influence coefficient; the first preset coating thickness real-time monitoring parameter is adjusted according to the size of the first vertical influence coefficient to obtain the first adjusted coating thickness real-time monitoring parameter, and the photovoltaic glass coating thickness of the first spraying subtask in the next preset monitoring window is monitored in real time according to the first adjusted coating thickness real-time monitoring parameter; the second preset coating thickness real-time monitoring parameter is adjusted according to the size of the first horizontal correlation influence coefficient to obtain the second coating thickness real-time monitoring parameter; the second spraying equipment is configured according to the second spraying subtask information of the second spraying subtask, and the second spraying equipment that has been configured is used to spray the coating on the photovoltaic glass surface that completes the first spraying subtask in the first preset monitoring window, and the photovoltaic glass coating thickness is monitored in real time according to the second coating thickness real-time monitoring parameter. The present invention solves the technical problem that the prior art cannot accurately monitor the coating thickness distribution, and dynamically adjusts the monitoring parameters and optimizes the spraying process through task information acquisition, coating monitoring parameter retrieval, spraying equipment configuration and real-time thickness monitoring, combined with vertical compliance analysis and horizontal correlation analysis, to achieve the technical effect of accurately monitoring the coating thickness of photovoltaic glass. 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 diagram of the structure of a real-time monitoring system for photovoltaic glass coating thickness provided in an embodiment of the present application.

[0009] Figure 2A schematic flow chart of a method for real-time monitoring of photovoltaic glass coating thickness provided in an embodiment of the present application.

[0010] Explanation of the reference numerals: task acquisition module 11 , retrieval module 12 , first thickness monitoring module 13 , horizontal and vertical analysis module 14 , second thickness monitoring module 15 , monitoring parameter adjustment module 16 , coating spraying module 17 . DETAILED DESCRIPTION

[0011] This application provides a real-time monitoring system for the thickness of photovoltaic glass coating, aiming to solve the technical problem that the existing technology cannot accurately monitor the distribution of coating thickness. Through task information acquisition, coating monitoring parameter retrieval, spraying equipment configuration and real-time thickness monitoring, combined with vertical compliance analysis and horizontal correlation analysis, the monitoring parameters are dynamically adjusted and the spraying process is optimized, thereby achieving the technical effect of accurately monitoring the thickness of photovoltaic glass coating.

[0012] 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.

[0013] It should be noted that any variations of the terms "include" and "have" 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 inherent to these processes, methods, products or devices.

[0014] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a real-time monitoring system for the thickness of photovoltaic glass coating, which is used to perform the following Figure 2 The real-time monitoring method of the photovoltaic glass coating thickness shown in the present invention comprises: The task acquisition module 11 acquires the first spraying subtask and the second spraying subtask of the target photovoltaic glass coating task, and the corresponding first spraying subtask information and the second spraying subtask information, wherein each spraying subtask information in the first spraying subtask information and the second spraying subtask information includes coating type, coating average thickness information, and coating thickness uniformity information.

[0015] In an embodiment of the present application, the task acquisition module receives the first spraying subtask and the second spraying subtask of the target photovoltaic glass coating task from the production management system, as well as the corresponding first spraying subtask information and the second spraying subtask information. The first spraying subtask is used to coat the bottom coating of the photovoltaic glass, such as an anti-reflective coating. The second spraying subtask is performed after the first spraying subtask is completed, and is usually used to coat the surface coating. The first spraying subtask information and the second spraying subtask information contain the operating parameters of the equipment when executing the corresponding tasks.

[0016] Each of the received first spraying subtask information and second spraying subtask information includes coating type, coating average thickness information, and coating thickness uniformity information. The coating type specifies the characteristics and use of the spraying material; the coating average thickness information indicates the overall thickness of the target coating after spraying, usually in microns; and the coating thickness uniformity information reflects the uniformity of the coating thickness distribution on the glass surface.

[0017] The retrieval module 12 uses the first spraying subtask information and the second spraying subtask information as indexes to search in a preset coating monitoring space to obtain a first preset coating thickness real-time monitoring parameter and a second preset coating thickness real-time monitoring parameter.

[0018] In the embodiment of the present application, the retrieval module uses the first spraying subtask information and the second spraying subtask information as indexes, performs retrieval in the preset coating monitoring space, and locates the first target space point and the second target space point respectively.

