Intelligent liquid crystal display module accurate manufacturing method, system, equipment and medium thereof

Abstract

The invention provides an intelligent liquid crystal display module precise manufacturing method, system and device and a medium thereof, and the method comprises the following steps: obtaining real-time process parameter data in the manufacturing process of an intelligent liquid crystal display module, and carrying out the preprocessing; according to the method, the real-time process parameter data is acquired and deeply analyzed, and the correlation model of the process parameters and the product quality is established, so that the precise control of the manufacturing process is realized, the manufacturing precision of the intelligent liquid crystal display module is remarkably improved, and the yield of the product is improved by more than 20% compared with that of a traditional method; automatic adjustment can be carried out according to changes of real-time process parameters through a self-adaptive process adjustment mechanism, manual intervention is not needed, the production efficiency is greatly improved, and meanwhile product quality fluctuation caused by human factors is reduced; product defects can be found and repaired in time through a high-precision optical detection and feedback correction system, the optical performance and the display quality of products are guaranteed, and the market competitiveness of the products is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of liquid crystal display module manufacturing, and particularly relates to a precise manufacturing method, system, device and medium for an intelligent liquid crystal display module. Background Art

[0002] With the rapid development of current technology, intelligent liquid crystal display modules are widely used. In smartphones, high-resolution screens require high-precision manufacturing to accurately present colors and brightness of pixels and meet users' demands for delicate displays. For tablets used for work and entertainment, improving manufacturing precision can reduce screen defects. Wearable devices such as smart watches have small screens and have strict requirements for the integration and precision of display modules. Otherwise, it is difficult to clearly display information. In industrial control, operators rely on high-precision display modules to accurately read data. Insufficient manufacturing precision is likely to cause misjudgment. Therefore, the manufacturing precision requirements for intelligent liquid crystal display modules in various fields are increasing day by day. However, there are still certain problems with traditional liquid crystal display module manufacturing methods:

[0003] I. Low process precision: In the liquid crystal dropping process, the precision of traditional equipment is limited, and the deviation of the dropping volume can reach ±5%. When manufacturing large-area panels, it is easy to cause uneven liquid crystal volume, resulting in problems such as uneven display brightness and pure color background patches, affecting the consistency of display effects; in the glass substrate lamination process, it is difficult for traditional equipment and processes to achieve high-precision alignment and bubble-free lamination. The position deviation of manual or semi-automatic lamination can reach ±0.1 mm, causing pixel misalignment, image ghosting and blurring, and the bubbles interfere with the light propagation, reducing the yield rate;

[0004] II. Poor equipment performance: The degree of intelligence and automation of manufacturing equipment is low. For example, in the pre-treatment stage of glass substrates, parameters cannot be automatically adjusted according to the real-time characteristics of the substrates, resulting in different pre-treatment effects for different batches, affecting the orientation of liquid crystal molecules; at the same time, the operation stability of the equipment is poor, and it frequently stops due to failures. Resetting parameters after restarting is likely to cause fluctuations in product quality and reduce production efficiency;

[0005] III. Poor system coordination: Each link of the existing manufacturing system is independent, lacking a data sharing and coordination mechanism, making it difficult to explore the potential relationships between parameters and the influence laws on quality, unable to achieve precise optimization and real-time control of the manufacturing process, and difficult to meet the requirements of precise manufacturing;

[0006] Therefore, a precise manufacturing method, system, device and medium for an intelligent liquid crystal display module are proposed. Summary of the Invention

[0007] In view of this, embodiments of the present invention hope to provide a precise manufacturing method, system, device and medium for an intelligent liquid crystal display module to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0008] To solve the above technical problems, a technical solution adopted in this application is: an intelligent liquid crystal display module precise manufacturing method, including the following steps:

[0009] Step 1: Obtain the process parameter data during the manufacturing process of the liquid crystal display module and perform preprocessing;

[0010] Step 2: Use big data analysis algorithms to deeply analyze the preprocessed process parameter data and construct a correlation model between process parameters and product quality;

[0011] Step 3: Based on the correlation model between process parameters and product quality, use computer-aided design and virtual reality technologies to construct a virtual manufacturing environment for intelligent liquid crystal display modules;

[0012] Step 4: Based on the virtual manufacturing environment of the intelligent liquid crystal display module, simulate the manufacturing process and predict the process defects and product quality problems that occur;

[0013] Step 5: According to the predicted process defects and product quality problems, perform process parameter adjustment and optimization plan rehearsal in the virtual manufacturing environment of the intelligent liquid crystal display module, and screen out the optimal process plan;

[0014] Step 6: Apply the selected optimal process plan to the actual manufacturing process, and monitor the change of process parameter data in real time. If the process parameter data deviates from the parameter window, the adaptive adjustment mechanism is automatically activated;

[0015] Step 7: Based on the detection index, use optical detection technology to detect the assembled display module, and adjust the process equipment through the feedback control system according to the detection results.

