Optical adhesive material production process optimization method

Abstract

The application relates to an optical adhesive production process optimization method in the information technology field, which comprises the following steps: obtaining initial formula data and production process parameters of optical adhesive, extracting dielectric constant related indexes and coating thickness distribution characteristics from the initial formula data and production process parameters; generating distribution mapping according to the dielectric constant related indexes and the coating thickness distribution characteristics, determining a dielectric constant high area and a thickness uneven area; adjusting formula component proportions according to the distribution mapping, generating optimized formula data; updating a production process flow by using the adjusted coating process parameters, collecting actual coating data, and determining a deviation value; adjusting production process parameters according to the deviation value, generating corrected process parameters; evaluating adhesion effects through the corrected process parameters, generating a supplementary adjustment scheme, and integrating all parameters to generate a final production process protocol.

Description

Technical Field

[0001] This invention relates to the field of information technology, and in particular to an optimization method for the production process of optical adhesive materials. Background Technology

[0002] In the fields of modern electronic products and communication technology, optical adhesives serve as key bonding materials for display and touchscreen components, and their performance directly affects the display effect and signal transmission quality. Especially in high-frequency communication scenarios, the low dielectric properties of optical adhesives become crucial for ensuring signal integrity and reducing interference, making their research and development and manufacturing processes paramount.

[0003] However, the industry still faces numerous challenges in the production and application of this material, requiring breakthroughs to meet the growing market demand. Current optical adhesive production methods are mostly segmented operations, lacking effective coordination between stages, resulting in low overall production efficiency. A deeper problem lies in the insufficient ability to optimize material properties and dynamically adjust process parameters during production, making it difficult to ensure both product quality and high-efficiency production. This limitation not only increases time and resource costs but also makes it difficult for products to fully meet the specific requirements of emerging fields such as high-frequency communication. Focusing on the technical level, the core challenge lies in how to reduce the dielectric constant of the optical adhesive through process improvements while ensuring thickness uniformity during production. The dielectric constant directly determines the degree of interference the material causes to electrical signals; if this indicator cannot be effectively reduced, the application value of the product in high-frequency environments will be significantly reduced. Thickness uniformity is a key factor affecting the adhesion effect and optical performance of the adhesive layer; poor control can lead to uneven display effects or even defects. There is a close relationship between the two: reducing the dielectric constant often requires the introduction of special materials or adjustment of the formulation, but this may change the fluidity and coating characteristics of the adhesive, thus bringing new challenges to thickness control.

[0004] Therefore, optimizing the production process to reduce the dielectric constant of optical adhesives while ensuring uniform coating thickness has become a key issue in improving product performance and production efficiency. Taking a real-world business scenario as an example, in the production of optical adhesives for 5G device displays, a high dielectric constant can lead to signal delays or interference, while uneven coating thickness may cause localized screen adhesion failures or display abnormalities, directly impacting device reliability and user experience. This issue not only concerns the improvement of the material's performance but also involves the overall coordination and technological innovation of the production process, requiring a systematic solution across the entire chain from material formulation to production processes to meet the industry's urgent need for high-performance optical adhesives. Summary of the Invention

[0005] This invention provides a method for optimizing the manufacturing process of optical adhesive materials, mainly including:

[0006] The process involves acquiring initial formulation data and production process parameters for optical adhesives, extracting dielectric constant-related indicators and coating thickness distribution characteristics from these data, generating a distribution map based on these indicators, and identifying regions with high dielectric constants and uneven thickness. The formulation component ratios are adjusted according to the distribution map to generate optimized formulation data. The coating process is simulated using the optimized formulation data to obtain a simulated thickness distribution, and the coating process parameters are adjusted accordingly to obtain adjusted coating process parameters. The production process flow is updated using the adjusted coating process parameters, actual coating data is collected, and deviation values ​​are determined. The production process parameters are adjusted based on the deviation values ​​to generate corrected process parameters. The bonding effect is evaluated using the corrected process parameters, a supplementary adjustment plan is generated, and all parameters are integrated to generate the final production process protocol. Furthermore, the step of extracting dielectric constant-related indicators and coating thickness distribution characteristics from the initial formula data and production process parameters includes: extracting dielectric constant-related indicators from the initial formula data to obtain coating thickness data from the production process parameters; identifying regions with high dielectric constants by comparing the dielectric constant-related indicators with a preset threshold; calculating thickness distribution characteristics based on the coating thickness data to determine regions with uneven thickness; analyzing the regions with high dielectric constants and regions with uneven thickness using a classification algorithm to generate a feature dataset; grouping the feature dataset using a clustering algorithm to determine material uniformity verification points and obtain a verification dataset; and adjusting the coating thickness distribution characteristics based on the verification dataset to generate the final distribution mapping data. Furthermore, the step of adjusting the proportions of formulation components for the distribution map to generate optimized formulation data includes: extracting data from regions with high dielectric constants from the distribution map; using an optimization algorithm to iteratively process the proportions of formulation components corresponding to the data in the regions with high dielectric constants to generate preliminary proportion combinations; using the preliminary proportion combinations to reduce variable indicators, implementing formulation optimization for the regions with high dielectric constants, and determining an iterative optimization loop; obtaining component proportion verification data in the iterative optimization loop; using the optimization algorithm to iteratively process the verification data to generate optimized data; adjusting the proportion variables according to the optimized data, and outputting the final optimized formulation data.Furthermore, the step of simulating the coating process using the optimized formulation data to obtain the simulated thickness distribution includes: extracting the proportions and physical property parameters of each component from the optimized formulation data; using a computational fluid dynamics model, with the physical property parameters as boundary conditions, and combining them with the initial coating process parameters to perform numerical simulation and obtain the simulated thickness distribution field; extracting the mean and standard deviation of the thickness from the simulated thickness distribution field to calculate the thickness uniformity index; comparing the thickness uniformity index with a preset threshold to determine whether the uniformity requirement is met; if the thickness uniformity index does not reach the preset threshold, then adjusting the initial coating process parameters according to the recommended adjustment direction based on the pre-established physical property-process correlation model to generate a new set of parameters to be verified; and obtaining the final adjusted coating process parameters through iterative simulation and judgment. Furthermore, the step of updating the production process flow using the adjusted coating process parameters, collecting actual coating data, and determining deviation values ​​includes: updating the production process flow using the adjusted coating process parameters; collecting actual coating thickness data and dielectric constant readings using a real-time monitoring module to generate a raw dataset; extracting the average thickness and average dielectric constant from the raw dataset; generating a deviation value sequence by comparing the average thickness and average dielectric constant with the target index; extracting outliers from the deviation value sequence; if the outliers exceed a preset threshold, triggering a quality traceability record and generating a coating batch log; and analyzing the deviation distribution pattern based on the coating batch log to determine the process consistency index. Furthermore, the step of adjusting the production process parameters based on the deviation value to generate corrected process parameters includes: collecting signal integrity test data from the production line; determining the degree of integrity degradation by comparing the signal integrity test data with a preset threshold; if the degree of integrity degradation exceeds the preset threshold, extracting influencing factors through a batch quality tracking module, analyzing the correlation between the influencing factors, and generating a correction increment sequence; activating a feedback loop based on the correction increment sequence to incrementally adjust the production process parameters and generate an updated parameter set; monitoring the subsequent coating process through the updated parameter set, judging the signal improvement result, and generating corrected process parameters. Furthermore, the step of evaluating the adhesion effect and generating a supplementary adjustment plan through the modified process parameters includes: obtaining adhesion strength data and layer thickness uniformity data from the modified process parameters; determining the adhesion effect level by comparing the adhesion strength data and layer thickness uniformity data with preset standards; extracting coating temperature parameters and coating pressure parameters as influencing factors from production batch records; analyzing the correlation weight of the coating temperature parameters and coating pressure parameters with the adhesion effect level to generate a parameter adjustment increment sequence; activating a feedback loop according to the parameter adjustment increment sequence to adjust the coating temperature parameters and coating pressure parameters, generating an updated process parameter set; collecting new adhesion strength data through the updated process parameter set, judging the improvement results, and generating a supplementary adjustment plan.Furthermore, the step of integrating all parameters to generate the final production process protocol includes: obtaining all parameters from the supplementary adjustment scheme; using an integration module to fuse the parameters and generate an initial production process protocol; determining dynamic adjustment rules for each stage of the initial production process protocol; monitoring the dielectric constant value through the dynamic adjustment rules; if the dielectric constant value is higher than a preset threshold, activating the dynamic adjustment rules to update the thickness distribution parameters; and performing production process optimization through the updated thickness distribution parameters to generate a final production process protocol that maintains a uniform thickness distribution.