[0019] Then, the k nearest neighbor algorithm is used to select the k neighboring sample points closest to the target space point from multiple sample space points to form a first nearest neighbor sample set and a second nearest neighbor sample set. Finally, the sample coating thickness real-time monitoring parameters in each set are traversed and calculated, and the average is taken to generate the first preset coating thickness real-time monitoring parameter and the second preset coating thickness real-time monitoring parameter.

[0020] Furthermore, in the system provided in the application embodiment, the search module 12 is also used for: Construct the preset coating monitoring space, wherein the coating monitoring space includes multiple sample space points, each sample space point corresponds to a sample spraying subtask information, and each sample space point has an identifier of a sample preset coating thickness real-time monitoring parameter; respectively input the first spraying subtask information and the second spraying subtask information into the preset coating monitoring space to obtain a first target space point and a second target space point; respectively extract the k sample space points closest to the first target space point and the second target space point from the multiple sample space points to obtain a first neighbor sample space point set and a second neighbor sample space point set, wherein k is an integer greater than or equal to 3; traverse and calculate the mean of the sample coating thickness real-time monitoring parameter set corresponding to the first neighbor sample space point set to obtain the first preset coating thickness real-time monitoring parameter; traverse and calculate the mean of the sample coating thickness real-time monitoring parameter set corresponding to the second neighbor sample space point set to obtain the second preset coating thickness real-time monitoring parameter.

[0021] In an embodiment of the present application, a three-dimensional coating monitoring space is first constructed based on the historical spraying task data, and the database storage technology is used to structure the storage of each historical spraying subtask information. Specifically, the coating type is mapped to the x-axis of the three-dimensional coordinate system, the average coating thickness is mapped to the y-axis, and the coating thickness uniformity is mapped to the z-axis, thereby generating sample space points. Each sample space point corresponds to a historical spraying task and is marked with sample preset coating thickness real-time monitoring parameters, such as monitoring frequency and window time information. Ultimately, these sample space points constitute a preset coating monitoring space.

[0022] Next, the retrieval module receives the first spraying subtask information, including parameters such as coating type, average coating thickness, and coating thickness uniformity. Through the coordinate mapping method, the first spraying subtask information is projected into the coating monitoring space and located at the first target space point corresponding to it. Similarly, the second spraying subtask information is input into the coating monitoring space in the same way to determine the second target space point. These target space points are the matching positions of the current spraying task and the historical tasks in terms of parameters, which serve as the basis for further retrieval.

[0023] In order to extract the sample most similar to the target point from the monitoring space, the k nearest neighbor algorithm is used to calculate the Euclidean distance between the target space point and all sample space points. The sample points are sorted according to the calculated distance, and the k sample points with the smallest distance are selected (k is an integer greater than or equal to 3). These sample points form the first nearest neighbor sample space point set and the second nearest neighbor sample space point set respectively.

[0024] Next, the monitoring parameters in the neighbor sample set are traversed and calculated. For the first neighbor sample space point set, the sample coating thickness real-time monitoring parameter corresponding to each sample point is extracted, and its mean is calculated, and the calculation result is used as the first preset coating thickness real-time monitoring parameter. Similarly, the same calculation is performed on the second neighbor sample space point set to obtain the second preset coating thickness real-time monitoring parameter.

[0025] Furthermore, in the system provided in the application embodiment, the search module 12 is also used for: Acquire a three-dimensional space coordinate system, wherein the x-axis of the three-dimensional space coordinate system is the coating type, the y-axis is the coating average thickness information, and the z-axis is the coating thickness uniformity information; acquire multiple sample spraying subtask information and corresponding multiple sample coating thickness real-time monitoring parameters; input the multiple sample spraying subtask information into the three-dimensional space coordinate system to obtain multiple sample space points, and use the multiple sample coating thickness real-time monitoring parameters to mark the multiple sample space points; obtain the preset coating monitoring space according to the marked multiple sample space points and the three-dimensional space coordinate system.

[0026] In the embodiment of the present application, a three-dimensional space coordinate system is first obtained, in which the x-axis represents the coating type, the y-axis represents the average coating thickness information, and the z-axis represents the coating thickness uniformity information. These three dimensions together define the characteristics of the coating task, where the coating type distinguishes coatings of different materials (such as anti-reflective coatings, anti-reflective coatings, etc.); the coating average thickness information is the target value of the overall thickness after spraying, in microns; and the coating thickness uniformity information indicates the uniformity of the coating thickness distribution.

