Capacitive touch screen conducting film laminating process optimization method and device and storage medium

Abstract

The invention discloses a capacitive touch screen conductive film laminating process optimization method, equipment and a storage medium, and relates to the technical field of touch screen manufacturing, the method comprises the steps of calibrating laminating equipment and generating initial laminating parameters based on material parameters of a capacitive touch screen conductive film, performing laminating prediction and dynamic optimization by using a self-adaptive control model, and performing dynamic optimization on the laminating parameters. And formulating and executing a lamination control strategy to finish accurate lamination of the conductive film. Finished product data are obtained through quality detection, a detection result is fed back to the model to optimize the fitting parameters, and intelligent dynamic adjustment and continuous improvement of the fitting process are achieved. The technical problems that in an existing capacitive touch screen conducting film attaching technology, attaching is not uniform and the waterproof and dustproof performance is poor due to the fact that parameters of a traditional frame attaching mode cannot be dynamically adjusted are solved, and the technical effect of improving the attaching uniformity and the waterproof and dustproof performance of a capacitive touch screen conducting film is achieved.

Description

Technical Field

[0001] The present application relates to the field of touch screen manufacturing technology, and in particular to a capacitive touch screen conductive film lamination process optimization method, equipment and storage medium. Background Art

[0002] With the development of electronic products towards thinness, lightness and high reliability, capacitive touch screens are widely used in various devices, and the conductive film bonding process has become a key link in touch screen manufacturing. The traditional frame bonding process has fixed parameters during the bonding process, and the bonding accuracy and uniformity are difficult to guarantee, which easily leads to gaps between the conductive film of the touch screen and the substrate, thereby reducing the waterproof and dustproof performance of the product. This process is more likely to cause the infiltration of water vapor and dust in harsh environments, affecting touch sensitivity and product life. In addition, the traditional frame bonding process lacks real-time parameter adjustment and finished product feedback mechanism, and has poor adaptability to different materials and bonding conditions. The process consistency and stability are difficult to meet the high-performance requirements of modern products. Therefore, how to break through the limitations of the frame bonding method, combine full bonding technology, optimize the pressure, temperature and speed control in the bonding process, and improve the bonding quality and environmental adaptability has become an urgent problem to be solved in the industry.

[0003] In the current related technologies, there are technical problems in the traditional frame lamination method in the capacitive touch screen conductive film lamination process, such as uneven lamination and poor waterproof and dustproof performance due to the inability to dynamically adjust parameters. Summary of the invention

[0004] This application provides a capacitive touch screen conductive film lamination process optimization method, equipment and storage medium, uses material parameters based on the capacitive touch screen conductive film, calibrates the lamination equipment and generates initial lamination parameters, uses an adaptive control model to predict and dynamically optimize lamination, and formulates and executes a lamination control strategy to achieve precise lamination of the conductive film. The finished product data is obtained through quality inspection, and the inspection results are fed back to the model to optimize the lamination parameters, so as to realize intelligent dynamic adjustment and continuous improvement of the lamination process, and achieve the technical effect of improving the lamination uniformity and waterproof and dustproof performance of the capacitive touch screen conductive film.

[0005] The present application provides a capacitive touch screen conductive film lamination process optimization method, including:

[0006] Based on the basic material parameters of the capacitive touch screen conductive film, the bonding equipment is calibrated to generate multiple initial bonding parameters; an adaptive control model is constructed, the multiple initial bonding parameters are synchronized to the adaptive control model, bonding prediction is performed according to the bonding process parameters of the capacitive touch screen conductive film, and multiple bonding control prediction information is obtained; the bonding of the capacitive touch screen conductive film is dynamically optimized according to the multiple bonding control prediction information, and a bonding control strategy is formulated; the bonding control strategy is executed to position and bond the capacitive touch screen conductive film, and bonding finished product information is generated, and the bonding finished product information is quality inspected to obtain finished product quality inspection data; the finished product quality inspection data is fed back to the adaptive control model for response, and an adaptive control optimization model is generated, and the bonding process parameters of the capacitive touch screen conductive film are intelligently optimized and updated through the adaptive control optimization model.

[0007] The present application also provides an electronic device, including:

[0008] The memory is used to store executable instructions; the processor is used to implement the capacitive touch screen conductive film laminating process optimization method when executing the executable instructions stored in the memory.

[0009] The present application also provides a computer-readable storage medium, comprising:

[0010] A computer program is stored thereon, and when the program is executed by a processor, a method for optimizing the laminating process of a conductive film of a capacitive touch screen is implemented.

[0011] The proposed capacitive touch screen conductive film lamination process optimization method, equipment and storage medium are first calibrated based on the material parameters of the capacitive touch screen conductive film and the initial lamination parameters are generated. The adaptive control model is used for lamination prediction and dynamic optimization, and the lamination control strategy is formulated and implemented to achieve the precise lamination of the conductive film. The finished product data is obtained through quality inspection, and the inspection results are fed back to the model to optimize the lamination parameters, so as to realize the intelligent dynamic adjustment and continuous improvement of the lamination process, and achieve the technical effect of improving the lamination uniformity and waterproof and dustproof performance of the capacitive touch screen conductive film. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0013] Figure 1 A schematic diagram of a process flow of a capacitive touch screen conductive film lamination process optimization method provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of a process flow of obtaining an adaptive control model for a capacitive touch screen conductive film lamination process optimization method provided in an embodiment of the present application;

[0015] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0017] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0018] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations 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 clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0019] The present application embodiment provides a method for optimizing the lamination process of a capacitive touch screen conductive film, such as Figure 1 As shown, the method includes:

[0020] Step S100, based on the material basic parameters of the capacitive touch screen conductive film, the laminating equipment is calibrated to generate multiple initial laminating parameters. Specifically, the capacitive touch screen conductive film has a variety of material basic parameters, including physical parameters (such as thickness, hardness, elastic modulus, thermal expansion coefficient), electrical parameters (such as conductivity, capacitance value) and chemical parameters (such as surface energy, chemical activity), etc. After obtaining and analyzing these parameters in depth, the laminating equipment is calibrated according to the characteristics of the conductive film. In terms of pressure calibration, the pressure system of the laminating equipment is adjusted according to the hardness, elastic modulus and thickness of the conductive film, including the upper limit of pressure, pressure sensor, pressure control mechanism and pressure distribution system to ensure that the pressure is sufficient and uniform during laminating. Temperature calibration is carried out according to the thermal expansion coefficient and laminating process requirements, the laminating temperature range is determined, and the temperature sensor and heating element are calibrated to ensure the stability and uniformity of the temperature. Speed ​​calibration needs to take into account the material properties of the conductive film, and adjust the moving speed of the laminating equipment according to its hardness and laminating accuracy requirements or flexibility and production efficiency requirements. Through these calibration processes, multiple initial bonding parameters are finally generated, including pressure value (numerical range or pressure curve), bonding temperature (initial temperature, fluctuation range, temperature gradient control), bonding speed (specific value or speed change curve), bonding time, vacuum degree, etc.