[0016] Preferably, as a further optimization of this technical solution, in Step 2, the method for constructing the correlation model between process parameters and product quality includes the following steps:

[0017] Step 201: Divide the preprocessed process parameter data and the corresponding product quality data into a training set, a validation set, and a test set according to a certain proportion;

[0018] Step 202: Use correlation analysis or principal component analysis to perform feature analysis on the process parameter data and screen out the key features;

[0019] Step 203: According to the data characteristics and problem types, select a linear regression model, a convolutional neural network, or a long short-term memory network as the correlation model, and use the training set data to train the selected correlation model;

[0020] Step 204: Use the validation set to evaluate and optimize the trained correlation model, and use the test set to test the optimized correlation model.

[0021] Preferably, as a further optimization of this technical solution, in step three, the method for constructing the virtual manufacturing environment of the intelligent liquid crystal display module includes the following steps:

[0022] Step 301: According to the actual physical structure and dimensions of the intelligent liquid crystal display module, use 3D modeling software to construct 3D models of each component and assign corresponding material properties to each component;

[0023] Step 302: Combine the process parameter and product quality correlation model to construct a process model during the manufacturing process of the intelligent liquid crystal display module;

[0024] Step 303: Use virtual reality technology to integrate the created 3D models and process models into a virtual scene to generate a virtual manufacturing environment;

[0025] Step 304: Based on the integrated physical simulation engine, simulate the physical phenomena in the virtual manufacturing environment;

[0026] Step 305: Develop a data interaction interface between the virtual manufacturing environment and the actual manufacturing system for real-time data transmission and synchronization between the two.

[0027] Preferably, as a further optimization of this technical solution, in step five, the method for screening out the optimal process plan includes the following steps:

[0028] Step 501: Classify process defects and product quality problems, analyze the causes of each problem, and combine the process parameter and product quality correlation model to determine the key process parameters related to the problem;

[0029] Step 502: Based on the key process parameters related to the problem, determine the adjustment range of the key process parameters according to historical production data, industry experience, and simulation results in the virtual manufacturing environment;

[0030] Step 503: Within the adjustment range of the key process parameters, use orthogonal experimental design and response surface method to generate multiple combinations of process parameters, and each combination of process parameters constitutes an optimization plan;

[0031] Step 504: In the virtual manufacturing environment of the intelligent liquid crystal display module, conduct simulation rehearsals for each optimization plan and evaluate them using a multi-objective optimization algorithm to obtain the comprehensive score of each optimization plan;

[0032] Step 505: Compare the comprehensive scores of all optimization plans and select the plan with the highest comprehensive score as the optimal process plan.

[0033] As a further preference of this technical solution, in step six, the parameter window is the normal fluctuation range of process parameters determined by statistically analyzing historical production data and combining with product quality standards.

[0034] As a further preference of this technical solution, in step one, the process parameter data is obtained by arranging sensors at each key link in the manufacturing process of the liquid crystal display module;

[0035] The process parameter data includes temperature and humidity data in the glass substrate pretreatment stage, dropping pressure and dropping volume data in the liquid crystal dropping process, and fitting speed and fitting pressure data during the polarizer fitting;

[0036] The pretreatment includes data cleaning, data standardization, and data missing processing.

[0037] As a further preference of this technical solution, in step seven, the detection indicators include brightness uniformity, color accuracy, and pixel defects of the display module.

[0038] To solve the above technical problems, another technical solution adopted by this application is: an intelligent liquid crystal display module precision manufacturing system, which includes: a data acquisition and processing module, a data analysis and modeling module, a virtual environment construction module, a simulation prediction module, a solution screening module, a production monitoring and adjustment module, and a detection and feedback module;

[0039] The data acquisition and processing module is configured to obtain process parameter data in the manufacturing process of the liquid crystal display module and perform pretreatment;

[0040] The data analysis and modeling module is configured to deeply analyze the pretreated process parameter data using big data analysis algorithms and construct a correlation model between process parameters and product quality;

[0041] The virtual environment construction module is configured to construct a virtual manufacturing environment for the intelligent liquid crystal display module based on the correlation model between process parameters and product quality, using computer-aided design and virtual reality technologies;

[0042] The simulation prediction module is configured to simulate the manufacturing process based on the virtual manufacturing environment of the intelligent liquid crystal display module and predict process defects and product quality problems that occur;

[0043] The solution screening module is configured to perform process parameter adjustment and optimization solution rehearsal in the virtual manufacturing environment of the intelligent liquid crystal display module according to the predicted process defects and product quality problems, and screen out the optimal process solution;

[0044] The production monitoring and adjustment module is configured to apply the selected optimal process plan to the actual manufacturing process, monitor the changes in process parameter data in real time, and automatically activate the adaptive adjustment mechanism if the process parameter data deviates from the parameter window.

[0045] The detection and feedback module is configured to detect the assembled display module based on the detection index by using optical detection technology, and adjust the process equipment through the feedback control system according to the detection results.