[0027] Next, multiple sample spraying subtask information and its corresponding multiple sample coating thickness real-time monitoring parameters are obtained from the historical spraying task database. The sample spraying subtask information includes coating type, average coating thickness and coating thickness uniformity, which describes the key characteristics of the spraying task. At the same time, the monitoring parameters related to each task are extracted, such as sampling frequency, monitoring window time and target thickness range, and these parameters are recorded to provide reference for the subsequent monitoring process. Through data collection, a sample data set containing task characteristics and monitoring parameters is formed.

[0028] Subsequently, multiple sample spraying subtask information is input into the three-dimensional space coordinate system. By traversing each sample spraying subtask information, it is mapped to a point in the three-dimensional space according to the coating type (x-axis), average coating thickness (y-axis) and coating thickness uniformity (z-axis), and multiple sample space points are obtained. Each sample space point is then identified, and the corresponding coating thickness real-time monitoring parameters are attached to each sample point. The identification process associates each sample point with its sampling frequency, monitoring window time, and thickness target range parameters through an indexing mechanism.

[0029] After the identification is completed, multiple sample space points and the three-dimensional space coordinate system together constitute the preset coating monitoring space.

[0030] The first thickness monitoring module 13 configures parameters of the first spraying equipment according to the first spraying subtask information of the first spraying subtask, sprays the coating on the surface of the photovoltaic glass using the configured first spraying equipment, and monitors the coating thickness according to the first preset coating thickness real-time monitoring parameters within the first preset monitoring window to obtain a first thickness monitoring result set.

[0031] In the embodiment of the present application, the first thickness monitoring module configures the first spraying device according to the device operating parameters determined in the first spraying subtask information of the first spraying subtask. Parameter configuration refers to adjusting the operating parameters of the spraying device, such as spraying pressure, paint flow rate, and spraying area range.

[0032] After completing the equipment configuration, the first spraying equipment starts the spraying process to coat the photovoltaic glass surface. During the spraying process, the first thickness monitoring module starts thickness monitoring based on the first preset monitoring window. The first preset monitoring window is a time range that defines the start time and end time of monitoring, such as a time period from 5 seconds to 15 seconds after the start of spraying.

[0033] According to the first preset coating thickness real-time monitoring parameter, the monitoring module determines the sampling frequency (such as the number of measurements per second) and the measurement time interval (such as once every 100 milliseconds) within the monitoring window. Within the time range of the monitoring window, the thickness of the coating on the surface of the photovoltaic glass is continuously measured by a dedicated thickness measuring device, such as a laser thickness gauge or an ultrasonic thickness detector. These measurement data are recorded in chronological order to form a dynamic data sequence of the coating thickness. Finally, the data of the entire monitoring process is organized into a first thickness monitoring result set, including the coating thickness value at each time point in the monitoring window and its corresponding timestamp information.

[0034] The horizontal and vertical analysis module 14 performs a vertical compliance analysis and a horizontal correlation analysis on the first thickness monitoring result set to determine a first vertical influence coefficient and a first horizontal correlation influence coefficient.

[0035] In an embodiment of the present application, the horizontal and vertical analysis module first extracts the first coating average thickness information and the first coating thickness uniformity information in the first spraying subtask information. In the vertical compliance analysis, the horizontal and vertical analysis module calculates the difference between the thickness measurement value in the first thickness monitoring result set and the first coating average thickness information point by point to generate a first coating thickness deviation value set. The deviation value set is then screened for a central value to determine the first coating thickness deviation central value representing the overall deviation trend. At the same time, the fluctuation variance of the thickness deviation value set is calculated to obtain the first deviation variance, which is used to quantify the overall stability of the thickness deviation. Combining the thickness deviation central value and the deviation variance, the module completes the vertical compliance analysis and finally calculates the first vertical influence coefficient.

[0036] In the horizontal correlation analysis, the horizontal and vertical analysis module directly calculates the fluctuation variance of the thickness measurement values ​​of the first thickness monitoring result set to quantify the amplitude of the thickness variation between each monitoring point. According to the size of the fluctuation variance, the first horizontal correlation influence coefficient is determined.