[0021] Step S200, construct an adaptive control model, synchronize the multiple initial fitting parameters to the adaptive control model, perform fitting prediction according to the fitting process parameters of the capacitive touch screen conductive film, and obtain multiple fitting control prediction information. Specifically, to construct an adaptive control model, it is necessary to select a suitable structure (such as neural network, fuzzy logic control, etc.) according to the characteristics of the capacitive touch screen conductive film fitting process. The design principle is to automatically adjust the control strategy according to the input parameters and feedback information. Initialize the model parameters (such as neural network weights, thresholds or fuzzy logic membership function parameters) during construction, and the initial values ​​can be determined according to experience or preset rules and adjusted later. Design a special parameter input interface to synchronize multiple initial fitting parameters (such as pressure, temperature, speed, etc.) to the model. Data preprocessing may be required before input, such as normalization to the [0, 1] interval to improve model training efficiency and accuracy. The bonding process parameters (such as pressure curves at different stages, temperature range, speed and time relationship) and initial bonding parameters are integrated as model inputs, and a mathematical model of the bonding process is constructed through a specific algorithm. The built-in prediction algorithm of the model (such as the neural network forward propagation algorithm) is used to predict the state of the conductive film at each moment of the bonding process (such as deformation, bonding quality in different areas). During the bonding process, strain gauge sensors, temperature sensor arrays and other highly sensitive and fast-responding sensors are used to collect key information such as deformation and temperature distribution in real time, and the information is fed back to the model to achieve closed-loop control. The model compares the prediction results. If there is a deviation, the prediction results are modified or the control strategy is adjusted (such as adjusting the heater power or bonding speed) according to the adaptive adjustment mechanism. Finally, multiple bonding control prediction information is obtained to provide a basis for subsequent operations.

[0022] In one possible implementation, Figure 2As shown, an adaptive control model is constructed, and the multiple initial bonding parameters are synchronized to the adaptive control model to perform bonding prediction according to the bonding process parameters of the capacitive touch screen conductive film to obtain multiple bonding control prediction information. Step S200 further includes step S210, calling a historical bonding data record log, and extracting multiple historical bonding parameters and multiple historical finished product quality data based on the historical bonding data record log, and the multiple historical bonding parameters correspond to the multiple historical finished product quality data. Specifically, a historical bonding data record log is retrieved from the storage system, which contains detailed information on the past capacitive touch screen conductive film bonding process. The log is processed to extract multiple historical bonding parameters, including pressure values ​​during bonding (including pressure magnitudes at different stages, pressure change rates, etc.), temperature settings (initial temperature, heating curve, constant temperature range, etc.), bonding speeds (speed adjustment of the whole and different bonding areas), and other relevant parameters of the bonding equipment (such as vacuum degree, bonding time, etc.). Multiple historical finished product quality data are extracted from the log, including electrical properties of the finished product (such as conductivity of the conductive film, capacitance value of the touch screen and its stability, etc.), physical properties (such as flatness after bonding, presence of bubbles or wrinkles, degree of bonding between the film and the substrate, etc.), and appearance quality (whether there are scratches, impurities, etc.). The correspondence between historical bonding parameters and historical finished product quality data is clarified, that is, a specific bonding parameter combination corresponds to a specific finished product quality situation, providing a basis for subsequent analysis.

[0023] Step S220: Adopting an adaptive precision control algorithm to analyze the plurality of historical bonding parameters and the plurality of historical finished product quality data, and determining a plurality of bonding-quality pairs. Specifically, an adaptive precision control algorithm is used to deeply analyze the extracted multiple historical fitting parameters and multiple historical finished product quality data, and the adaptive precision control algorithm is started to dynamically adjust the analysis accuracy according to the characteristics of the data. Before starting the analysis, the algorithm is initialized, including setting some initial precision ranges, adjustment steps, and convergence criteria. The parameters will be adaptively adjusted according to the actual situation of the data during the operation of the algorithm. The extracted multiple historical fitting parameters and multiple historical finished product quality data are preprocessed, including data normalization, mapping parameter values ​​of different magnitudes to a unified interval to avoid unreasonable effects on the analysis results due to excessively large or small values ​​of some parameters, and performing feature extraction operations. For example, for the fitting pressure parameter, its mean, variance, rate of change and other features can be extracted. For the conductivity in the finished product quality data, its fluctuation characteristics under different environments can be extracted. The preprocessing and feature extraction operations help the algorithm to better explore the potential relationships in the data. The algorithm conducts an in-depth analysis of the historical fitting parameters and historical finished product quality data based on the characteristics of the data and the current analysis accuracy. During the analysis process, the accuracy adjustment mechanism of the algorithm plays a role. If the data changes relatively slowly and the features are relatively simple, the algorithm will automatically improve the analysis accuracy, such as increasing the complexity of the fitting model or refining the data grouping. On the contrary, if the data fluctuates greatly and the features are complex, the algorithm will appropriately reduce the accuracy and adopt a more generalized analysis model. Through adaptive analysis, the algorithm can accurately capture the correlation between historical fitting parameters and historical finished product quality data. Based on the analysis results, each group of related historical fitting parameters and historical finished product quality data are combined to form multiple fitting-quality pairs. For example, a set of specific fitting pressure, temperature, and speed parameters and the corresponding conductivity, flatness, and appearance quality evaluation constitute a fitting-quality pair. The fitting-quality pair comprehensively and accurately reflects the impact of different fitting conditions on the quality of the finished product, providing key material for the subsequent data set division and model training.

[0024] Step S230, determine the data training set, data supervision set, and data verification set according to the multiple fit-quality pairs. Specifically, divide the data set according to the multiple fit-quality pairs that have been determined, follow the scientific and reasonable division principles, the goal is to ensure that each data set can play a specific role in the model training and evaluation process, while ensuring the independence and representativeness of the data, select a part from all fit-quality pairs as the data training set, the selection process must take into account the diversity and coverage of the data, try to include various types of fit conditions and corresponding quality results, for example, cover fitting cases under different pressure ranges, temperature ranges and speed combinations, as well as various finished product quality conditions from high quality to low quality, so that the training set can fully reflect the complex relationship between fit parameters and finished product quality, and provide rich samples for model learning, select a part from the remaining fit-quality pairs as the data supervision set, the role of the supervision set is to provide additional supervision information during the model training process. , help the model adjust parameters and avoid overfitting. When selecting the supervision set, we should pay attention to its complementarity with the training set. There should be a certain similarity to ensure the effectiveness of supervision, and there should be enough difference to give full play to the supervision role. For example, the supervision set can contain some fitting parameter combinations similar to those in the training set, but the corresponding finished product quality data may have slight differences. In this way, the model is guided to learn more accurate relationships. The remaining fit-quality pairs constitute the data validation set. The validation set is mainly used to evaluate the generalization ability of the model at different stages of model training. When selecting the validation set, we should ensure the independence of its data, that is, the fit-quality pairs in the validation set have no obvious overlap with the data in the training set and the supervision set. When the model performs well on the validation set, we can be more confident that the model has good generalization ability and can handle new data that has not been seen.