[0046] To solve the above technical problems, another technical solution adopted by this application is: an electronic device, which includes a processor and a memory coupled to the processor. Program instructions are stored in the memory. When the program instructions are executed by the processor, the processor executes the steps of an accurate manufacturing method for an intelligent liquid crystal display module as described above.

[0047] To solve the above technical problems, another technical solution adopted by this application is: a storage medium storing program instructions capable of implementing an accurate manufacturing method for an intelligent liquid crystal display module as described above.

[0048] Due to the above technical solutions adopted in the embodiments of the present invention, it has the following advantages:

[0049] 1. By acquiring real-time process parameter data and performing in-depth analysis, the present invention establishes an association model between process parameters and product quality, realizes precise control of the manufacturing process, significantly improves the manufacturing accuracy of the intelligent liquid crystal display module, and the yield rate of the product is increased by more than 20% compared with the traditional method.

[0050] 2. The present invention can automatically adjust according to the changes in real-time process parameters through the adaptive process adjustment mechanism without manual intervention, greatly improving the production efficiency and reducing the product quality fluctuations caused by human factors.

[0051] 3. The present invention can timely detect and repair product defects through the high-precision optical detection and feedback correction system, ensuring the optical performance and display quality of the product and enhancing the market competitiveness of the product.

[0052] The above summary is only for the purpose of the specification and is not intended to be limiting in any way. In addition to the above-described illustrative aspects, embodiments and features, further aspects, embodiments and features of the present invention will be readily apparent by reference to the drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0054] Figure 1 It is a schematic flow chart of a precise manufacturing method for an intelligent liquid crystal display module of the present invention;

[0055] Figure 2 It is a schematic flow chart of a method for constructing a correlation model between process parameters and product quality of the present invention;

[0056] Figure 3 It is a schematic flow chart of a method for constructing a virtual manufacturing environment for an intelligent liquid crystal display module of the present invention;

[0057] Figure 4 It is a schematic flow chart of a method for screening out the optimal process plan of the present invention;

[0058] Figure 5 It is a schematic diagram of the functional modules of a precise manufacturing system for an intelligent liquid crystal display module of the present invention;

[0059] Figure 6 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0060] The following will describe the embodiments of the present disclosure in detail with reference to the drawings.

[0061] It should be clear that the following illustrates the implementation manners of the present disclosure through specific specific examples. Those skilled in the art can easily understand other advantages and effects of the present disclosure from the content disclosed in this specification. Obviously, the described embodiments are only some embodiments of the present disclosure, rather than all embodiments. The present disclosure can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts belong to the scope of protection of the present disclosure.

[0062] It should be noted that the following description relates to various aspects of embodiments within the scope of the appended claims. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on this disclosure, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement a device and / or practice a method. Additionally, this device can be implemented and this method can be practiced using other structures and / or functionality in addition to one or more of the aspects described herein.

[0063] It should also be noted that the diagrams provided in the following embodiments only schematically illustrate the basic concept of the present disclosure. Only the components related to the present disclosure are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0064] In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the aspects can be practiced without these specific details.

[0065] Figure 1 It is a schematic flowchart of a precise manufacturing method for an intelligent liquid crystal display module according to an embodiment of the present invention. It should be noted that if there are substantially the same results, the method of the present application is not limited to Figure 1 the process sequence shown. As Figures 1-4 shown: A precise manufacturing method for an intelligent liquid crystal display module includes the following steps:

[0066] Step 1: Obtain process parameter data during the manufacturing process of the liquid crystal display module and perform preprocessing;

[0067] Specifically, first, determine the process parameters to be obtained at multiple key links in the manufacturing of the liquid crystal display module; during the pretreatment stage of the glass substrate, temperature and humidity will affect the microscopic state of the glass substrate surface, and thus affect the adhesion and arrangement of liquid crystal molecules, so it is necessary to obtain the temperature and humidity data at this stage; during the liquid crystal dripping process, the dripping pressure and dripping amount directly determine the liquid crystal amount of each pixel point and play a key role in the display effect, so it is necessary to obtain the dripping pressure and dripping amount data; when attaching the polarizer, the attaching speed and attaching pressure will affect the attaching quality of the polarizer and the liquid crystal layer, and it is necessary to obtain the attaching speed and attaching pressure data;

[0068] Then, according to the parameters to be obtained, select sensors with appropriate accuracy and type; for the acquisition of temperature data, a high-precision thermistor sensor is selected, whose accuracy can reach ±0.1°C, and it can accurately measure the temperature change during the pre-treatment stage of the glass substrate; for pressure data, a piezoelectric pressure sensor is used, with an accuracy of up to ±0.01 MPa, which can accurately measure the liquid crystal dripping pressure and the polarizer lamination pressure; for the dripping volume, a high-precision dripping volume sensor based on the volume measurement principle is used; for humidity, a capacitive humidity sensor is selected, with an accuracy of up to ±2%RH; install these sensors at the corresponding positions of the manufacturing equipment to ensure that the sensors are in full contact with the materials or equipment components during the manufacturing process to accurately collect data; install the dripping pressure and dripping volume sensors at the dripping head of the liquid crystal dripping equipment, install the temperature and humidity sensors in the baking oven for pre-treating the glass substrate, and install the lamination speed and lamination pressure sensors near the lamination roller of the polarizer lamination equipment;