[0037] Furthermore, in the system provided in the embodiment of the application, the horizontal and vertical analysis module 14 is also used for: Extract the first coating average thickness information and the first coating thickness uniformity information of the first spraying subtask information; perform a longitudinal compliance analysis on the first thickness monitoring result set according to the first coating average thickness information and the first coating thickness uniformity information to determine the first longitudinal influence coefficient; calculate the fluctuation variance of the first thickness monitoring result set to obtain the first transverse correlation influence coefficient.

[0038] In the embodiment of the present application, the first coating average thickness information and the first coating thickness uniformity information of the first spraying subtask information are first extracted. The first coating average thickness information is the target thickness value of the spraying task; the first coating thickness uniformity information is the requirement for coating distribution consistency.

[0039] In the vertical compliance analysis, the actual thickness value of each monitoring point is first extracted from the first thickness monitoring result set, compared with the average thickness information of the first coating, and the thickness deviation value is calculated point by point to form a thickness deviation value set. The thickness deviation value set is then statistically processed, and the overall deviation trend is extracted by calculating the central value. In addition, the degree of discreteness of the thickness deviation value set is quantified, the variance is calculated, and the fluctuation range of the data distribution is evaluated. The smaller the variance, the more concentrated the thickness data is distributed around the target value, and the lower the overall deviation. Combining the analysis results of the central value and the variance, the first vertical influence coefficient is finally calculated.

[0040] In the lateral correlation analysis, the spatial distribution of the thickness measurement data is further analyzed. By extracting the thickness values ​​of adjacent monitoring points in the first thickness monitoring result set one by one, the thickness difference between adjacent points is calculated to form an inter-point difference set, which is used to record the spatial variation of the coating thickness. The inter-point difference set is then statistically processed, and the stability of the thickness variation between adjacent monitoring points is quantified by calculating the variance. The smaller the variance, the more uniform the thickness variation and the more consistent the distribution of the coating on the surface. Finally, the first lateral correlation influence coefficient is obtained based on the calculation results.

[0041] Furthermore, in the system provided in the embodiment of the application, the horizontal and vertical analysis module 14 is also used for: A difference calculation is performed based on the first coating average thickness information and the first thickness monitoring result set to obtain a first coating thickness deviation value set; a concentration value screening is performed on the first coating thickness deviation value set to determine the first coating thickness deviation concentration value; the fluctuation variance of the first coating thickness deviation set is calculated to obtain a first deviation variance; a longitudinal compliance analysis is performed in combination with the first coating thickness deviation concentration value, the first deviation variance and the first coating thickness uniformity information to obtain the first longitudinal influence coefficient.

[0042] In the embodiment of the present application, the actual thickness value of each monitoring point is firstly extracted from the first thickness monitoring result set, and the difference is calculated with the first coating average thickness information to generate a first coating thickness deviation value set.

[0043] Next, the first coating thickness deviation value set is screened for a concentrated value to determine a main trend of the thickness deviation and obtain a first coating thickness deviation concentrated value.

[0044] Then, the fluctuation amplitude of the first coating thickness deviation value set is quantitatively analyzed to calculate the first deviation variance. Specifically, each deviation value is subtracted from the first coating thickness deviation concentration value to calculate its deviation degree, and then these deviation degrees are squared to eliminate the influence of positive and negative differences on the fluctuation analysis. Then, the squared data are accumulated and the accumulated results are averaged to obtain the first deviation variance.

[0045] After completing the calculation of the concentration value and deviation variance, the longitudinal compliance analysis is performed in combination with the first coating thickness deviation concentration value, the first deviation variance and the first coating thickness uniformity information. Specifically, these three features are input into the pre-built feedforward neural network model. The feedforward neural network performs a comprehensive analysis of the input features through multi-layer nonlinear mapping. The training data of the neural network model includes the coating thickness deviation concentration value, thickness deviation variance, and coating thickness uniformity information recorded in the historical spraying tasks as input features, and the corresponding longitudinal influence coefficient as the target output label. The longitudinal influence coefficient is provided by technical experts based on the actual quality performance of historical tasks, reflecting the longitudinal compliance level of the task. During the training process, the neural network optimizes the weights and bias values ​​through multiple forward propagations and back propagations, and learns the complex relationship between the input features and the longitudinal influence coefficient.