[0007] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0008] To address the challenges of high dielectric constant and uneven coating thickness in optical adhesive manufacturing, this invention proposes a comprehensive solution that optimizes process parameters and formulation. The method extracts dielectric constant and thickness distribution features, uses a classification algorithm to generate a distribution map, and accurately locates problem areas. For areas with high dielectric constants, an optimization algorithm iteratively adjusts the formulation ratio to reduce key indicators. Simultaneously, the coating process is simulated and process parameters are fine-tuned to ensure thickness uniformity. Through real-time monitoring and feedback loops, deviations are corrected and adhesion is optimized, ultimately generating a production process protocol with dynamically adjustable rules. This invention integrates all parameters through an integrated module, achieving synergistic optimization of maintaining low dielectric constants and uniform thickness distribution, significantly improving the performance and production stability of optical adhesives, and providing technical assurance for high-quality production. Attached Figure Description

[0009] Figure 1 This is a flowchart of an optimization method for the production process of optical adhesive materials according to the present invention;

[0010] Figure 2 This is a schematic diagram of the framework of step S101 in the optical adhesive material production process optimization method of the present invention;

[0011] Figure 3 This is a schematic diagram of step S102 in an optical adhesive material manufacturing process optimization method of the present invention.

[0012] Figure 4 This is a schematic diagram of step S103 in an optical adhesive material manufacturing process optimization method of the present invention;

[0013] Figure 5 This is a schematic diagram of step S104 in the optical adhesive material production process optimization method of the present invention. Detailed Implementation

[0014] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] like Figures 1-5 This embodiment of an optimization method for the production process of optical adhesive materials may specifically include:

[0016] Step S101: Obtain the initial formula data and production process parameters of the optical adhesive material, extract dielectric constant related indicators and coating thickness distribution characteristics from them, and use a classification algorithm to analyze the characteristics to obtain the distribution mapping of regions with high dielectric constant and uneven thickness.

[0017] Initial formulation data and production process parameters of the optical adhesive material are obtained. Dielectric constant-related indicators and coating thickness distribution characteristics are extracted from the data to obtain a feature dataset. A classification algorithm is used to analyze the feature dataset. By comparing the dielectric constant indicators with preset thresholds, regions with high dielectric constants and regions with uneven thickness are identified, resulting in a preliminary distribution map. The preliminary distribution map is clustered using the K-means algorithm. Points in the distribution map are grouped to determine material uniformity verification points, obtaining a verification dataset. The coating thickness distribution characteristics are adjusted based on the verification dataset to obtain the final distribution map of regions with high dielectric constants and regions with uneven thickness.

[0018] In one embodiment, the initial formulation data for the optical adhesive includes the proportions of its main components, such as the specific weight percentages of the resin matrix, curing agent, and additives, which are obtained from a production database. Production process parameters cover temperature control, stirring time, and curing conditions, such as a stirring speed set at 300 revolutions per minute and a curing temperature of 80 degrees Celsius. These data ensure the stability of the adhesive in optical applications.

[0019] It should be noted that initial formulation data helps to trace the basic electrical and physical properties of the adhesive, while process parameters directly affect the uniformity of the final product.

[0020] Specifically, the process of extracting dielectric constant-related parameters first involves measuring the capacitance value of the optical adhesive sample. The dielectric constant is a measure of a material's ability to store electrical energy in an electric field, and is usually calculated using the bridge method or the resonance method.

[0021] For example, in a laboratory environment, a sample of adhesive material is placed in a parallel-plate capacitor, a voltage of a specific frequency is applied, the capacitance change is recorded, and then the dielectric constant is calculated using a formula. Relevant indicators include the average dielectric constant, standard deviation, and peak value, which are extracted from multi-point measurement data. The specific process involves collecting measurement data from different regions of the sample to form a dataset, then calculating the dielectric constant at each point, and statistically analyzing the data to identify deviations from the normal range. These extracted indicators reflect the insulating performance of the adhesive material in optical devices such as displays. If the dielectric constant is too high, it may cause signal interference and affect the device's operating efficiency. Furthermore, the extraction of coating thickness distribution characteristics is based on laser scanning or ultrasonic measurement techniques. Coating thickness refers to the thickness of the layer formed by the adhesive material on the substrate, and its distribution characteristics include the average thickness, variance, and spatial gradient.