[0069] Next, after the sensors collect the data, it needs to be transmitted to the data processing center in a certain way; adopt a combined wired and wireless transmission method. For sensors that are relatively close to the data processing center, such as sensors installed on the same equipment, use industrial Ethernet for wired transmission to ensure the stability and high speed of data transmission, and its transmission rate can reach more than 100 Mbps; for some sensors with scattered installation positions or difficult wiring, such as some sensors distributed in different workshop areas, adopt a wireless transmission method, such as ZigBee wireless communication technology, which has characteristics such as low power consumption and self-organizing network, and is suitable for data transmission in industrial environments. The transmission distance is between 10 - 100 meters, which can meet the needs of general manufacturing workshops; converge the wired and wireless transmitted data through a gateway and uniformly transmit it to the server of the data processing center;

[0070] Finally, perform data cleaning, data standardization, and data missing value processing on the process parameter data collected by the sensors.

[0071] Step 2: Use big data analysis algorithms to deeply analyze the pre-processed process parameter data and construct a correlation model between process parameters and product quality;

[0072] Specifically, first, divide the pre-processed process parameter data and the corresponding product quality data into a training set, a validation set, and a test set according to the ratio of 70%, 15%, and 15%; the training set is used for the training and learning of the model, enabling the model to learn the relationship between process parameters and product quality from a large amount of data; the validation set is used to evaluate the performance of the model during the training process and adjust the hyperparameters of the model to prevent overfitting of the model; the test set is used to finally evaluate the generalization ability of the model and test the performance of the model on unseen data;

[0073] Then, correlation analysis is used to calculate the correlation coefficients between each process parameter and product quality indicators (such as brightness uniformity, color accuracy, pixel defect rate, etc.), and the process parameters with higher correlation with product quality are selected as key features. At the same time, for multiple related process parameters, principal component analysis (PCA) can be used to transform them into a set of uncorrelated principal components, and these principal components are used as new features to participate in the subsequent model construction, which not only reduces data redundancy but also can more effectively reflect the internal structure of the data;

[0074] Next, according to the data characteristics and problem types, a suitable correlation model is selected from linear regression models, convolutional neural networks (CNNs), and long short-term memory networks (LSTMs), and the correlation model is trained using the training set data;

[0075] Finally, the trained correlation model is evaluated using the validation set. If the performance of the model on the validation set does not meet the expectations, the model needs to be optimized. The hyperparameters of the model can be adjusted to observe the performance changes of the model on the validation set; the amount of training data can also be increased to further improve the generalization ability of the model; regularization methods (such as L1 regularization, L2 regularization) can also be used to prevent the model from overfitting and make the model more stable. After multiple optimization adjustments, the optimized model is finally evaluated using the test set to ensure that the model can accurately reflect the correlation between process parameters and product quality.

[0076] Step 3: Based on the correlation model between process parameters and product quality, use computer-aided design and virtual reality technologies to construct a virtual manufacturing environment for intelligent liquid crystal display modules;

[0077] Specifically, first, use professional computer-aided design software to accurately construct 3D models of each component according to the actual physical structure and dimensions of the intelligent liquid crystal display module. For example, for components such as glass substrates, liquid crystal layers, and polarizers in the liquid crystal display module, model them according to their true shapes, sizes, and proportions; and assign corresponding material properties to each component. Set its optical, mechanical, etc. properties for the glass substrate, set its dielectric constant, viscosity, etc. for the liquid crystal material, and set its polarization characteristics for the polarizer. These properties will affect the simulation of physical phenomena in the subsequent virtual manufacturing environment;

[0078] Then, integrate the process parameter and product quality correlation model into it to construct a process model for the manufacturing process of intelligent liquid crystal display modules. For example, in the liquid crystal dripping process, according to the relationship between the dripping pressure, dripping volume and product quality in the correlation model, set the simulation rules under different parameter conditions during the dripping process; for the glass substrate pretreatment process, based on the influence of temperature and humidity on the surface state of the substrate and the subsequent arrangement of liquid crystal molecules in the correlation model, determine the simulation parameters and processes of the pretreatment process; in this way, the process model can reflect the influence of different process parameters on product quality;

[0079] Next, use virtual reality technology to integrate the created 3D model and process model into a virtual scene. In this virtual scene, simulate the layout of the manufacturing workshop of the liquid crystal display module, place each component model according to the actual manufacturing process, and display the entire process from raw material preparation to finished product assembly; operators can perform interactive operations in the virtual scene through VR devices (such as head-mounted displays, gamepads, etc.), such as simulating picking up components, bonding, etc., to achieve an immersive manufacturing process simulation experience;