[0025] Step S240, supervised iterative control training is performed on the data training set according to the data supervision set to obtain multiple training results. Specifically, the data training set and the data supervision set are loaded into a training environment, which is built based on a specific machine learning or data analysis framework and has the ability to process large-scale data and run complex model training algorithms. In this environment, a model structure is prepared for training. The model can be built based on algorithms such as neural networks, support vector machines, and decision trees. The specific model selection depends on the characteristics of the fitting process and the nature of the data. In each iterative training, one or a group of fitting-quality pairs are selected from the data training set in turn as input data, which are input into the model to be trained. The model predicts the corresponding finished product quality data based on the input historical fitting parameters. Then, the predicted results are compared with the corresponding actual finished product quality data in the data supervision set, and the error between the predicted results and the actual results is calculated. A variety of error measurement methods can be used, such as mean square error (MSE), mean absolute error (MAE), etc. According to the calculated error value, the model parameters are adjusted using the model optimization algorithm. If it is a neural network model, the back propagation algorithm is usually used to adjust the parameters such as weights and biases in the network according to the error back propagation, so that the model can reduce the error in subsequent predictions. Repeat the above training steps and perform multiple iterative training on all data in the data training set. As the number of iterations increases, the model continuously adjusts parameters and gradually learns the intrinsic relationship between historical fitting parameters and historical finished product quality data. A set of training results will be obtained in each iteration, and the results reflect the model's degree of fit to the data and its predictive ability in the current training stage.

[0026] Step S250, perform fit verification on the multiple training results according to the data verification set, generate a verification token, obtain multiple verification training results according to the verification token, and when the multiple verification training results tend to converge, obtain the adaptive control model. Specifically, after the model completes a certain round of iterative training, use the data verification set to verify the model, input the fit-quality pairs in the data verification set into the trained model in sequence, obtain the model's prediction results for each fit-quality pair, compare the model's prediction results with the actual finished product quality data in the data verification set, and generate a verification token based on the comparison results. The verification token is an indicator or a group of indicators that comprehensively evaluates the performance of the model. For example, it can be accuracy (the ratio of the number of samples predicted to be correct to the total number of samples), recall (the ratio of the number of samples predicted to be positive and actually positive to the actual number of positive samples), F1 value (an indicator of comprehensive accuracy and recall), or other specific performance indicators related to the bonding process, such as bonding precision error, finished product quality Deviation, etc., according to the generated verification token, multiple verification training results are obtained, and the results reflect the performance of the model in the current verification stage. For example, if the verification token is accuracy, then different accuracy values ​​correspond to the model performance after different rounds of training, and the changing trend of multiple verification training results in the continuous verification process is observed. When the results tend to converge, that is, the performance indicators of the model on the data verification set no longer have obvious fluctuations, and meet the predetermined convergence standards (such as the accuracy reaches a certain threshold, the error is less than a set value, etc.), it indicates that the model has learned a stable and reliable fitting-quality relationship model. The obtained model is the adaptive control model we need, which can be used to accurately control and optimize the new capacitive touch screen conductive film bonding process.

[0027] In a possible implementation, an adaptive control model is constructed, the multiple initial lamination parameters are synchronized to the adaptive control model, and lamination prediction is performed according to the lamination process parameters of the capacitive touch screen conductive film to obtain multiple lamination control prediction information. Step S200 further includes step S260, synchronizing the multiple initial lamination parameters to the adaptive control model through the input layer, performing lamination analysis according to the multiple lamination-quality pairs and the multiple initial lamination parameters according to the lamination process parameters, and obtaining multiple lamination information, wherein the multiple lamination information includes lamination deformation information and lamination quality information. Specifically, multiple initial lamination parameters (including lamination pressure value, lamination temperature setting, lamination speed and other related equipment parameters, which are determined according to the basic material parameters of the capacitive touch screen conductive film during the calibration stage of the lamination equipment) enter the model through the input layer as input data of the adaptive control model, and the input layer can standardize parameters of different types and magnitudes to ensure that the model is correctly received and processed. The adaptive control model has learned the relationship between multiple fit-quality pairs and mastered the requirements of the fit process parameters during training. The fit-quality pairs reflect the historical relationship between different fit parameters and the quality of the final product, and the fit process parameters specify the range of ideal fit conditions. Within the model, fit analysis is carried out based on the input fit-quality pairs, initial fit parameters, and fit process parameters, and the fit process is simulated and calculated. For example, the influence of the current fit pressure on the fit quality is analyzed based on the ideal pressure curve in the fit process parameters, the initial fit pressure parameters, and the fit-quality pairs under similar pressure conditions in history. The analysis covers all aspects of the entire fit process, and ultimately multiple fit information is obtained, among which the fit deformation information is a quantitative description of the shape change of the capacitive touch screen conductive film during the fit process, which is crucial to evaluating the fit tightness and uniformity. The fit quality information is a comprehensive evaluation of the fit results, including whether there are bubbles, whether the electrical performance after fitting meets the standards, and other multi-dimensional quality indicators.

[0028] Step S270, feeding back the fitting deformation information to the data processing layer of the adaptive control model for control evaluation to generate a plurality of fitting scores. Specifically, the bonding deformation information is transmitted from the input-related part of the model to the data processing layer. The data processing layer is one of the core components of the adaptive control model and is responsible for processing and analyzing various feedback information. The information transmission channel is optimized to ensure the accuracy and timeliness of the data. In the data processing layer, the bonding deformation information is processed according to the preset control evaluation algorithm. The algorithm is established based on a large amount of experimental data and theoretical models, and can accurately evaluate the impact of the bonding deformation on the bonding quality. For example, if the bonding deformation exceeds a certain threshold, it may mean that the bonding pressure is uneven or the temperature is too high, resulting in excessive softening of the material, thereby affecting the bonding quality. Through control evaluation, multiple bonding scores are generated for each link of the bonding process. The bonding score is a quantitative evaluation of different aspects of the bonding process. For example, different scores can be given for bonding in different areas, or there are corresponding scores for different stages in the bonding process (such as initial bonding and stable bonding stages). The score can intuitively reflect the degree of deviation of the current bonding process from the ideal state.

[0029] Step S280, perform fitting prediction based on the multiple fitting scores combined with the fitting quality information, obtain the multiple fitting control prediction information and output data through the output layer. Specifically, the fitting prediction is performed based on the generated multiple fitting scores and the existing fitting quality information. The fitting score reflects the dynamic situation of the current fitting process, while the fitting quality information provides an overall quality benchmark. The combination of the two can more comprehensively consider various factors in the fitting process. For example, if the fitting score of a certain area is low, but the current fitting quality information shows that the overall electrical performance has not been significantly affected, the model can predict that the area may have problems in the subsequent use process and needs to be adjusted in time. Through the prediction algorithm in the model, the fitting score and the fitting quality information are comprehensively considered to generate multiple fitting control prediction information. The prediction information includes suggestions for adjusting various parameters in the future fitting process, such as whether it is necessary to increase or decrease The bonding pressure, bonding temperature, bonding speed, etc., as well as the prediction of possible quality problems, such as whether bubbles will appear, conductivity reduction, etc., the bonding control prediction information is output through the output layer, and the output layer converts the prediction information into a suitable format to interact with the external bonding control system. The output information can be directly used to adjust the parameters of the bonding equipment in real time, thereby achieving precise control of the bonding process. During the bonding process, the sensors installed on the equipment collect key information such as deformation and temperature distribution in real time, and feed it back to the adaptive control model to form a closed-loop control. The closed-loop control mechanism can continuously correct the model's prediction and control strategies to ensure that the bonding process is always moving in the direction of high quality.