[0022] For example, on a production line, a laser thickness gauge is used to scan the surface of the coated adhesive material, acquiring gridded thickness data points, each corresponding to a specific coordinate position. Then, an interpolation method is used to generate a thickness distribution map, from which statistical characteristics of uneven areas are calculated, such as the proportion of areas with thickness deviations exceeding 5 micrometers. This feature extraction helps identify defects in the production process, such as thickness fluctuations caused by unstable coating machine speeds, thereby ensuring optical transparency and uniformity when optical adhesives are used for lens bonding.

[0023] Preferably, when analyzing the extracted features using a classification algorithm, a Support Vector Machine (SVM) or a Decision Tree algorithm can be selected. These algorithms use dielectric constant indices and thickness distribution features as input vectors for training and classification. For example, an SVM constructs a hyperplane to separate data points of different categories. First, the model is trained on a historical dataset. Input features include points with a high dielectric constant threshold set to greater than 3.5, and areas with uneven thickness defined as deviations exceeding 10%. Then, the algorithm outputs classification labels, identifying samples with high and uneven dielectric constants. Through this analysis, the model can handle high-dimensional features, achieve accurate region segmentation, and provide data support in the quality control of optical adhesives.

[0024] In one possible implementation, the distribution mapping of regions with high dielectric constant and uneven thickness is obtained through visualization tools.

[0025] For example, the classification results can be overlaid onto a two-dimensional coordinate graph of the adhesive material, using color coding to represent different areas. Red marks areas with high dielectric constants, and blue indicates areas with uneven thickness. This mapping, generated from the algorithm output, covers the entire surface of the adhesive sample, helping production personnel adjust process parameters, such as lowering the curing temperature to reduce dielectric constant fluctuations.

[0026] For example, in scenarios where optical adhesives are used for bonding mobile phone screens, the above method can be extended to batch production monitoring. First, formula data and process parameters from multiple batches are acquired. Then, features are extracted and classified to generate a mapping map, which is used to provide real-time feedback for adjusting the coating speed, thereby maintaining product consistency.

[0027] Understandably, this technical solution is applicable in the field of optical adhesives, such as in the production of optical filters, where feature analysis is used to optimize thickness distribution and achieve uniform coating.

[0028] Step S102: Based on the distribution mapping, adjust the formulation component ratio of the optical adhesive material for regions with high dielectric constant, and process the ratio combination through an optimization algorithm to determine the optimized formulation data, wherein the optimization algorithm iteratively processes the ratio variable to reduce dielectric constant-related indicators.

[0029] Data on regions with high dielectric constants are extracted based on the distribution mapping. An optimization algorithm is used to iteratively process the corresponding formulation components to obtain preliminary ratio combinations. These preliminary ratio combinations are then used to reduce variable indices, and material formulation optimization is implemented for the high-dielectric-constant regions, establishing an iterative optimization cycle. Component ratio verification data from this iterative optimization cycle is obtained, and the optimization algorithm iteratively processes this verification data to obtain optimized data. The dielectric constant is controlled using this optimized data, and the ratio variables are adjusted for the final formulation output to obtain optimized formulation data.

[0030] In one implementation, based on regions of high dielectric constant identified by distribution mapping, the current formulation composition data of the optical adhesive is first collected, such as the weight proportions of main components like the polymer matrix, crosslinking agent, and filler; this data is obtained from production records. For the high-conductivity regions, the adjustment process involves modifying the proportions of specific components, such as increasing the filler proportion to affect the material's electrical properties.

[0031] It should be noted that the distribution mapping provides region-specific guidance to ensure that adjustments are targeted.

[0032] Specifically, when adjusting the proportions of components in an optical adhesive formulation, the regional characteristics indicated by the mapping, such as the coordinates of locations with high dielectric constants, are considered. By analyzing the adhesive samples corresponding to these locations, the indicators that need to be reduced, such as the average value or deviation, are determined. One possible approach is to manually make an initial modification to the proportions, for example, reducing the crosslinking agent proportion from its original value by a certain percentage, and then verifying the performance of the adjusted sample. This initial adjustment provides initial input for subsequent optimization algorithms. Further, the combination of proportions is processed by an optimization algorithm that uses an iterative method to handle the variables.

[0033] For example, the algorithm treats the component proportions as a variable vector, such as the polymer matrix proportion as variable x, the crosslinking agent as y, and the filler as z. The iterative process starts from the initial proportions and gradually adjusts these variables, for example, calculating the effect of the variable changes on the dielectric constant index in each iteration and updating the vector.

[0034] Preferably, a gradient descent-like method is used, wherein the algorithm calculates the gradient direction of the variable and moves in the direction of reducing the index, for example, through multiple iterations until a preset condition is met.

[0035] In one embodiment, when determining the optimized formulation data, the algorithm outputs the final ratio combination, for example, adjusting the polymer matrix to 40%, the crosslinking agent to 15%, and the filler to 45%. This output is based on the convergence result of the iterative processing, ensuring that the variable adjustments meet the goal of reducing dielectric constant-related indicators.

[0036] Understandably, this process is implemented in scenarios where optical adhesives are used to bond display devices, such as for optimizing the formulation of screen adhesives. In one implementation, the iterative processing of the optimization algorithm specifically includes an initialization phase, an update phase, and a termination phase. During initialization, variable boundaries are set, for example, the total proportion is set to 100%. In the update phase, the adjustment step size for each variable is calculated, for example, the step size value is derived based on historical iteration data and then applied to the vector. During termination, it is checked whether the metric is below a threshold, such as the number of iterations reaching an upper limit or the rate of change being less than a set value. This process ensures that the proportion combinations are optimized step-by-step.

[0037] For example, in the scenario where optical adhesives are used in the assembly of optical lenses, for areas where the distribution mapping is too high, the algorithm iteratively processes the proportional variable. First, it extracts the index value from the mapping data, and then iteratively adjusts it, for example, by reducing the proportion of certain additives to affect the electrical response.

[0038] It should be noted that this iteration emphasizes the dependencies between variables; for example, when one proportion increases, other proportions decrease accordingly to maintain balance. Furthermore, the optimized formulation data can be extended to mass production, for example, by applying the same algorithm to the formulation of filter adhesives, iteratively processing variables to address thickness-related dielectric issues.