[0046] The fully trained feedforward neural network receives the feature input of the current task in the actual task and outputs the first longitudinal influence coefficient through calculation.

[0047] Through the above process, the first longitudinal influence coefficient is finally obtained.

[0048] Furthermore, in the system provided in the embodiment of the application, the horizontal and vertical analysis module 14 is also used for: Calculate the mean of the first coating thickness deviation value set to obtain the first coating thickness deviation mean; use the first coating thickness deviation mean as the initial weighted center, and iteratively update the initial weighted center in the first coating thickness deviation value set in combination with the weighted center update formula until the preset number of iterative updates is met, and use the last updated weighted center as the first coating thickness deviation concentration value.

[0049] In the embodiment of the present application, firstly, a mean is calculated from the first coating thickness deviation value set to obtain the first coating thickness deviation mean.

[0050] Then, the first coating thickness deviation mean is used as the initial weighted center, and the initial weighted center is iteratively updated in combination with the weighted center update formula. In each iteration, the center position is gradually moved toward the true center of the data distribution by redistributing the weights. The iterative update process continues until the preset number of iterative updates is met. The preset number of iterative updates is the maximum number of iterations set in advance, which is used to limit the computational cost of the iterative process and prevent efficiency from being reduced due to excessive iterations.

[0051] The updated weighted center obtained by the last calculation is used as the first coating thickness deviation concentration value.

[0052] Furthermore, in the system provided in the embodiment of the application, the horizontal and vertical analysis module 14 is also used for: Obtain a weighted center update formula, wherein the weighted center update formula is: ; in, To update the weight center, is a plurality of first coating thickness deviation values ​​in the first coating thickness deviation value set, is the i-th first coating thickness deviation value in the first coating thickness deviation value set, is the deviation of the first coating thickness from the mean, It is a weight kernel function built based on the Gaussian function.

[0053] In the embodiment of the present application, the weighted center update formula is obtained, and the weighted center update formula is ,in To update the weighted center, it means that in this iteration, the center value is recalculated based on all deviation values ​​and their weights. is a plurality of first coating thickness deviation values ​​in the first coating thickness deviation value set, is the i-th first coating thickness deviation value in the first coating thickness deviation value set, is the deviation of the first coating thickness from the mean, It is a weight kernel function built on the basis of Gaussian function, which is used to calculate the weight according to the distance between the current weighted center and each data point. The closer the distance is, the greater the weight is, and the farther the distance is, the smaller the weight is.

[0054] During the specific calculation, the first coating thickness deviation mean is used as the initial weighted center value to start the iterative calculation process. In each iteration, the current weighted center value is compared with each deviation value, and the distance between the two is calculated. In order to weight these distances, a weight function constructed by a Gaussian kernel function is used. After completing the weight assignment, the new weighted center value is calculated in combination with the weighted center update formula. The update formula multiplies all deviation values ​​with their corresponding weights to calculate the weighted sum; then the weighted sum is divided by the sum of all weights to obtain a new weighted center value. The iterative process continues, repeating the weight assignment and center update steps in each iteration. When the stop condition is met, the iteration ends, and the weighted center value obtained by the last calculation is determined as the first coating thickness deviation concentration value.

[0055] The second thickness monitoring module 15 adjusts the first preset coating thickness real-time monitoring parameter according to the size of the first longitudinal influence coefficient, obtains the first adjusted coating thickness real-time monitoring parameter, and performs real-time monitoring of the photovoltaic glass coating thickness of the first spraying subtask in the next preset monitoring window according to the first adjusted coating thickness real-time monitoring parameter.

[0056] In an embodiment of the present application, a plurality of historical data are first used as training samples, including historical longitudinal influence coefficients, historical preset coating thickness real-time monitoring parameters, and historical adjusted coating thickness real-time monitoring parameters. These data are input into a longitudinal influence network layer model constructed based on a feedforward neural network for supervised training. Through training, the complex relationship between the longitudinal influence coefficient and the real-time monitoring parameter adjustment is learned, and the network parameters are continuously optimized until the model converges to form a trained longitudinal influence network layer.

[0057] In the actual task, the second thickness monitoring module inputs the first longitudinal influence coefficient and the first preset coating thickness real-time monitoring parameter into the trained longitudinal influence network layer for analysis. The model calculates and outputs the first adjusted coating thickness real-time monitoring parameter based on the input data.