[0030] Step S300, dynamically optimize the bonding of the conductive film of the capacitive touch screen according to the multiple bonding control prediction information, and formulate a bonding control strategy. Specifically, dynamically optimize the bonding of the conductive film of the capacitive touch screen according to the multiple bonding control prediction information and formulate a bonding control strategy, specifically, according to the prediction results of the adaptive control model, the bonding pressure is monitored in real time by the pressure sensor, if the pressure in a certain area is insufficient or too high, the control system sends a signal to the pressure regulating device to adjust, to ensure that the conductive film and the touch screen substrate are evenly bonded; the temperature sensor in the bonding area is used to monitor the temperature in real time, and according to the temperature change and the prediction information, the heater power is adaptively adjusted by the control system to maintain the temperature stability, because the temperature will affect the material properties and the bonding quality; at the same time, the bonding pressure and temperature changes are comprehensively considered to adjust the bonding speed in real time, when the pressure and temperature are appropriate, the speed is appropriately increased to improve the efficiency, and when the two are abnormal, the speed is reduced to ensure the quality, and the pressure, temperature, and speed adjustment measures are integrated to form a bonding control strategy with high dynamic adaptability, to ensure that the bonding process is in the best state, and to achieve high-quality bonding and efficient production.

[0031] Step S400, execute the lamination control strategy to position and laminat the capacitive touch screen conductive film, generate the lamination product information, perform quality inspection on the lamination product information, and obtain the finished product quality inspection data. Specifically, execute the lamination control strategy to position and laminat the capacitive touch screen conductive film, first accurately place the capacitive touch screen conductive film and the touch screen substrate at the specified position of the lamination device, and the device completes parameter initialization according to the strategy. Determine the relative position of the two through a high-precision positioning system of optics, mechanics or a combination of the two, so that the position error is controlled at the micron level. When laminating, first make the two contact initially with lower pressure and moderate speed according to the strategy, increase the pressure and stabilize the temperature according to the strategy during the process, until the lamination of the entire lamination area is completed, and generate the lamination product information including lamination parameter records, time information, positioning accuracy data and equipment operation status. Check the appearance for scratches, impurities, bubbles, and whether the lamination edge is neatly warped by visual or high-resolution optical inspection equipment, measure the conductivity of the conductive film, the capacitance value of the touch screen and its distribution, and the electrical insulation performance with professional electrical testing equipment, and detect the physical properties by measuring the thickness, performing stretching or peeling tests, etc. The appearance, electrical and physical performance test data are sorted and summarized, and the finished product quality evaluation indicators such as conductivity value, number of bubbles, whether the appearance is qualified, whether the fit is firm, etc. are classified to obtain the finished product quality test data.

[0032] In one possible implementation, the bonding control strategy is executed to position and bond the capacitive touch screen conductive film, generate bonding product information, perform quality inspection on the bonding product information, and obtain finished product quality inspection data. Step S400 further includes step S410, performing plane analysis based on the capacitive touch screen conductive film to construct a bonding space coordinate system. Specifically, the planar characteristics of the conductive film of the capacitive touch screen are analyzed, and its length, width and other dimensions are accurately measured to the micron level, because the dimensional information is extremely critical for subsequent positioning. At the same time, a high-precision flatness measuring instrument is used to analyze the surface flatness of the conductive film to detect whether there are slight undulations or distortions, because they will affect the quality of bonding. The geometric center position of the conductive film must also be determined, which is used as an important reference point for constructing a coordinate system. A two-dimensional plane coordinate system is established based on the length and width directions of the conductive film with the geometric center as the origin. If it is necessary to consider the thickness change during the bonding process or the operation of the bonding equipment in three-dimensional space, a three-dimensional space coordinate system is established, and the direction perpendicular to the plane of the conductive film is set as the third dimension. When establishing the coordinate system, it is necessary to ensure that the direction of the coordinate axis matches the movement direction and measurement direction of the bonding equipment to facilitate subsequent coordinate calculation and alignment operations. The coordinate axis unit is determined according to the measurement accuracy, usually at the micron level to ensure coordinate accuracy.

[0033] Step S420, synchronize the conductive film and the capacitive touch screen to the fitting space coordinate system for alignment, and generate multiple fitting positioning coordinates. Specifically, the capacitive touch screen and the conductive film are included in the constructed fitting space coordinate system, and they are fixed at the corresponding positions of the fitting device with the help of a positioning device, and then the position information of the two is converted into coordinate values ​​in the coordinate system by a sensor, and it is necessary to ensure that their initial positions in the coordinate system are accurate, because a small deviation may cause inaccurate fitting. Then, a high-precision alignment system based on optical principles (which can be achieved by emitting a laser beam or using an optical camera) is used to align the capacitive touch screen and the conductive film. The system adjusts the positions of the two by identifying the positions of the tiny marking points set at the edges or specific positions of the two in the coordinate system, so that their coordinates are as close to the ideal alignment state as possible, and continuous measurement and adjustment are required during the alignment process until the preset alignment accuracy requirements are met. When the capacitive touch screen and the conductive film are aligned, multiple fitting positioning coordinates are generated according to their positions in the fitting space coordinate system. These coordinates not only cover the center coordinates of the two as a whole, but also include the coordinate points of the edges and key areas. The number and distribution of coordinate points will be determined according to the fitting accuracy requirements and the shape and size of the conductive film and the capacitive touch screen. Usually, when the shape is complex, the size is large, or the fitting accuracy requirements are high, more positioning coordinate points are required.

[0034] Step S430, positioning calibration is performed according to the multiple fitting positioning coordinates to determine the fitting positioning data. Specifically, according to the generated multiple fitting positioning coordinates, the position of the capacitive touch screen and the conductive film is accurately calibrated, and a micro-displacement adjustment device is used. The device can adjust the position of the capacitive touch screen and the conductive film on a scale of microns or even smaller. For each fitting positioning coordinate point, its actual coordinate is compared with the ideal alignment coordinate. If there is a deviation, the micro-displacement adjustment device is used to make fine adjustments in the corresponding direction. For example, if a certain coordinate point has a deviation in the x-axis direction, it is adjusted by the micro-displacement adjustment mechanism in the x-axis direction to return the coordinate point to the ideal position. After completing the calibration of all fitting positioning coordinate points, the final fitting positioning data is determined. The data includes the accurate coordinate value of each calibrated coordinate point, the adjustment amount information during the calibration process, and the overall position deviation information after the calibration is completed. The fitting positioning data fully reflects the final position state of the capacitive touch screen and the conductive film before the fitting, and provides an accurate positioning basis for the subsequent fitting operation.

[0035] Step S440, according to the laminating positioning data, the laminating device is started to execute the laminating control strategy to laminat the conductive film of the capacitive touch screen, and the laminating product information is generated. Specifically, the laminating positioning data is input into the control system of the laminating device, and the control system starts each execution component accordingly, such as starting the pressure control system to prepare to apply the laminating pressure according to the preset pressure curve, starting the temperature control system to adjust the laminating area temperature to the appropriate initial temperature, and starting the mobile control system to prepare to perform the laminating operation according to the predetermined trajectory and speed. The laminating device laps the conductive film of the capacitive touch screen according to the laminating control strategy. During the process, the pressure control system applies corresponding pressure at different stages according to the pressure parameters in the strategy to ensure that the conductive film and the capacitive touch screen are closely attached. The temperature control system maintains temperature stability in real time to ensure that the material properties are not affected by temperature changes. The mobile control system moves the two according to the predetermined trajectory and speed, so that they gradually complete the laminating in the entire laminating area. At the same time, the laminating process is dynamically adjusted according to real-time feedback information such as pressure changes and temperature fluctuations to ensure quality. After the bonding is completed, the bonding product information is generated, including parameter records such as pressure value, temperature value, moving speed and position at each moment in the bonding process, as well as the finished product quality information such as whether there are bubbles, flatness, bonding strength, etc. after the bonding is completed.