[0080] Subsequently, based on the integrated physical simulation engine, simulate the physical phenomena in the virtual manufacturing environment; simulate the flow and diffusion process of liquid crystal in the liquid crystal dripping link, considering the influence of factors such as surface tension and gravity on the liquid crystal distribution; simulate the pressure distribution, stress change, and generation and movement of bubbles during the glass substrate bonding process; simulate the propagation and refraction of light in the liquid crystal layer and polarizer when the display module is working, so as to intuitively observe the display effect of the product under different process conditions; through the physical phenomenon simulation, potential process defects and product quality problems can be discovered in advance;

[0081] Finally, develop a data interaction interface between the virtual manufacturing environment and the actual manufacturing system to achieve real-time data transmission and synchronization between the two; obtain real-time process parameter data from the actual manufacturing system, such as temperature, pressure, speed, etc., and input these data into the virtual manufacturing environment to keep the simulation process in the virtual scene synchronized with the actual production; at the same time, feedback the results obtained from the simulation in the virtual manufacturing environment (such as predicted process defects, product quality evaluation, etc.) to the actual manufacturing system to provide decision-making support for actual production, and help operators adjust process parameters in a timely manner and optimize the production process.

[0082] Step 4: Based on the virtual manufacturing environment of intelligent liquid crystal display modules, simulate the manufacturing process to predict potential process defects and product quality problems;

[0083] Specifically, first, referring to historical production data, the product quality standards of current orders, and the actual manufacturing process requirements, various parameters required for simulation are set in the virtual manufacturing environment. For example, based on the temperature range for the pretreatment of glass substrates, the pressure and reference value of the liquid crystal injection amount during the production of similar products in the past, the temperature during the pretreatment stage of the glass substrate in this simulation is set to 80 °C, the humidity is 30%, the liquid crystal injection pressure is 0.02 MPa, the injection amount is 8 nanoliters, the polarizer bonding speed is 50 mm / s, and the bonding pressure is 50 N, etc. These parameters should be close to the actual production situation to ensure the reliability of the simulation results.

[0084] Then, in the virtual manufacturing environment, each manufacturing link is simulated in sequence according to the actual production process. Starting from the pretreatment of the glass substrate, the surface microscopic change process of the glass substrate in the set temperature and humidity environment is simulated, and it is observed whether the ideal pretreatment effect can be achieved, such as whether the surface flatness, cleanliness and other indicators meet the requirements. Then, the liquid crystal injection process is simulated. According to the set injection pressure and injection amount, the distribution of the liquid crystal on the glass substrate is simulated, and it is checked whether the liquid crystal is evenly distributed, whether there are problems such as insufficient injection, excessive injection or deviation of the injection position. Then, the polarizer bonding process is simulated, and the influence of the bonding speed and pressure on the bonding quality of the polarizer and the liquid crystal layer is observed, and it is checked whether there are phenomena such as loose bonding, bubble residue or polarizer deviation. At the same time, during the simulation manufacturing process, data generated in each link are collected in real time. For example, record the surface roughness after the pretreatment of the glass substrate, the actual liquid crystal amount distribution data after the liquid crystal injection, the bonding strength and the number of bubbles after the polarizer bonding, etc. These data are important bases for subsequent analysis and prediction of process defects and product quality problems.

[0085] Next, data analysis algorithms and tools are used to deeply analyze the collected simulation data. The liquid crystal amount distribution data obtained from the simulation is compared with the ideal distribution model, and the degree of difference between the two is calculated. If the difference exceeds the preset threshold, it is judged that there is a process defect of uneven liquid crystal injection, which will lead to product quality problems such as uneven display brightness and color deviation. For the polarizer bonding link, analyze the bonding strength data. If the bonding strength is lower than the standard value, combined with the number and position information of the bubbles, it is judged that there is a defect of loose polarizer bonding, which will affect the stability and service life of the display module.

[0086] Finally, based on the data analysis results and combined with the correlation model between process parameters and product quality, predict the process defects and product quality problems that occur; if it is found in the simulation that the deviation of the liquid crystal injection volume is large in some areas, according to the correlation model, it can be predicted that pixel display abnormalities such as bright spots, dark spots or color distortion will occur in this area during actual production; for the case where the pretreatment effect of the glass substrate is not good, it is predicted that it will cause irregular arrangement of liquid crystal molecules, affecting the clarity and contrast of the display; through such predictions, potential problems can be discovered in advance, providing a basis for subsequent optimization of the process plan.