[0058] Finally, according to the first adjustment coating thickness real-time monitoring parameter, the photovoltaic glass coating thickness of the first spraying subtask is monitored in real time within the next preset monitoring window.

[0059] Furthermore, in the system provided in the embodiment of the application, the second thickness monitoring module 15 is also used for: Acquire multiple historical longitudinal influence coefficients, multiple historical preset coating thickness real-time monitoring parameters and multiple historical adjusted coating thickness real-time monitoring parameters as training data; use the training data to supervise the training of the network layer constructed based on the feedforward neural network, and update the network parameters according to the training output results until the training converges to obtain the trained longitudinal influence network layer; use the trained longitudinal influence network layer to analyze the first longitudinal influence coefficient and the first preset coating thickness real-time monitoring parameter to obtain the first adjusted coating thickness real-time monitoring parameter.

[0060] In an embodiment of the present application, firstly, a plurality of historical longitudinal influence coefficients, a plurality of historical preset coating thickness real-time monitoring parameters and a plurality of historical adjusted coating thickness real-time monitoring parameters are obtained from historical spraying task data as training data for the neural network model.

[0061] Then, these training data are used to supervise the training of the longitudinal influence network layer built based on the feedforward neural network. During the supervised training process, the training data is used for multiple forward propagation and back propagation. The predicted value is calculated by forward propagation, compared with the actual historical adjustment of the coating thickness real-time monitoring parameters, and the loss value (such as mean square error) is calculated. During the back propagation process, the network parameters are gradient updated according to the loss value, and the weights and bias values ​​are gradually optimized. The training process is repeated until the loss value converges, indicating that the model can accurately capture the mapping relationship between the input features and the target output. At this point, the trained longitudinal influence network layer is obtained.

[0062] Finally, the trained longitudinal influence network layer is used to analyze the first longitudinal influence coefficient of the current task and the first preset coating thickness real-time monitoring parameter, and the first adjusted coating thickness real-time monitoring parameter is output through calculation.

[0063] The monitoring parameter adjustment module 16 adjusts the second preset coating thickness real-time monitoring parameter according to the size of the first transverse correlation influence coefficient to obtain the second coating thickness influencing real-time monitoring parameter.

[0064] In the embodiment of the present application, the monitoring parameter adjustment module adjusts the second preset coating thickness real-time monitoring parameter according to the magnitude of the first transverse correlation influence coefficient. Specifically, by subtracting the difference of the first transverse correlation influence coefficient from 1 and then multiplying it by the second preset coating thickness real-time monitoring parameter, the second preset coating thickness real-time monitoring parameter is adjusted to obtain the second coating thickness real-time monitoring parameter.

[0065] The coating spraying module 17 configures the parameters of the second spraying equipment according to the second spraying subtask information of the second spraying subtask, and uses the configured second spraying equipment to spray the coating on the surface of the photovoltaic glass that has completed the first spraying subtask within the first preset monitoring window, and monitors the photovoltaic glass coating thickness in real time according to the second parameter affecting the real-time monitoring of the coating thickness.

[0066] In the embodiment of the present application, the coating spraying module first receives the second spraying subtask information of the second spraying subtask. The second spraying subtask information includes the coating type, the coating average thickness target value, and the coating thickness uniformity requirement.

[0067] According to the second spraying subtask information, the coating spraying module performs parameter configuration on the second spraying equipment. The second spraying equipment usually includes a spray gun, a spraying pressure control system, and a spraying flow rate adjustment module. The parameter configuration process includes adjusting the spraying pressure, setting the coating flow rate, and defining the spraying path.

[0068] After the equipment configuration is completed, the second spraying equipment is started to spray the second layer of coating on the photovoltaic glass surface that has completed the first spraying subtask within the first preset monitoring window. At the same time, during the second spraying task, the coating thickness is monitored in real time according to the second real-time monitoring parameter affecting the coating thickness.