[0039] Preferably, the algorithm incorporates a feedback loop to obtain data from new sample tests and further refine the proportions.

[0040] In one possible implementation, the algorithm considers multi-objective optimization when processing proportional combinations, such as simultaneously reducing the dielectric constant and maintaining the viscosity of the adhesive. The iterative process is implemented using weighted variables, for example, assigning higher weight to the dielectric constant.

[0041] For example, the index value changes each time in the iteration, forming a trajectory for analysis.

[0042] Specifically, this optimization algorithm is applicable in the field of optical adhesives, for example, to the formulation adjustment of touch screen adhesives, based on the mapping of iterative variables for areas with excessively high values ​​to determine the final data.

[0043] Step S103: Simulate the coating process from the optimized formula data to obtain the simulated thickness distribution. If the simulated thickness distribution exceeds the preset uniformity threshold, fine-tune the coating process parameters, determine whether the fine-tuned thickness distribution meets the uniformity requirements, and obtain the adjusted coating process parameters.

[0044] The optimized formulation data, containing the precise proportions and key physical properties of each component of the optical adhesive, is obtained. A computational fluid dynamics model is used, with the rheological properties corresponding to the formulation data as boundary conditions. Combined with the initial coating process parameter set, a numerical simulation of the coating process is performed to obtain the simulated thickness distribution field of the entire coating area. The mean and standard deviation of the thickness are extracted from the simulated thickness distribution field, and a thickness uniformity index is calculated. This calculation uses the normalized coefficient of variation obtained by dividing the standard deviation by the mean. This index is compared with a preset uniformity threshold to determine whether the simulated thickness distribution meets the uniformity requirements. If the thickness uniformity index is better than the threshold, the initial coating process parameter set is determined to be qualified. If the thickness uniformity index does not reach the preset uniformity threshold, the spatial characteristics of the simulated thickness distribution field are analyzed to identify specific patterns of thin and thick areas. Based on a pre-established physical property-process correlation model, which is trained using historical coating data to correlate the mapping relationship between rheological properties and process variables, historical process adjustment cases matching the current formulation rheological properties and the thickness distribution characteristics are queried. Using the adjustment direction and magnitude recommended by the property-process correlation model, the key variables in the initial coating process parameter set are quantitatively fine-tuned. These key variables include the coating head slit width, substrate feed rate, and feed pressure, generating a new set of coating process parameters to be verified. This new set of parameters is then re-input into the computational fluid dynamics model, and the coating simulation is executed again. A new simulated thickness distribution is obtained, and its uniformity index is calculated. The uniformity index is iteratively compared with a threshold, and the parameters are fine-tuned based on the results until the thickness uniformity index consistently meets the preset threshold, resulting in the final determined adjusted coating process parameters.

[0045] In one implementation, the coating process is simulated from optimized formulation data to obtain a simulated thickness distribution.

[0046] Specifically, the simulation process is based on the rheological parameters of the adhesive material and the physical model of the coating process.

[0047] It should be noted that the optimized formulation data determines the key properties of the adhesive, such as viscosity and shear thinning characteristics. These performance parameters are input into a pre-established coating simulation model. This simulation model can be a simplified hydrodynamic model used to calculate the flow and spreading behavior of the adhesive on the substrate.

[0048] For example, the model takes the gap between the coating head and the substrate, the coating speed, and the viscosity curve of the adhesive as input variables. By solving the flow equation under set boundary conditions, the theoretical thickness of the adhesive at different locations on the substrate is calculated, thereby forming the simulated thickness distribution map.

[0049] Understandably, this simulation avoids the material consumption of actual trial coatings and can quickly predict the impact of formulation changes on coating results. Furthermore, the obtained simulated thickness distribution is compared with a preset uniformity threshold. The uniformity threshold is typically set according to product specifications.

[0050] For example, the thickness can be specified to fluctuate within ±5% of the target value, or the difference between the maximum and minimum thickness within the entire coating area can be specified to not exceed a certain specific value. If the simulation results show that the thickness deviation in some areas exceeds this threshold, it is determined that the uniformity requirement is not met, triggering a fine-tuning procedure for the coating process parameters. For cases requiring fine-tuning, the coating process parameters are iteratively adjusted. Coating process parameters include, but are not limited to, the doctor blade gap of the coating head, the discharge pressure of the feed pump, the substrate conveyor speed, and the temperature of the coating area.

[0051] In one possible implementation, the fine-tuning process follows a pre-defined set of adjustment rules.

[0052] For example, when the simulated display shows that the center area of ​​the adhesive material is too thick and the edges are too thin, the adjustment rules may indicate to slightly increase the gap between the two ends of the scraper or reduce the feeding pressure in the center.

[0053] Specifically, the system queries a rule base based on the location and degree of deviation of areas where the thickness distribution exceeds a threshold, generating a preliminary set of process parameter adjustments. Then, based on these preliminarily adjusted parameters, the aforementioned coating process simulation is rerun to obtain a new simulated thickness distribution. The system then determines whether the adjusted thickness distribution meets the uniformity requirements. This determination process also compares the new distribution with the same uniformity threshold. If it meets the requirements, the current set of process parameters is identified as the adjusted coating process parameters. If it still does not meet the requirements, the system continues iterating through the fine-tuning and simulation verification steps.

[0054] Preferably, to improve efficiency, a simple optimization algorithm can be introduced, such as dynamically adjusting the step size based on the difference between two simulation results, until a set of process parameters that satisfies the uniformity requirement of the simulated thickness distribution is found. This method can be specifically implemented in scenarios where optical adhesives are used in the production of touchscreen sensors.

[0055] For example, for an optical adhesive used to bond an indium tin oxide conductive layer to a cover glass, its optimized formulation might have a higher filler content to reduce the dielectric constant, but this could also alter the adhesive's leveling properties. Through simulation in this embodiment, it can be anticipated that this formulation might result in a "dog-bone" pattern—thick at the edges and thin in the center—in a slot coating process. The system then automatically fine-tunes the lip opening distribution of the coating head and the substrate tension. After several simulation iterations, it outputs a set of coating speed and pressure parameters that ensure uniform adhesive layer thickness, guiding the process settings on the actual production line. In another embodiment, the simulation process can be based on different technical principles.