[0087] Step Five: According to the predicted process defects and product quality problems, adjust the process parameters and pre-run the optimization plan in the virtual manufacturing environment of the intelligent liquid crystal display module, and screen out the optimal process plan;

[0088] Specifically, first, classify in detail the process defects and product quality problems predicted in Step Four; classify the problems of the liquid crystal display module into display effect categories (such as uneven brightness, color deviation), structural categories (such as poor adhesion of the glass substrate, bubbles in the polarizer), etc., and combine the correlation model between process parameters and product quality to analyze the causes of each problem and determine the key process parameters related to it; if it is found that the uneven brightness is caused by the difference in the liquid crystal injection volume, then the liquid crystal injection volume is the key process parameter; if bubbles appear in the polarizer because of improper bonding pressure and speed, the bonding pressure and bonding speed are the key parameters;

[0089] Then, based on the determined key process parameters, determine the adjustment range of the parameters according to historical production data, industry experience and simulation results in the virtual manufacturing environment; check the historical production records to find the process parameter settings when similar problems were successfully solved; refer to the best practices and technical literature in the industry to obtain the general reasonable range of such parameters; conduct multiple sets of exploratory simulations in the virtual manufacturing environment to observe the impact of key parameters on product quality at different values, so as to determine an adjustment range that can solve the current problem without causing other adverse effects; if the standard value of the liquid crystal injection volume is 8 nanoliters, through the above analysis, the adjustment range can be set to 7 - 9 nanoliters;

[0090] Next, within the adjustment range of key process parameters, optimization methods such as orthogonal experimental design and response surface method are used to generate multiple combinations of process parameters. Each combination constitutes an optimization plan. By using orthogonal experimental design and selecting representative parameter combinations for experiments, the number of experiments can be significantly reduced and the efficiency can be improved. Suppose the key process parameters are liquid crystal injection volume, lamination pressure, and lamination speed, and each parameter is set at 3 levels. Through the orthogonal table to arrange the experiments, a set of optimization plans with different parameter combinations can be obtained. By using the response surface method, a mathematical model between process parameters and product quality is constructed, and the product quality under different parameter combinations is predicted according to the model. The parameter combination with the best predicted quality is selected as the optimization plan.

[0091] Subsequently, in the virtual manufacturing environment of intelligent liquid crystal display modules, each optimization plan is simulated. According to the set combination of process parameters, the entire manufacturing process is simulated, and the product quality index data under each plan is recorded, such as brightness uniformity, color accuracy, the number of pixel defects, etc. A multi-objective optimization algorithm is used to evaluate the simulation results, comprehensively considering multiple objectives such as product quality, production cost, and production efficiency. Set the weight of brightness uniformity to 0.4, the weight of color accuracy to 0.3, the weight of the number of pixel defects to 0.2, and the weight of production cost to 0.1. Calculate the comprehensive score according to the performance of each plan on these indicators.

[0092] Finally, compare the comprehensive scores of all optimization plans, and select the plan with the highest comprehensive score as the optimal process plan. If the comprehensive score of Plan A is 85 points, Plan B is 78 points, and Plan C is 82 points, then Plan A is the optimal process plan. Record the process parameters of the optimal plan to provide precise operation guidance for actual production, ensuring that process defects and product quality problems predicted can be effectively avoided or reduced during the actual manufacturing process, and improving the yield rate and overall quality of products.

[0093] Step 6: Apply the selected optimal process plan to the actual manufacturing process, and monitor the change of process parameter data in real time. If the process parameter data deviates from the parameter window, the adaptive adjustment mechanism is automatically activated.

[0094] Specifically, first, import the parameters and operation procedures of the selected optimal process plan into the actual manufacturing system, and conduct training for operators on the new process plan to make them familiar with the new process parameters, operation key points, and precautions. For example, if the liquid crystal injection pressure in the optimal plan becomes 0.025 MPa and the injection volume becomes 8.5 nanoliters, special training should be conducted for operators so that they can accurately set and adjust the equipment parameters.

[0095] Then, establish a complete process parameter monitoring system that can collect and record various process parameter data during the manufacturing process in real time; in the glass substrate pretreatment stage, monitor temperature and humidity; in the liquid crystal dropping stage, monitor dropping pressure and dropping volume; in the polarizer lamination stage, monitor lamination speed, lamination pressure, etc. Use devices such as sensors and data acquisition cards to transmit the collected process parameter data to the monitoring center; and based on the optimal process plan and historical production experience, set the reasonable range for each process parameter, that is, the parameter window; for example, the parameter window for the glass substrate pretreatment temperature is set to 78 - 82 °C, and the humidity parameter window is set to 28% - 32%; the liquid crystal dropping pressure parameter window is set to 0.023 - 0.027 MPa, and the dropping volume parameter window is set to 8.3 - 8.7 nanoliters;

[0096] Next, use the monitoring system to obtain the process parameter data in real time and compare and analyze it with the set parameter window; once it is found that a certain process parameter data exceeds the parameter window range, the system immediately issues an alarm signal; for example, when the real-time data of the liquid crystal dropping pressure is 0.028 MPa, which exceeds the parameter window range of 0.023 - 0.027 MPa, the system automatically issues an alarm; at the same time, when the process parameter data deviates from the parameter window, the adaptive adjustment mechanism is automatically activated; if the liquid crystal dropping pressure is too high, the system automatically adjusts the pressure control valve of the dropping device to reduce the dropping pressure and bring it back within the parameter window range; for some complex process parameter adjustments, the system can automatically calculate the appropriate adjustment value based on the preset algorithms and models, combined with historical data and real-time monitoring data, to ensure that the process parameters can quickly and accurately return to the normal range;

[0097] In addition, after the adaptive adjustment mechanism is activated, continuously monitor the changes in process parameters and product quality indicators to evaluate the adjustment effect; if the process parameters return to normal after adjustment and there is no obvious fluctuation in product quality, it indicates that the adjustment is effective; if there are still problems after adjustment, or new problems are caused, the system should give timely feedback, analyze the reasons, and optimize and improve the adaptive adjustment mechanism; through continuous evaluation and feedback, improve the accuracy and reliability of the adaptive adjustment mechanism to ensure the stability of the actual manufacturing process and the consistency of product quality.