[0069] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects: The present application obtains the first spraying subtask and the second spraying subtask of the target photovoltaic glass coating task, and the corresponding first spraying subtask information and the second spraying subtask information, wherein each spraying subtask information in the first spraying subtask information and the second spraying subtask information includes the coating type, the coating average thickness information, and the coating thickness uniformity information; respectively uses the first spraying subtask information and the second spraying subtask information as indexes to search in the preset coating monitoring space to obtain the first preset coating thickness real-time monitoring parameters and the second preset coating thickness real-time monitoring parameters; configures the parameters of the first spraying equipment according to the first spraying subtask information of the first spraying subtask, sprays the coating on the surface of the photovoltaic glass using the configured first spraying equipment, and monitors the coating thickness according to the first preset coating thickness real-time monitoring parameters within the first preset monitoring window to obtain a first thickness monitoring result set; and performs a first thickness monitoring The result set is subjected to vertical compliance analysis and horizontal correlation analysis to determine the first vertical influence coefficient and the first horizontal correlation influence coefficient; the first preset coating thickness real-time monitoring parameter is adjusted according to the size of the first vertical influence coefficient to obtain the first adjusted coating thickness real-time monitoring parameter, and the photovoltaic glass coating thickness of the first spraying subtask in the next preset monitoring window is monitored in real time according to the first adjusted coating thickness real-time monitoring parameter; the second preset coating thickness real-time monitoring parameter is adjusted according to the size of the first horizontal correlation influence coefficient to obtain the second coating thickness real-time monitoring parameter; the second spraying equipment is configured according to the second spraying subtask information of the second spraying subtask, and the second spraying equipment that has been configured is used to spray the coating on the photovoltaic glass surface that completes the first spraying subtask in the first preset monitoring window, and the photovoltaic glass coating thickness is monitored in real time according to the second coating thickness real-time monitoring parameter. The present invention solves the technical problem that the prior art cannot accurately monitor the coating thickness distribution, and dynamically adjusts the monitoring parameters and optimizes the spraying process through task information acquisition, coating monitoring parameter retrieval, spraying equipment configuration and real-time thickness monitoring, combined with vertical compliance analysis and horizontal correlation analysis, to achieve the technical effect of accurately monitoring the coating thickness of photovoltaic glass.

[0070] 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 and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] 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.

[0072] 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 real-time monitoring system for photovoltaic glass coating thickness, characterized in that: The system comprises: A task acquisition module, wherein the task acquisition module acquires a first spraying subtask and a second spraying subtask of a target photovoltaic glass coating task, and corresponding first spraying subtask information and second spraying subtask information, wherein each spraying subtask information in the first spraying subtask information and the second spraying subtask information includes a coating type, coating average thickness information, and coating thickness uniformity information; A retrieval module, wherein the retrieval module uses the first spraying subtask information and the second spraying subtask information as indexes, searches in a preset coating monitoring space, and obtains a first preset coating thickness real-time monitoring parameter and a second preset coating thickness real-time monitoring parameter; a first thickness monitoring module, wherein the first thickness monitoring module configures parameters of a first spraying device according to the first spraying subtask information of the first spraying subtask, sprays a coating on the surface of the photovoltaic glass using the configured first spraying device, and monitors the coating thickness according to the first preset coating thickness real-time monitoring parameters within a first preset monitoring window to obtain a first thickness monitoring result set; A horizontal and vertical analysis module, wherein the horizontal and vertical analysis module performs a vertical compliance analysis and a horizontal correlation analysis on the first thickness monitoring result set to determine a first vertical influence coefficient and a first horizontal correlation influence coefficient; a second thickness monitoring module, wherein the second thickness monitoring module adjusts the first preset coating thickness real-time monitoring parameter according to the size of the first longitudinal influence coefficient, obtains a first adjusted coating thickness real-time monitoring parameter, and performs real-time monitoring of the photovoltaic glass coating thickness of the first spraying subtask in the next preset monitoring window according to the first adjusted coating thickness real-time monitoring parameter; A monitoring parameter adjustment module, wherein the monitoring parameter adjustment module adjusts a second preset coating thickness real-time monitoring parameter according to the magnitude of the first lateral correlation influence coefficient to obtain a second coating thickness influencing real-time monitoring parameter; A coating spraying module, wherein the coating spraying module configures parameters of a second spraying device according to the second spraying subtask information of the second spraying subtask, utilizes the configured second spraying device to spray the coating on the surface of the photovoltaic glass that has completed the first spraying subtask within the first preset monitoring window, and monitors the photovoltaic glass coating thickness in real time according to the second parameter affecting the real-time monitoring of the coating thickness.