[0036] In one possible implementation, the bonding control strategy is executed to position and bond the capacitive touch screen conductive film, generate bonding product information, perform quality inspection on the bonding product information, and obtain finished product quality inspection data. Step S400 further includes step S450, performing feature analysis on the capacitive touch screen conductive film according to the historical bonding data record log, generating multiple feature parameters, and formulating multiple quality inspection standards based on the multiple feature parameters. Specifically, the historical bonding data record logs containing a large number of past capacitive touch screen conductive film bonding processes and product-related data are analyzed. From the perspective of bonding process, the changes in parameters such as pressure, temperature, and bonding time during the bonding of different batches of conductive films are analyzed. From the perspective of material properties, the influence of conductive film material composition, thickness, hardness, etc. on the bonding quality is studied. Statistical analysis methods are used to calculate statistical quantities such as the mean, variance, maximum, and minimum values ​​of each parameter to find out the distribution pattern. For example, the mean and variance of the conductive film resistance value in different batches are analyzed to understand its stability. Correlation analysis and other methods are used to determine the relationship between different parameters, such as the correlation between bonding pressure and the conductive performance of the finished product. Based on this, multiple characteristic parameters are generated, covering physical characteristic parameters such as the average thickness, hardness, and surface roughness of the conductive film. Electrical characteristic parameters such as the average resistance value, capacitance value and change rate of different regions of the conductive film, and process characteristic parameters such as the average pressure in the bonding process, temperature variation range, and bonding time, etc., comprehensively describe the key characteristics of the production and use of capacitive touch screen conductive films. Quality inspection standards are then formulated based on the generated multiple characteristic parameters. For physical characteristic parameters, the qualified thickness interval is determined based on the functional requirements of the conductive film and the thickness range of historical high-quality products. For electrical characteristic parameters, the upper and lower resistance limits are set based on the performance requirements of the touch screen and the resistance range of products with good conductive performance in the past. For process characteristic parameters, the pressure, temperature and time standards in the bonding process are formulated based on the bonding parameter range of historical stable production of high-quality products, thereby providing a clear basis for subsequent product quality inspections.

[0037] Step S460, based on the information of the finished product, the capacitive touch screen conductive film is tested and analyzed according to the multiple quality inspection standards, and multiple test items are determined. Specifically, the finished product information covers various data after the capacitive touch screen conductive film produced this time is bonded, including bonding parameter records and finished product appearance. Based on this information and the established quality inspection standards, the capacitive touch screen conductive film is fully tested and analyzed, and the conductive performance test items are determined from the perspective of conductive performance to check whether the conductive film can meet the conductive requirements of the touch screen, ensure that the current is evenly distributed on the conductive film, and achieve accurate touch function; for the transmittance test items, considering the display effect of the touch screen, use professional transmittance detection equipment to measure the transmittance of the conductive film to ensure that it does not affect the display; in the durability test items, simulate the frequent touch, temperature change, humidity change and other environmental conditions and operating conditions when the touch screen is used for a long time, evaluate the performance stability of the conductive film, and then combine with other contents in the quality inspection standards to determine specific test items such as resistance uniformity, bonding integrity, adhesion test, appearance quality, etc., and comprehensively evaluate the product quality.

[0038] Step S470, performing quality tests on the capacitive touch screen conductive film according to the multiple test items, generating multiple quality inspection reports, wherein the multiple quality inspection reports correspond to the multiple test items. Specifically, for each test item, a corresponding test device and method are used to perform quality tests on the capacitive touch screen conductive film. In the conductivity test, a high-precision resistance measuring instrument is used to measure multiple points on the surface of the conductive film to obtain resistance data to evaluate its uniformity and stability. In the transmittance test, the conductive film is placed in the transmittance test equipment to measure the transmittance values ​​under different wavelengths of light. The durability test is to place the conductive film on a test platform that simulates the actual use environment, and detect performance changes after a certain number of simulated touch, temperature and humidity cycles. The resistance uniformity test uses professional resistance scanning equipment to record in detail the distribution of resistance values ​​in different areas of the conductive film surface to evaluate the uniformity. The bonding integrity test uses optical detection instruments or ultrasonic detection equipment to detect whether there are defects such as gaps and bubbles in the bonding area to ensure quality. The adhesion test equipment is used to quantitatively evaluate the bonding strength between the conductive film and the substrate to ensure that it does not fall off during use. The appearance quality inspection is to carefully check the surface of the conductive film for scratches, impurities or other defects through visual inspection combined with high-resolution microscopes and other equipment. The corresponding quality inspection report is generated according to the results of each test item. For example, the resistance uniformity report records in detail the resistance value, average value, standard deviation and change trend of each test point on the surface of the conductive film. The bonding integrity report contains the number, size and position of gaps and bubbles in the bonding area. The adhesion test report gives the bonding strength value. The appearance quality report describes the length, depth, number and impurity type and distribution of scratches. Each quality inspection report is closely related to a specific test item and comprehensively reflects the quality status of the capacitive touch screen conductive film in this aspect.

[0039] Step S480, based on the multiple quality inspection reports, the finished product impact analysis of the capacitive touch screen conductive film is performed to obtain multiple impact coefficients. Specifically, a comprehensive analysis is performed on multiple quality inspection reports to evaluate the degree of impact of the quality problems reflected in each inspection item on the performance of the finished product of the capacitive touch screen conductive film. For the resistance uniformity report, the impact of uneven resistance values ​​on the touch accuracy and response speed of the touch screen is analyzed. If the resistance value in some areas is too high or too low, it may cause inaccurate touch or local touch failure, affecting the performance of the finished product; in terms of fitting integrity, the impact of gaps or bubbles on the display effect and durability of the touch screen is analyzed, and the impact on the refraction and reflection of light and the delamination problems that may be caused during long-term use are considered to determine the degree of impact on the quality of the finished product; for the adhesion test results, the risk of falling off caused by insufficient bonding strength between the conductive film and the substrate during use and the degree of damage to the touch screen function are evaluated; for appearance quality issues, the impact of scratches and impurities on the visual effect, touch sensitivity and long-term stability of the touch screen is considered. By establishing a mathematical model or an empirical evaluation method, an impact coefficient is determined for each quality inspection item. This coefficient represents the weight of the impact of quality issues on the quality of finished products. For example, the impact coefficient of conductivity as a key performance indicator may be higher because it directly determines whether the touch screen can work properly, while the impact coefficient of relatively minor appearance defects that do not affect the function and long-term stability of the touch screen may be lower. These impact coefficients accurately quantify the impact of each quality problem on the finished product.

[0040] Step S490, the multiple quality inspection reports are associated and integrated according to the multiple influence coefficients to obtain the finished product quality inspection data. Specifically, according to the obtained multiple influence coefficients, the multiple quality inspection reports are associated and integrated, and the data in each quality inspection report is multiplied by its corresponding influence coefficient, so that the data of different test items are weighted based on the degree of influence on the quality of the finished product. For example, for the resistance value data in the resistance uniformity report, after multiplying its influence coefficient, the importance of resistance uniformity to the quality of the finished product is highlighted. Through association and integration, all weighted quality inspection data are aggregated together to form a comprehensive and integrated finished product quality inspection data set, which not only contains the original data of each quality inspection item, but also takes into account their different degrees of influence on the quality of the finished product, and can accurately and objectively reflect the overall quality status of the capacitive touch screen conductive film, and provide a strong basis for product quality evaluation, improvement and decision-making.