[0056] For example, for spin coating, the simulation model mainly considers the coupling effect of adhesive spreading and solvent evaporation under centrifugal force. In this case, the fine-tuning of process parameters may become spin coating speed, acceleration, and dispensing volume, etc. However, the core logic remains the same: to replace actual experiments with virtual simulation, quickly linking formulation data and process parameters to ensure that the uniformity of the final coating thickness meets the product design requirements.

[0057] Step S104: Update the production process flow through the adjusted coating process parameters, and use a real-time monitoring module to collect actual coating thickness data and dielectric constant readings to determine the deviation value between the readings and the target index.

[0058] The production process is updated by adjusting the coating process parameters. A real-time monitoring module collects actual coating thickness data and dielectric constant readings to obtain the original dataset corresponding to these readings. The average thickness and average dielectric constant are extracted from the original dataset. These average values ​​are compared with the target indicators to determine a deviation value sequence. Outliers in the deviation value sequence are identified. If an outlier exceeds a preset threshold, a quality traceability record is triggered, generating a coating batch log. The deviation distribution pattern is analyzed based on the coating batch log, and the matching degree between the pattern and historical data is determined to obtain the process consistency index corresponding to the deviation value sequence.

[0059] In one implementation, the production process is updated using the adjusted coating process parameters.

[0060] Specifically, the adjusted parameters include the doctor blade gap of the coating head, the discharge pressure of the feed pump, and the substrate conveyor speed, which are obtained from the aforementioned simulation fine-tuning. The update process first inputs these parameters into the production control system.

[0061] For example, parameters can be automatically loaded using a programmable logic controller.

[0062] It should be noted that this update ensures the continuity of the process flow and avoids errors caused by manual intervention. In scenarios where optical adhesives are used in the production of touchscreen sensors, the updated process can directly guide production line operations.

[0063] For example, after adjusting the doctor blade gap to an optimized value, the system will simultaneously modify the substrate tension parameters, thereby making the adhesive spread more evenly. Furthermore, a real-time monitoring module is used to collect actual coating thickness data and dielectric constant readings. The real-time monitoring module typically consists of a laser thickness sensor and a dielectric constant measuring instrument, which are installed downstream of the coating machine.

[0064] For example, a laser sensor calculates the adhesive layer thickness by emitting a laser beam and receiving the reflected signal. This principle is based on the measurement of optical path difference, ensuring the accuracy of the acquired data is at the micrometer level. The dielectric constant reading is obtained through a capacitive probe that contacts the adhesive layer surface, calculating the constant value based on changes in the electric field.

[0065] Specifically, during the acquisition process, the module samples data multiple times per second and transmits it to the central processing unit via a data cable. This module deployment can handle vibration interference during production.

[0066] For example, noise can be eliminated through built-in filtering algorithms.

[0067] In one possible implementation, for the coating of optical adhesive for touch screens, a monitoring module is integrated into the continuous production line to capture thickness distribution maps and dielectric reading curves in real time to support subsequent deviation analysis.

[0068] Understandably, the real-time monitoring module emphasizes the immediacy and accuracy of data acquisition.

[0069] For example, measurements are taken immediately after the adhesive is applied to avoid changes in the adhesive layer before it cures affecting the readings.

[0070] Preferably, the module also includes a calibration function to verify the sensor accuracy using standard samples before production begins, thereby ensuring the reliability of the readings. This design is particularly suitable in the field of optical adhesives, as the dielectric constant of the adhesive directly affects the signal transmission performance of the touchscreen. The deviation of the reading from the target specification is determined based on a comparative calculation of the acquired data.

[0071] Specifically, the target indicators include a preset thickness range, such as ±5% of the target value, and a target dielectric constant value, such as a specific numerical range. Deviation values ​​are calculated using formulas; for example, thickness deviation equals the actual reading minus the target value, and dielectric constant deviation is calculated similarly.

[0072] It should be noted that this determination process is executed automatically using software algorithms to generate deviation reports. In touchscreen sensor production, if the deviation exceeds a threshold, the system will trigger an alarm, further guiding process optimization. In another implementation, updating the production process can be combined with manual verification steps.

[0073] For example, after loading the parameters, operators can conduct small-batch trial production to confirm the update's effect before scaling up to the entire line. This approach is suitable for scenarios where adhesive formulations change frequently, ensuring that updates do not disrupt the production rhythm. Furthermore, for the data acquisition by the real-time monitoring module, another implementation can use non-contact optical sensors instead of lasers. The principle is based on spectral interferometry, calculating thickness by analyzing the interference pattern. This method has significant advantages in high-speed coating lines because it reduces the risk of contamination from physical contact. In practical applications of optical adhesives, the dielectric constant readings acquired by this module help assess the electrical uniformity of the adhesive layer.

[0074] For example, the determination of deviation values ​​can also incorporate statistical analysis, such as calculating the mean deviation and standard deviation, to quantify overall performance.

[0075] In one embodiment, if the thickness deviation remains consistently high, the system records this as feedback data for subsequent parameter iterations. This objective calculation supports closed-loop control of production, effectively reducing the defect rate in touchscreen manufacturing.

[0076] Preferably, the logic of the entire process starts with parameter updates, transitions to monitoring and deviation determination, forming a continuous chain.

[0077] For example, the monitoring module should be activated immediately after the update to ensure that the data reflects the effects of the latest process.

[0078] In one embodiment, for different types of optical adhesives, such as those used in flexible touchscreens, the monitoring module can adjust the sampling frequency to match the flow characteristics of the adhesive, thereby accurately capturing changes in readings. This flexibility demonstrates the versatility of the technical solution within the same field.

[0079] Step S105: For the deviation value, obtain signal integrity test data. If the deviation value causes a decrease in signal integrity, activate the feedback loop and apply a correction increment to the production process parameters to obtain the corrected process parameters.

[0080] For the aforementioned deviation value, signal integrity test data is collected from the production line. This test data is compared with a preset threshold to determine the degree of integrity degradation. If the degree of integrity degradation exceeds the threshold, the batch quality tracking module extracts influencing factors from the source of the deviation, analyzes the correlation between these factors, and obtains a correction increment sequence. Based on this correction increment sequence, a feedback loop is activated to apply incremental adjustments to the production process parameters, resulting in an updated parameter set. The subsequent coating process is monitored using this updated parameter set to determine the signal improvement verification results and obtain the corrected process parameters.

[0081] In one implementation, signal integrity test data is acquired for the deviation value.

[0082] Specifically, signal integrity test data is collected using dedicated testing equipment installed at the end of the coating production line to evaluate the signal transmission quality in touchscreen sensors.