2. The real-time monitoring system for photovoltaic glass coating thickness according to claim 1, characterized in that: include: Constructing the preset coating monitoring space, wherein the coating monitoring space includes a plurality of sample space points, each sample space point corresponds to a sample spraying subtask information, and each sample space point has an identification of a sample preset coating thickness real-time monitoring parameter; Inputting the first spraying subtask information and the second spraying subtask information into the preset coating monitoring space respectively to obtain a first target space point and a second target space point; Extracting k sample space points closest to the first target space point and the second target space point from the multiple sample space points, respectively, to obtain a first neighbor sample space point set and a second neighbor sample space point set, where k is an integer greater than or equal to 3; Traversing and calculating the mean of the sample coating thickness real-time monitoring parameter set corresponding to the first neighboring sample space point set to obtain a first preset coating thickness real-time monitoring parameter; The mean of the sample coating thickness real-time monitoring parameter set corresponding to the second neighboring sample space point set is traversed and calculated to obtain the second preset coating thickness real-time monitoring parameter.

3. The real-time monitoring system for photovoltaic glass coating thickness according to claim 2, characterized in that: include: Obtain a three-dimensional space coordinate system, wherein the x-axis of the three-dimensional space coordinate system is the coating type, the y-axis is the coating average thickness information, and the z-axis is the coating thickness uniformity information; Obtaining multiple sample spraying subtask information and corresponding multiple sample coating thickness real-time monitoring parameters; Inputting the plurality of sample spraying subtask information into the three-dimensional space coordinate system to obtain a plurality of sample space points, and using the plurality of sample coating thickness real-time monitoring parameters to mark the plurality of sample space points; The preset coating monitoring space is obtained according to the marked multiple sample space points and the three-dimensional space coordinate system.

4. The real-time monitoring system for photovoltaic glass coating thickness according to claim 1, characterized in that: include: Extracting first coating average thickness information and first coating thickness uniformity information from the first spraying subtask information; Performing a longitudinal compliance analysis on the first thickness monitoring result set according to the first coating average thickness information and the first coating thickness uniformity information to determine a first longitudinal influence coefficient; The fluctuation variance of the first thickness monitoring result set is calculated to obtain a first lateral correlation influence coefficient.

5. The real-time monitoring system for photovoltaic glass coating thickness according to claim 4, characterized in that: include: Performing difference calculation based on the first coating average thickness information and the first thickness monitoring result set to obtain a first coating thickness deviation value set; Performing concentrated value screening on the first coating thickness deviation value set to determine a first coating thickness deviation concentrated value; Calculating the fluctuation variance of the first coating thickness deviation set to obtain a first deviation variance; A longitudinal compliance analysis is performed in combination with the first coating thickness deviation concentration value, the first deviation variance and the first coating thickness uniformity information to obtain the first longitudinal influence coefficient.

6. The real-time monitoring system for photovoltaic glass coating thickness according to claim 5, characterized in that: include: Calculating the mean of the first coating thickness deviation value set to obtain a first coating thickness deviation mean; The first coating thickness deviation mean is taken as the initial weighted center, and the initial weighted center is iteratively updated in the first coating thickness deviation value set in combination with the weighted center update formula until the preset number of iterative updates is met, and the last updated weighted center obtained is taken as the first coating thickness deviation concentration value.

7. The real-time monitoring system for photovoltaic glass coating thickness according to claim 6, characterized in that: include: Obtain a weighted center update formula, wherein the weighted center update formula is: ； in, To update the weight center, is a plurality of first coating thickness deviation values ​​in the first coating thickness deviation value set, is the i-th first coating thickness deviation value in the first coating thickness deviation value set, is the deviation of the first coating thickness from the mean, It is a weight kernel function built based on the Gaussian function.

8. The real-time monitoring system for photovoltaic glass coating thickness according to claim 1, characterized in that: include: Acquire multiple historical longitudinal influence coefficients, multiple historical preset coating thickness real-time monitoring parameters, and multiple historical adjusted coating thickness real-time monitoring parameters as training data; The training data is used to supervise the training of the network layer constructed based on the feedforward neural network, and the network parameters are updated according to the training output results until the training converges, thereby obtaining a trained longitudinal influence network layer; The first longitudinal influence coefficient and the first preset coating thickness real-time monitoring parameter are analyzed using the trained longitudinal influence network layer to obtain the first adjusted coating thickness real-time monitoring parameter.

Images