[0041] Step S500, the finished product quality inspection data is fed back to the adaptive control model for response, and an adaptive control optimization model is generated. The bonding process parameters of the capacitive touch screen conductive film are intelligently optimized and updated through the adaptive control optimization model. Specifically, a dedicated data feedback channel from the finished product quality inspection module to the adaptive control model is established in the bonding process system to ensure accurate and timely data transmission, follow a specific communication protocol, and perform format matching and preprocessing on the finished product quality inspection data, including format conversion, noise removal and outlier processing, to ensure reliable data quality. After receiving the data, the adaptive control model conducts a comprehensive analysis, classifies and analyzes it according to different quality indicators, starts a parameter adjustment mechanism, traces the bonding process parameters related to the quality problem, determines its potential impact based on the built-in algorithm, and then adjusts the model structure or parameters, integrates new algorithms and rules, and generates an adaptive control optimization model. The optimization model optimizes and calculates the bonding process parameters (such as pressure, temperature, speed, time, etc.) based on the finished product quality inspection data and its own algorithm, and accurately and promptly transmits the calculated updated values ​​to the bonding equipment control system. The control system adjusts the bonding process accordingly to achieve intelligent optimization and update. Subsequent bonding process data is fed back to the model to form a closed-loop control with continuous improvement.

[0042] In a possible implementation, the finished product quality inspection data is fed back to the adaptive control model for response, and an adaptive control optimization model is generated. The bonding process parameters of the capacitive touch screen conductive film are intelligently optimized and updated through the adaptive control optimization model. Step S500 further includes step S510, in which the finished product quality inspection data is fed back to the adaptive control model to extract the bonding parameters of the capacitive touch screen conductive film. Specifically, a reliable data transmission link is established from the finished product quality inspection link to the adaptive control model to ensure the integrity and consistency of the data transmission process, avoid data loss or damage, and accurately feed back the finished product quality inspection data covering the electrical, physical, appearance quality and other aspects of the capacitive touch screen conductive film after bonding to the adaptive control model. The model has a special data receiving module for identifying and receiving these data. After receiving the data, the adaptive control model starts the parameter extraction program. Through internal specific algorithms and data processing logic, it mines out parameters related to the bonding of the capacitive touch screen conductive film from a large amount of quality inspection data, including pressure values ​​such as pressure distribution in different areas during bonding, temperature conditions such as the temperature change curve of the entire bonding process and temperature settings at different stages, speed parameters such as the speed adjustment of the bonding equipment in different areas and the moving speed, as well as physical parameters related to the bonding equipment such as vacuum degree and bonding time, providing valuable information for analyzing the bonding process.

[0043] Step S520, traverse the finished product quality inspection data and the fitting parameters for correlation analysis, and generate multiple correlation coefficients. Specifically, in the adaptive control model, data is prepared for correlation analysis, and the finished product quality inspection data and the extracted fitting parameters are organized and stored in the form of arrays, matrices or data tables that support efficient data access and calculation. Then start the correlation analysis algorithm, comprehensively traverse and analyze the finished product quality inspection data and fitting parameters, calculate the correlation between each quality inspection index (such as finished product conductivity) and each fitting parameter (such as pressure, temperature, speed, etc.), and use Pearson correlation coefficient calculation method, Spearman rank correlation coefficient calculation method and other mathematical methods to obtain the correlation value between each pair of data and parameters that reflects the strength of the linear or nonlinear relationship. Finally, multiple correlation coefficients are generated based on the analysis results, and their value range is between -1 and 1. The absolute value close to 1 indicates a strong correlation, and close to 0 indicates a weak correlation, so as to clearly understand the impact of each fitting parameter on the quality of the finished product.

[0044] Step S530, optimize the bonding process parameters according to the multiple correlation coefficients to generate bonding process optimization parameters. Specifically, the optimization target of the bonding process parameters is determined according to the generated multiple correlation coefficients. When a bonding parameter is strongly correlated with a key finished product quality indicator (the absolute value of the correlation coefficient is close to 1), the bonding parameter is adjusted to improve the quality of the relevant finished product as a goal. For example, if the bonding temperature is strongly correlated with the finished product electrical performance indicator and the current electrical performance has problems, the optimization goal is to adjust the bonding temperature parameter to improve the electrical performance. Based on the optimization target, the bonding process parameters are optimized using a suitable optimization algorithm (such as an algorithm based on gradient descent, a genetic algorithm, a simulated annealing algorithm, etc.). Taking the optimization of the bonding pressure parameter by the gradient descent algorithm as an example, the algorithm will calculate the gradient direction based on the relationship between the pressure parameter and the finished product quality indicated by the correlation coefficient, and adjust the pressure parameter in the direction of improving the finished product quality. When adjusting, the influence of other related parameters and process constraints (such as the adjustable range of pressure, the impact on the equipment, etc.) will be considered to ensure that the optimized parameters are feasible in actual operation. The bonding process parameters are adjusted through the optimization algorithm to generate the bonding process optimization parameters. These optimization parameters are improvements on the original parameters. The correlation between the finished product quality inspection data and the bonding parameters is taken into account, which can more effectively improve the quality of the finished product. For example, the optimized bonding pressure parameters may increase or decrease in some areas, the bonding temperature curve may be more finely adjusted, and the bonding speed may have new set values ​​at different stages. These optimization parameters can provide specific guidance for subsequent bonding process improvements.

[0045] Step S540, the bonding process optimization parameters are merged with the multiple historical bonding parameters, the multiple historical finished product quality data are updated according to the fusion results, and multiple bonding-quality optimization pairs are generated. Specifically, the generated bonding process optimization parameters are merged with multiple historical bonding parameters. This fusion is not a simple addition or replacement, but a comprehensive treatment based on a certain strategy, such as assigning different weights according to the reliability and effectiveness of the historical bonding parameters, and then weighted averaging with the optimization parameters, giving higher weights to the stable and effective parameters in the historical bonding, and determining the appropriate weights for the new optimization parameters according to their rationality and ability to address the current quality issues. Through this weighted fusion method, the new optimization information is combined with historical experience to form a new set of bonding parameters. Multiple historical finished product quality data are updated according to the fused bonding parameters. Because the new parameters will affect the quality of the finished product, it is necessary to use the existing quality assessment model and method combined with the fused parameters to simulate and calculate or predict the historical finished product quality data. For example, when the pressure parameter changes after the fusion, the data of the finished product quality indicators such as conductivity and bonding firmness under the new pressure conditions are recalculated according to the model of the influence of pressure on the finished product quality, and the updated historical finished product quality data are obtained. Based on the updated historical finished product quality data and the fused fitting parameters, multiple fit-quality optimization pairs are generated. Each optimization pair consists of a set of fused fitting parameters and the corresponding updated finished product quality data. These optimization pairs reflect the expected quality of the finished product under the new parameter settings, and can more accurately reflect the current state of process improvement than the original fit-quality pairs, providing a more valuable data basis for further optimization of models and processes.