[0098] Step 7: Use optical detection technology to detect the assembled display module, and adjust the process equipment through the feedback control system according to the detection results.

[0099] Specifically, first of all, according to the characteristics and detection requirements of the intelligent LCD display module, select appropriate optical detection equipment, such as high-resolution industrial cameras, laser scanning equipment, spectrometers, etc.; if you need to detect pixel defects of the display module, you can choose an industrial camera with high resolution and high frame rate; if you want to analyze the color accuracy of the display module, a spectrometer is a good choice; at the same time, in order to ensure the accuracy of the test results, it is necessary to build a stable test environment, control the light intensity, uniformity and color temperature of the test area, and avoid external light interference. A darkroom environment or a professional lighting system, such as a ring light source, backlight source, etc., can be used to meet different test requirements; in addition, before using the optical detection system, it should be strictly calibrated, and the focal length, aperture, gain and other parameters of the industrial camera should be adjusted through standard samples to ensure the accuracy of image acquisition; the wavelength and sensitivity of the laser scanning equipment and the spectrometer should be calibrated to ensure the reliability of the measurement data;

[0100] Then, clearly define the items and indicators that need to be tested, such as pixel defects (bright spots, dark spots, bad spots), brightness uniformity, color accuracy, contrast, viewing angle characteristics, etc. Different types of display modules have different detection focuses, which should be set according to the specifications and requirements of the product; at the same time, select appropriate detection methods for different detection items. For pixel defect detection, image analysis algorithms can be used to process and analyze the collected display images to identify abnormal pixels; for brightness uniformity detection, brightness sensors or industrial cameras can be used for multi-point measurement to calculate the brightness uniformity index; a reasonable detection process must also be formulated to ensure that each detection item can be carried out in an orderly manner. Generally speaking, an appearance inspection can be carried out first to eliminate obvious physical defects; then pixel defect detection, brightness uniformity detection, color accuracy detection, etc. can be carried out; finally, a comprehensive analysis and evaluation of the test results can be carried out;

[0101] Then, in the optical inspection process, the inspection data is collected in real time and preliminarily processed. The images collected by the industrial camera are subjected to noise reduction, filtering, enhancement and other processing to improve the image quality; the spectral data measured by the spectrum analyzer is analyzed and converted to obtain indicators such as color accuracy; and the inspection results are classified and judged according to the preset standards and thresholds, and pixel defects are divided into different levels, such as primary defects (seriously affecting the display effect) and secondary defects (slightly affecting the display effect). Indicators such as brightness uniformity and color accuracy are evaluated to determine whether they meet the quality requirements of the product; at the same time, the inspection data is statistically analyzed, and an inspection report is generated to statistically analyze the incidence and distribution of different types of defects, etc., to provide data support for subsequent process improvements; the inspection results, defect analysis, evaluation conclusions and other information are recorded in detail in the inspection report for the convenience of relevant personnel to review and refer to;

[0102] Subsequently, according to the detection results and the characteristics of the process equipment, corresponding control strategies are formulated; if it is detected that the brightness uniformity of the display module is poor, it can be improved by adjusting the brightness distribution of the backlight; if a high pixel defect rate is found, the parameters of the liquid crystal dispensing equipment can be adjusted, such as dispensing pressure, dispensing volume, etc.; and the interface between the feedback control system and the process equipment is developed to achieve real-time data transmission and accurate execution of instructions, using industrial communication protocols (such as Modbus, Profibus, etc.) or network communication technologies (such as TCP / IP, HTTP, etc.) to ensure that the feedback control system can communicate and interact effectively with the process equipment; at the same time, the control algorithm of the feedback control system is continuously optimized to improve the response speed and control accuracy of the system. PID control algorithm, fuzzy control algorithm, etc. can be used to adjust the parameters of the process equipment in real time according to the changes in the detection results, so as to effectively improve the product quality;

[0103] Finally, according to the instructions issued by the feedback control system, the parameters of the process equipment are adjusted, such as adjusting the temperature and humidity parameters of the glass substrate pretreatment equipment, optimizing the dispensing pressure and dispensing volume of the liquid crystal dispensing equipment, changing the bonding speed and bonding pressure of the polarizer bonding equipment, etc.;

[0104] In addition, the process equipment needs to be maintained and serviced regularly to ensure its normal operation. Clean the optical components and mechanical components of the equipment, check the electrical system and control system of the equipment, and replace the worn parts in time to ensure the stable performance of the equipment; at the same time, combined with the detection results and the adjustment of the process equipment, the manufacturing process is continuously improved and innovated, new process methods and technologies are explored, the process flow is optimized, and the product quality and production efficiency are improved.