[0083] For example, after the optical adhesive is applied, the test data includes signal attenuation values ​​and noise levels, which are read from the sensor electrodes.

[0084] It should be noted that the acquisition process is based on high-speed sampling technology to ensure that the data reflects the impact of adhesive layer deviations on electrical signals. This test is particularly important in touchscreen manufacturing because deviations in the thickness or dielectric constant of the adhesive material can interfere with the signal path. Furthermore, if the deviation value leads to a decrease in signal integrity, a feedback loop is activated. The determination of signal integrity degradation is achieved by comparing the test data with a preset threshold.

[0085] For example, when the signal attenuation exceeds 10% of the target value, the system confirms the decline. The feedback loop is a closed-loop control mechanism that works by converting deviation information into parameter adjustment commands.

[0086] Specifically, the loop begins with deviation analysis and iterates until the signal indicators return to normal.

[0087] In one possible implementation, the feedback loop for adhesive coating on flexible touchscreens is integrated into the control software, automatically handling multiple rounds of corrections. This activation ensures production stability and prevents signal problems from affecting the final product performance.

[0088] Preferably, a correction increment is applied to the production process parameters to obtain the corrected process parameters. The correction increment is an increment value calculated by an algorithm.

[0089] For example, adjust the scraper gap or belt speed according to the proportion of the deviation.

[0090] In one embodiment, incremental calculation takes into account historical data, based on proportional-integral-derivative control, to ensure that the correction is gradual and accurate.

[0091] For example, in a touchscreen sensor production line, if thickness deviation causes signal degradation, the system applies a positive increment to the feed pump pressure to optimize adhesive uniformity.

[0092] It should be noted that this application process is executed by a programmable controller, updating parameters in real time without interrupting production.

[0093] Understandably, in another implementation, signal integrity test data acquisition can utilize a wireless transmission module to improve data real-time performance. Furthermore, after the feedback loop is activated, the history of each correction is recorded to support subsequent optimization. In scenarios where optical adhesives are used in high-resolution touchscreens, this method reduces signal interference and improves touch response accuracy.

[0094] Specifically, the correlation between the deviation value and signal integrity was analyzed through a simulation model, which simulates the effect of the adhesive layer on the signal based on electrical principles.

[0095] In one embodiment, if a deviation in dielectric constant causes a decrease, the feedback loop prioritizes correcting the substrate speed, with the incremental value derived from the deviation ratio. This design demonstrates the versatility of the technology in touchscreen manufacturing.

[0096] For example, in a continuous coating production line, after obtaining the corrected process parameters, the system verifies signal integrity recovery to ensure the effectiveness of the closed loop.

[0097] Preferably, the entire process emphasizes gradual parameter correction to avoid excessive increments that could lead to new deviations.

[0098] Step S106: Extract the bonding effect evaluation index from the modified process parameters, and determine whether the bonding effect meets the requirements by comparing the evaluation index with the preset standard, thereby obtaining a supplementary adjustment scheme to enhance the bonding effect.

[0099] Adhesion strength data and layer thickness uniformity data are obtained from the corrected process parameters. The adhesion strength data and layer thickness uniformity data are compared using a preset standard to determine the adhesion effect level. For the adhesion effect level, coating temperature and coating pressure parameters are extracted from the production batch records as influencing factors. The correlation weights of the coating temperature and coating pressure parameters with the adhesion effect level are analyzed to obtain a parameter adjustment increment sequence. A feedback loop is activated based on the parameter adjustment increment sequence to apply corresponding corrections to the coating temperature and coating pressure parameters, obtaining an updated process parameter set. Subsequent coating processes are executed using the updated process parameter set, and new adhesion strength data is collected. The new adhesion strength data is compared with the preset standard to determine the adhesion effect improvement result, and a supplementary adjustment scheme to enhance the adhesion effect is obtained.

[0100] In one implementation, an adhesion performance evaluation index is extracted from the modified process parameters.

[0101] Specifically, the revised process parameters include adhesive coating thickness, feed pump pressure, and doctor blade clearance, which had been optimized in previous feedback loops. The extraction process is achieved through a sensor system integrated into the production line.

[0102] For example, an optical scanner is used to measure the bonding interface between the adhesive layer and the touchscreen substrate. Adhesion performance evaluation metrics refer to numerical values ​​that quantify the adhesion of the adhesive layer, such as peel strength and interface uniformity, which are calculated from parametric data.

[0103] It should be noted that the peel strength value is derived through a simulated tensile test model, based on the intermolecular forces between the adhesive and the substrate, ensuring that the evaluation reflects the actual bonding quality. In touchscreen sensor production, this extraction helps identify potential bonding defects. Furthermore, by comparing the evaluation indicators with preset standards, it is determined whether the bonding effect meets the requirements. The preset standards are thresholds set based on industry specifications.

[0104] For example, the peel strength must exceed the benchmark of 5 Newtons per square centimeter. The comparison process is executed by an automated software module, which matches the extracted index values ​​with the standard item by item. If the index is lower than the standard, it is judged as not meeting the requirements.

[0105] For example, on the adhesive coating lines of a flexible touchscreen, this comparison is integrated into the control system to process data in real time to avoid production delays.

[0106] Understandably, the judgment logic takes into account environmental factors, such as the effect of temperature on adhesion, thereby improving accuracy.

[0107] Preferably, a supplementary adjustment scheme to enhance the adhesion effect is obtained.

[0108] Specifically, the supplementary adjustment plan is a parameter correction instruction generated through analysis and judgment results.

[0109] For example, if the peel strength is insufficient, the solution suggests increasing the preheating time of the adhesive or adjusting the curing temperature.

[0110] In one embodiment, in the production of high-resolution touchscreens, the solution generation is based on a historical database, which works by accumulating previous adjustment experience to optimize the current solution. This method ensures continuous improvement in adhesion and avoids adhesive layer peeling problems.

[0111] In one possible implementation, a wireless data transmission module can be used to improve extraction efficiency when extracting indicators from the modified process parameters.

[0112] Specifically, the process of sending parameter data from the sensor to the central processing unit and extracting indicators such as peel strength involves simple data filtering to ensure that the indicators accurately reflect the adhesion state. This method is particularly suitable for continuous coating production lines. Furthermore, when judging the adhesion effect, the comparison mechanism can be extended to the fusion of multiple indicators, such as combining interface uniformity and optical transmittance for comprehensive evaluation.