[0046] Step S550, update the data training set according to the multiple fit-quality optimization pairs, obtain the data optimization training set to correct the adaptive control model, and generate the adaptive control optimization model. Specifically, use the newly generated multiple fit-quality optimization pairs to update the data training set, add these optimization pairs to the original training set, and adjust the conflicting or redundant parts with the new data. If some data of the new fit-quality optimization pairs are significantly different from the data under the same conditions in the original training set, it is necessary to further analyze the reasons, and it may be necessary to delete inaccurate data in the original training set or verify and correct the new data, so that the data training set can more comprehensively and accurately reflect the relationship between the fitting process parameters and the quality of the finished product, and improve the quality of the training set. The updated data optimization training set contains richer and more accurate fit-quality information, and its data distribution is more reasonable, covering more process conditions and quality results, which can provide more sufficient sample space for model learning, and help improve the model's generalization ability and adaptability to different process conditions. The adaptive control model is corrected by using the data optimization training set. During the training process, the fit-quality optimization pairs in the optimized training set are used as input data. The model parameters (such as the weights and biases of the neural network model, the membership function parameters of the fuzzy logic model, etc.) are adjusted to make the model better fit the new data. During the training, a variety of training algorithms and optimization methods such as the back propagation algorithm and the stochastic gradient descent algorithm can be used to continuously adjust the parameters until the model performs best on the optimized training set. The corrected model is the adaptive control optimization model, which can more accurately predict the quality of the finished product based on the fitting process parameters, and provide more precise control and optimization for the capacitive touch screen conductive film bonding process.

[0047] In a possible implementation, the bonding process parameters are optimized according to the multiple correlation coefficients to generate bonding process optimization parameters, and step S530 further includes step S531, determining the optimization objective function based on the multiple correlation coefficients. Specifically, the multiple correlation coefficients calculated previously are analyzed, and the correlation coefficients reflect the degree of association between the finished product quality inspection data and the bonding parameters. By observing the size and positive and negative of each correlation coefficient, the relationship between the bonding parameters and the quality indicators that have a greater impact on the quality of the finished product is determined. For example, if it is found that the absolute value of the correlation coefficient between the bonding pressure and the bonding uniformity index of the finished product is large, it means that the bonding pressure has a significant effect on the bonding uniformity. According to the analysis results of the correlation coefficient, the optimization objective function is determined. Since the goal is to improve the bonding quality, the optimization objective function is set to minimize the bonding uniformity error or adhesion deviation and other indicators that are closely related to the bonding quality. For example, when the bonding uniformity is critical to the quality of the finished product, the optimization objective function is defined as minimizing the bonding uniformity error, that is, by adjusting the bonding process parameters, the conductive film is bonded more evenly on the touch screen, reducing quality problems caused by uneven bonding, such as local poor conductivity or the appearance of bubbles.

[0048] Step S532, introduce parameter constraints, randomly select the bonding process parameters according to the parameter constraints, and generate an initial parameter population. Specifically, the parameter constraints are introduced based on the physical limitations of the actual bonding process and the equipment performance. For example, the upper and lower limits of the bonding pressure are set. This is because too much bonding pressure may damage the conductive film or the touch screen substrate, and too little pressure cannot guarantee a good bonding effect. Similarly, upper and lower limits are set for the bonding speed, temperature, and electrostatic control strength. Too fast a bonding speed may lead to inaccurate bonding, too high or too low a temperature may affect the performance of the material, and improper electrostatic control strength may adsorb impurities and affect the bonding quality. The parameter constraints ensure that the generated bonding process parameters are feasible in actual operation. The bonding process parameters are randomly selected within the range of the parameter constraints. For example, multiple pressure values ​​are randomly generated within the upper and lower limits of the bonding pressure, and corresponding values ​​are randomly selected within the set speed, temperature and electrostatic control intensity ranges. The randomly selected bonding process parameters are combined together to form multiple parameter combinations. Each parameter combination is an individual, and many such individuals constitute the initial parameter population. The initial parameter population provides an initial search space for the subsequent optimization process.

[0049] Step S533, evaluate the initial parameter population according to the optimization objective function to generate multiple fitness values. Specifically, each parameter combination in the initial parameter population is substituted into the optimization objective function, and for each parameter combination, its situation in the bonding process is simulated, and the bonding quality result generated under the parameter combination is calculated according to the optimization objective function (such as minimizing the bonding uniformity error or adhesion deviation). It is necessary to use the existing bonding process model and quality evaluation method, combined with the given parameter combination, to predict the size of the bonding uniformity error or adhesion deviation, and generate a fitness value for each parameter combination according to the calculation result of the optimization objective function. The fitness value represents the degree of pros and cons of the parameter combination in achieving the optimization goal (such as reducing the bonding uniformity error or adhesion deviation). For example, if a parameter combination can make the bonding uniformity error very small, then its fitness value is high; conversely, if a parameter combination leads to a large bonding uniformity error, its fitness value is low. In this way, each individual in the initial parameter population is assigned a fitness value, and these fitness values ​​will be used for subsequent selection and cross-validation operations.

[0050] Step S534, cross-validate the initial parameter population based on the multiple fitness values ​​to generate multiple bonding process parameter groups, each bonding process parameter of the multiple bonding process parameter groups has a bonding optimization effect. Specifically, according to the generated multiple fitness values, a selection operation is performed on the initial parameter population, and individuals with higher fitness values ​​are selected, because the parameter combinations corresponding to these individuals perform better in achieving the optimization goal. For example, individuals corresponding to parameter combinations that can reduce the bonding uniformity error or adhesion deviation are selected. The selection operation simulates the process of natural selection, so that excellent individuals have more opportunities to participate in the subsequent reproduction (cross-validation) process, and the selected individuals are cross-validated. Cross-validation is the process of generating new parameter combinations by exchanging some parameter values. For example, for two selected parameter combinations (individuals), one or more parameter positions can be randomly selected, and then the parameter values ​​of the two individuals at these positions can be exchanged to generate a new parameter combination. Through multiple such cross-operations, multiple new bonding process parameter groups are generated. The newly generated parameter groups inherit some characteristics of the excellent individuals and generate new possibilities through cross-validation. Each parameter group has a certain bonding optimization effect, that is, it can reduce the bonding uniformity error or adhesion deviation to a certain extent.

[0051] Step S535, screening and reorganizing the multiple bonding process parameter groups according to the multiple bonding optimization effects to generate the bonding process optimization parameters. Specifically, the generated multiple bonding process parameter groups are screened according to the bonding optimization effect of each parameter group, that is, their actual performance in reducing the bonding uniformity error or adhesion deviation. For example, each parameter group is re-substituted into the optimization objective function for calculation, and their optimization effects are compared. The parameter group that can significantly reduce the bonding uniformity error or adhesion deviation is selected, and the parameter group that has no obvious effect or may even cause the quality problem to worsen is eliminated. The screened parameter groups are reorganized. During the reorganization process, the parameter values ​​in the parameter group can be fine-tuned to further optimize the parameter combination. For example, if it is found that the bonding pressure in a certain parameter group can achieve a good optimization effect within a certain range, but there is still room for improvement, the pressure value can be adjusted more finely within the range. Through the screening and reorganization operations, the bonding process optimization parameters are finally generated. The parameters can optimize the bonding process to the greatest extent and improve the bonding quality under the premise of meeting the parameter constraints.

[0052] The embodiment of the present application uses the material parameters of the conductive film of the capacitive touch screen to calibrate the bonding equipment and generate the initial bonding parameters, uses the adaptive control model to predict and dynamically optimize the bonding, and formulates and executes the bonding control strategy to complete the precise bonding of the conductive film. The finished product data is obtained through quality inspection, and the inspection results are fed back to the model to optimize the bonding parameters, so as to realize the intelligent dynamic adjustment and continuous improvement of the bonding process, and achieve the technical effect of improving the bonding uniformity and waterproof and dustproof performance of the conductive film of the capacitive touch screen.