[0113] It should be noted that the principle of multi-indicator fusion is to calculate the total score through weighted averaging to determine whether the requirements are met, thereby providing more comprehensive feedback on the bonding quality. In touchscreen assembly scenarios, this judgment helps to identify problems early.

[0114] For example, the generation of the supplementary adjustment plan includes an iterative optimization step. If the initial judgment does not meet the standard, the plan automatically calculates the incremental value, such as extending the solidification time by 10%.

[0115] In one embodiment, for scenarios where optical adhesives are applied to curved touchscreens, the solution prioritizes adjusting pressure parameters to enhance the adhesion between the adhesive layer and the curved substrate. This design demonstrates the versatility of the solution across different touchscreen types.

[0116] Understandably, the entire process emphasizes the linkage between parameters and indicators, forming a closed-loop control from extraction to adjustment. In production practice, this linkage can maintain the stability of adhesive coating and ensure the durability of the touch screen.

[0117] Preferably, machine vision technology can be introduced to assist in measuring interface uniformity during the stage of extracting adhesion effect evaluation indicators.

[0118] Specifically, the machine vision system captures images of the adhesive layer and analyzes pixel distribution to quantify uniformity metrics. This technology is widely used in touchscreen sensor production lines, improving the objectivity of evaluations. Furthermore, after obtaining supplementary adjustment plans, the system can record the adjustment history to support future optimizations.

[0119] For example, in the manufacturing of large-size touchscreens, if insufficient display adhesion is determined, the solution generation process includes multiple rounds of verification to ensure that the final adhesion effect meets requirements. In one implementation, the judgment process can incorporate real-time monitoring data, such as monitoring temperature fluctuations during the curing process, to dynamically adjust preset standards. This flexibility enhances the adaptability of the method to changing production environments.

[0120] Step S107: Integrate all parameters according to the supplementary adjustment scheme, use the integration module to generate the final production process protocol, and determine the dynamic adjustment rules of each link in the protocol to maintain a low dielectric constant and uniform thickness distribution.

[0121] All parameters are obtained from the supplementary adjustment scheme, and the parameters are fused using an integration module to generate an initial production process protocol. For the initial production process protocol, dynamic adjustment rules are determined for each stage, and the dielectric constant value is monitored using these rules. The dielectric constant value is obtained, and it is determined whether it meets the low-value requirement. If it exceeds a preset threshold, the dynamic adjustment rules are activated to update the thickness distribution parameters. Production process optimization is performed by updating the thickness distribution parameters to obtain the final production process protocol that maintains a uniform thickness distribution.

[0122] In one implementation, all parameters are integrated according to the supplementary adjustment scheme.

[0123] Specifically, the supplementary adjustment plan includes parameters such as adhesive coating thickness, feed pump pressure, and doctor blade clearance, which are derived from previous assessments of the bonding effect. The integration process is executed through a data aggregation module, which first collects the values ​​of each parameter and then performs standardization to ensure compatibility between parameters.

[0124] For example, in the production of adhesive coatings for touchscreens, the interrelationships between parameters, such as the relationship between thickness and pressure, are considered to form a complete parameter set. This integration is achieved in the production line control system, supporting subsequent protocol generation. Furthermore, an integrated module is used to generate the final production process protocol. The integrated module refers to an embedded software system that includes parameter input interfaces and a protocol compilation engine.

[0125] Specifically, the module receives the integrated parameter set and maps the parameters to the protocol structure using a predefined template.

[0126] It should be noted that the protocol generation process involves verifying the validity of each parameter, such as checking whether the thickness value is within the allowable range.

[0127] In one possible implementation, for flexible touchscreen production scenarios, the integration module uses a cloud database to generate a protocol document containing operational steps. This method ensures that the protocol covers the coating, curing, and inspection stages.

[0128] Preferably, the dynamic adjustment rules for each link in the protocol are determined.

[0129] Specifically, the dynamic adjustment rules are formulated based on a threshold triggering mechanism.

[0130] For example, when a thickness deviation is detected, the rule command automatically corrects the scraper gap.

[0131] In one embodiment, during high-resolution touchscreen assembly, these rules are defined through logical expressions. The principle is to compare current parameters with target values ​​in real time, such as maintaining the dielectric constant within a low range. The rule determination process includes the steps of first identifying critical stages, such as the coating stage, and then setting adjustment conditions for each stage. For example, if the thickness is uneven, the rule specifies increasing the stirring time to improve distribution. Furthermore, these rules are integrated into a protocol to support adaptive control on the production line. In touchscreen sensor manufacturing, the rules also consider environmental variables, such as the effect of humidity on the dielectric constant, thereby defining compensatory adjustments.

[0132] For example, in a production environment with curved touchscreens, the dynamic adjustment rules are extended to multi-parameter linkage.

[0133] Specifically, if the dielectric constant increases, the rules prioritize adjusting the curing temperature while monitoring the uniformity of thickness distribution.

[0134] It should be noted that the dielectric constant refers to the polarization ability of the adhesive material in an electric field. Maintaining a low value is achieved by optimizing the molecular structure, a process that includes parameter adjustments to reduce dielectric loss. In one implementation, rule formulation employs historical data analysis, such as reviewing previous batch production records, to extract patterns and generate rule templates. This approach is used in continuous production lines to ensure dynamic responses at each stage, such as feeding and scraper operation.

[0135] Understandably, the entire process, from parameter integration to rule determination, forms a closed loop.

[0136] Specifically, after the protocol is generated, dynamic rules are embedded in it to maintain a low dielectric constant and a uniform thickness distribution.

[0137] For example, in the manufacturing of large-size touchscreens, rules are executed cyclically through sensor feedback, adjusting parameters to keep thickness deviations below a specified threshold. This linkage emphasizes the practicality of the protocol, supporting the production of different touchscreen types. Furthermore...

[0138] In one possible implementation, the process of generating the integrated module can be combined with wireless transmission technology.

[0139] Specifically, parameters are transmitted to the module in real time from production line sensors, and dynamic rules are automatically embedded when generating the protocol. This technology is applicable in touchscreen adhesive coating scenarios, improving the protocol's response speed.

[0140] If the technical solution of this application involves personal information, the product using this solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If sensitive personal information is involved, the user's separate consent has been obtained before processing, and the "express consent" requirement is met. For example, a clear sign is placed at the collection device such as a camera to inform the user that they have entered the collection area, and the user's voluntary entry is considered as consent; or the processing device clearly indicates the processing rules and obtains authorization through pop-up windows or by asking the user to upload information themselves. The personal information processing rules include the processor, the purpose of processing, the processing method, and the types of personal information.

[0141] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for optimizing the manufacturing process of optical adhesive materials, characterized in that, include: The process involves: acquiring initial formulation data and production process parameters for optical adhesives; extracting dielectric constant-related indicators and coating thickness distribution characteristics from these data; generating a distribution map based on the dielectric constant-related indicators and coating thickness distribution characteristics to identify regions with high dielectric constants and uneven thicknesses; adjusting the formulation component ratios according to the distribution map to generate optimized formulation data; simulating the coating process using the optimized formulation data to obtain a simulated thickness distribution; and adjusting the coating process parameters based on the simulated thickness distribution to obtain the adjusted coating process parameters. The production process flow is updated using the adjusted coating process parameters, actual coating data is collected, and deviation values ​​are determined. Adjust the production process parameters according to the deviation value to generate the corrected process parameters; The bonding effect is evaluated using the revised process parameters, supplementary adjustment plans are generated, and all parameters are integrated to generate the final production process agreement.

2. The method for optimizing the production process of optical adhesive materials as described in claim 1, characterized in that, The step of extracting dielectric constant-related indicators and coating thickness distribution characteristics from the initial formulation data and production process parameters includes: extracting dielectric constant-related indicators from the initial formulation data to obtain coating thickness data from the production process parameters; identifying regions with high dielectric constants by comparing the dielectric constant-related indicators with a preset threshold; calculating thickness distribution characteristics based on the coating thickness data to determine regions with uneven thickness; analyzing the regions with high dielectric constants and regions with uneven thickness using a classification algorithm to generate a feature dataset; grouping the feature dataset using a clustering algorithm to determine material uniformity verification points and obtain a verification dataset; and adjusting the coating thickness distribution characteristics based on the verification dataset to generate the final distribution mapping data.

3. The method for optimizing the production process of optical adhesive materials as described in claim 1, characterized in that, The step of adjusting the formulation component ratios for the distribution map to generate optimized formulation data includes: extracting data from regions with high dielectric constants from the distribution map; iteratively processing the formulation component ratios corresponding to the high dielectric constant regions using an optimization algorithm to generate preliminary ratio combinations; reducing variable indicators using the preliminary ratio combinations, implementing formulation optimization for the high dielectric constant regions, and determining an iterative optimization loop; obtaining component ratio verification data in the iterative optimization loop; iteratively processing the verification data using the optimization algorithm to generate optimized data; adjusting the ratio variables based on the optimized data, and outputting the final optimized formulation data.

4. The method for optimizing the production process of optical adhesive materials as described in claim 1, characterized in that, The step of simulating the coating process using the optimized formulation data to obtain the simulated thickness distribution includes: extracting the proportions and physical property parameters of each component from the optimized formulation data; using a computational fluid dynamics model, with the physical property parameters as boundary conditions, and combining them with the initial coating process parameters to perform numerical simulation and obtain the simulated thickness distribution field; extracting the mean and standard deviation of the thickness from the simulated thickness distribution field to calculate the thickness uniformity index; comparing the thickness uniformity index with a preset threshold to determine whether the uniformity requirement is met; if the thickness uniformity index does not reach the preset threshold, adjusting the initial coating process parameters according to the recommended adjustment direction based on the pre-established physical property-process correlation model to generate a new set of parameters to be verified; and obtaining the final adjusted coating process parameters through iterative simulation and judgment.

5. The method for optimizing the production process of optical adhesive materials as described in claim 1, characterized in that, The process of updating the production process using the adjusted coating process parameters, collecting actual coating data, and determining deviation values ​​includes: updating the production process using the adjusted coating process parameters; collecting actual coating thickness data and dielectric constant readings using a real-time monitoring module to generate a raw dataset; extracting the average thickness and average dielectric constant from the raw dataset; generating a deviation value sequence by comparing the average thickness and average dielectric constant with the target index; extracting outliers from the deviation value sequence; triggering quality traceability records and generating a coating batch log if the outliers exceed a preset threshold; and analyzing the deviation distribution pattern based on the coating batch log to determine the process consistency index.

6. The method for optimizing the production process of optical adhesive materials as described in claim 1, characterized in that, The step of adjusting production process parameters based on the deviation value to generate corrected process parameters includes: collecting signal integrity test data from the production line; determining the degree of integrity degradation by comparing the signal integrity test data with a preset threshold; if the degree of integrity degradation exceeds the preset threshold, extracting influencing factors through a batch quality tracking module, analyzing the correlation between the influencing factors, and generating a correction increment sequence; activating a feedback loop based on the correction increment sequence to incrementally adjust the production process parameters and generate an updated parameter set; monitoring the subsequent coating process through the updated parameter set, judging the signal improvement result, and generating corrected process parameters.

7. The method for optimizing the production process of optical adhesive materials as described in claim 1, characterized in that, The process of evaluating the adhesion effect using the modified process parameters and generating a supplementary adjustment plan includes: obtaining adhesion strength data and layer thickness uniformity data from the modified process parameters; determining the adhesion effect level by comparing the adhesion strength data and layer thickness uniformity data with preset standards; extracting coating temperature parameters and coating pressure parameters from production batch records as influencing factors; analyzing the correlation weight of the coating temperature parameters and coating pressure parameters with the adhesion effect level, and generating a parameter adjustment increment sequence; activating a feedback loop based on the parameter adjustment increment sequence, adjusting the coating temperature parameters and coating pressure parameters, and generating an updated process parameter set; collecting new adhesion strength data through the updated process parameter set, judging the improvement results, and generating a supplementary adjustment plan.

8. The method for optimizing the production process of optical adhesive materials as described in claim 1, characterized in that, The process of integrating all parameters to generate the final production process protocol includes: obtaining all parameters from the supplementary adjustment scheme; fusing the parameters using an integration module to generate an initial production process protocol; determining dynamic adjustment rules for each stage of the initial production process protocol; monitoring the dielectric constant value through the dynamic adjustment rules; if the dielectric constant value is higher than a preset threshold, activating the dynamic adjustment rules to update the thickness distribution parameters; and performing production process optimization through the updated thickness distribution parameters to generate a final production process protocol that maintains a uniform thickness distribution.

Images