[0053] Based on the foregoing embodiments, the embodiments of the present application further provide an electronic device and a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of the electronic device, it can implement the method described in any of the foregoing embodiments.

[0054] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing an implementation of the present invention. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. The electronic device is in the form of a general computing device, and its components may include but are not limited to an input device 301, a processor 302, a memory 303, and an output device 304. Among them, the processor 302 may be one or more; the memory 303 may include a computer-readable medium and at least one program product, and the program product has a set (at least one) of program modules, which are configured to perform the functions of each embodiment of the present application.

[0055] The memory 303 shown in the embodiment of the present invention may adopt any combination of one or more computer-readable media; the computer-readable storage medium may be, but is not limited to, an infrared, semiconductor system, device or device, or any combination of the above, for storing software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the capacitive touch screen conductive film bonding process optimization method in the embodiment of the present invention. The processor 302 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 303, that is, realizing the above-mentioned capacitive touch screen conductive film bonding process optimization method.

[0056] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does 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.

Claims

1. A capacitive touch screen conductive film lamination process optimization method, characterized in that: The method comprises: Based on the basic material parameters of the capacitive touch screen conductive film, the bonding equipment is calibrated to generate multiple initial bonding parameters; Constructing an adaptive control model, synchronizing the multiple initial lamination parameters to the adaptive control model, performing lamination prediction according to the lamination process parameters of the capacitive touch screen conductive film, and obtaining multiple lamination control prediction information; Performing dynamic optimization of lamination of the capacitive touch screen conductive film according to the plurality of lamination control prediction information, and formulating a lamination control strategy; Executing the lamination control strategy to position and laminate the capacitive touch screen conductive film, generating finished lamination product information, performing quality inspection on the finished lamination product information, and obtaining finished product quality inspection data; The finished product quality inspection data is fed back to the adaptive control model for response, and an adaptive control optimization model is generated. The bonding process parameters of the capacitive touch screen conductive film are intelligently optimized and updated through the adaptive control optimization model.

2. The capacitive touch screen conductive film lamination process optimization method according to claim 1, characterized in that: The adaptive control model is constructed, and the method includes: Retrieving a historical laminating data record log, and extracting a plurality of historical laminating parameters and a plurality of historical finished product quality data based on the historical laminating data record log, wherein the plurality of historical laminating parameters and the plurality of historical finished product quality data have a corresponding relationship; Adopting an adaptive precision control algorithm to analyze the plurality of historical lamination parameters and the plurality of historical finished product quality data to determine a plurality of lamination-quality pairs; Determine a data training set, a data supervision set, and a data verification set according to the plurality of fit-quality pairs; Performing supervised iterative control training on the data training set according to the data supervision set to obtain multiple training results; The multiple training results are fit-verified according to the data verification set to generate a verification token, and multiple verification training results are obtained according to the verification token. When the multiple verification training results tend to converge, the adaptive control model is obtained.

3. The capacitive touch screen conductive film lamination process optimization method according to claim 2, characterized in that: The multiple initial lamination parameters are synchronized to the adaptive control model to perform lamination prediction according to the lamination process parameters of the capacitive touch screen conductive film to obtain multiple lamination control prediction information, the method comprising: Synchronizing the multiple initial bonding parameters to the adaptive control model through the input layer, performing bonding analysis according to the multiple bonding-quality pairs and the multiple initial bonding parameters according to the bonding process parameters, and obtaining multiple bonding information, wherein the multiple bonding information includes bonding deformation information and bonding quality information; Feeding back the fitting deformation information to the data processing layer of the adaptive control model for control evaluation to generate a plurality of fitting scores; Based on the multiple fitting scores and the fitting quality information, a fitting prediction is performed, and the multiple fitting control prediction information is obtained and outputted as data through the output layer.

4. The capacitive touch screen conductive film lamination process optimization method according to claim 1, characterized in that: Executing the lamination control strategy to position and laminate the capacitive touch screen conductive film to generate lamination product information, the method includes: Based on the conductive film of the capacitive touch screen, plane analysis is performed to construct a fitting space coordinate system; Synchronize the conductive film and the capacitive touch screen to the laminating space coordinate system for alignment, and generate a plurality of laminating positioning coordinates; Perform positioning calibration according to the multiple fitting positioning coordinates to determine fitting positioning data; The laminating device is started according to the laminating positioning data to execute the laminating control strategy to laminate the conductive film of the capacitive touch screen, and the laminating finished product information is generated.

5. The capacitive touch screen conductive film lamination process optimization method according to claim 2, characterized in that: Performing quality inspection on the finished product information to obtain finished product quality inspection data, the method includes: Performing feature analysis on the capacitive touch screen conductive film according to the historical lamination data record log to generate a plurality of feature parameters, and formulating a plurality of quality inspection standards based on the plurality of feature parameters; Based on the information of the finished product, the capacitive touch screen conductive film is tested and analyzed according to the multiple quality inspection standards to determine multiple test items; Performing quality testing on the capacitive touch screen conductive film according to the multiple test items to generate multiple quality inspection reports, wherein the multiple quality inspection reports correspond to the multiple test items; Performing a finished product impact analysis of the capacitive touch screen conductive film based on the multiple quality inspection reports to obtain multiple impact coefficients; The multiple quality inspection reports are associated and integrated according to the multiple influence coefficients to obtain the finished product quality inspection data.

6. The capacitive touch screen conductive film lamination process optimization method according to claim 2, characterized in that: Feeding back the finished product quality detection data to the adaptive control model for response and generating an adaptive control optimization model, the method includes: Feeding back the finished product quality inspection data to the adaptive control model to extract the lamination parameters of the capacitive touch screen conductive film; Traversing the finished product quality inspection data and the fitting parameters to perform correlation analysis and generate multiple correlation coefficients; Optimizing the bonding process parameters according to the multiple correlation coefficients to generate bonding process optimization parameters; Merging the bonding process optimization parameters with the multiple historical bonding parameters, updating the multiple historical finished product quality data according to the fusion result, and generating multiple bonding-quality optimization pairs; The data training set is updated according to the multiple fitting-quality optimization pairs, and the data optimization training set is obtained to modify the adaptive control model to generate the adaptive control optimization model.

7. The method for optimizing the lamination process of a capacitive touch screen conductive film according to claim 6, characterized in that: The bonding process parameters are optimized according to the multiple correlation coefficients to generate bonding process optimization parameters, the method comprising: determining an optimization objective function based on the plurality of correlation coefficients; Introducing parameter constraints, randomly selecting the bonding process parameters according to the parameter constraints, and generating an initial parameter population; Evaluate the initial parameter population according to the optimization objective function to generate multiple fitness values; Cross-validating the initial parameter population based on the multiple fitness values ​​to generate multiple bonding process parameter groups, each bonding process parameter in the multiple bonding process parameter groups has a bonding optimization effect; The plurality of bonding process parameter groups are screened and reorganized according to a plurality of bonding optimization effects to generate the bonding process optimization parameters.

8. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; The processor is used to implement the capacitive touch screen conductive film lamination process optimization method according to any one of claims 1 to 7 when executing the executable instructions stored in the memory.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the capacitive touch screen conductive film lamination process optimization method according to any one of claims 1 to 7 is implemented.

Images