[0105] In one embodiment, specifically, in step two, the method for constructing the correlation model between process parameters and product quality includes the following steps:

[0106] Step 201: Divide the preprocessed process parameter data and the corresponding product quality data into a training set, a validation set, and a test set according to a ratio;

[0107] Specifically, before constructing the model, the preprocessed process parameter data and the corresponding product quality data need to be divided; usually, according to the ratio of 70%, 15%, and 15%, the data is divided into a training set, a validation set, and a test set; assuming there are a total of 2000 groups of data, then the training set contains 2000×70% = 1400 groups of data, and the validation set and the test set each contain 2000×15% = 300 groups of data;

[0108] When dividing data, the method of random sampling can be adopted. First, number all the data, then use a random number generator to generate random numbers, and select data according to the numbers corresponding to the random numbers. This can ensure that each group of data has the same probability of being assigned to different sets, making the divided data set random and representative, avoiding data bias, and ensuring the accuracy of subsequent model training and evaluation.

[0109] Step 202: Use correlation analysis or principal component analysis to perform feature analysis on the process parameter data and screen out key features;

[0110] Specifically, correlation analysis: Calculate the correlation coefficient between each process parameter and the product quality index. Taking the liquid crystal display module as an example, the product quality indexes include brightness uniformity, color accuracy, pixel defect rate, etc. Use statistical methods, such as the Pearson correlation coefficient, to measure the linear correlation degree between the process parameter and these indexes;

[0111] For example, calculate the correlation coefficient between the liquid crystal dripping amount and the brightness uniformity. If the calculation result is 0.7, it indicates a strong positive correlation between the two; while the correlation coefficient between the humidity in the pre-treatment stage of the glass substrate and the pixel defect rate is 0.1, and the correlation is weak; Set a correlation coefficient threshold, such as 0.5, and screen out the process parameters with the absolute value of the correlation coefficient greater than 0.5. These are the key features that have a greater impact on the product quality;

[0112] Principal component analysis (PCA): For multiple interrelated process parameters, adopt the principal component analysis method. Take these process parameters as a whole and convert them into a group of uncorrelated principal components through PCA;

[0113] Suppose there are originally 6 process parameters. After PCA analysis, 3 principal components are obtained. These 3 principal components can retain most of the information of the original 6 parameters. For example, the cumulative contribution rate reaches more than 85%. Take these 3 principal components as new features to represent the original process parameter data. While reducing the data dimension, it can also effectively reflect the internal structure of the data and improve the efficiency of subsequent model construction and analysis.

[0114] Step 203: According to the data characteristics and problem types, select a linear regression model, a convolutional neural network, or a long short-term memory network as the association model, and use the training set data to train the selected association model;

[0115] Specifically, the application of the linear regression model is as follows:

[0116] When there is a linear relationship between process parameters and product quality, a linear regression model is selected; for example, if it is found that there is an approximately linear variation law between the polarizer lamination pressure and the display brightness uniformity, and the brightness uniformity shows a stable upward trend as the lamination pressure increases, a linear regression model can be used;

[0117] Take the process parameter data in the training set as the independent variable and the product quality data as the dependent variable, and determine the parameters in the model through the least squares method. During the process of continuously adjusting the parameters, minimize the sum of the squared errors between the model prediction value and the actual value. In this way, the model can fit the linear relationship between the process parameters and the product quality, and be used to predict the product quality under different process parameters;

[0118] The application of the convolutional neural network (CNN) is as follows:

[0119] If the process parameter data has a spatial structure or image-like features, and there is a complex non-linear relationship with the product quality, select the CNN model; for example, when analyzing the relationship between the pixel defects of a liquid crystal display module and the process parameters, organize the process parameter data related to the pixels into a data form similar to an image according to certain rules and input it into the CNN model;

[0120] CNN automatically extracts the features in the data through structures such as convolutional layers, pooling layers, and fully connected layers. During the training process, use the backpropagation algorithm to continuously adjust the weights of the model, so that the model can learn the rules in the data and improve the prediction accuracy of the product quality; for example, in the convolutional layer, perform a convolution operation by sliding the convolution kernel on the data to extract the local features in the data, and the pooling layer reduces the dimension of the features after convolution and retains the main information;

[0121] The application of the long short-term memory network (LSTM) is as follows:

[0122] When the process parameter data has time series features and the product quality is affected by previous process parameters, the LSTM model is more suitable; for example, during the continuous production of liquid crystal display modules, the liquid crystal dripping amount changes over time, and the current product quality is related to the dripping amount in a previous period;

[0123] The LSTM model processes this long-term dependence relationship through a gating mechanism (input gate, forget gate, and output gate). During training, input the training set data into the model in chronological order. The model will decide which information to retain and update according to the gating mechanism. As the training progresses, continuously optimize the parameters of the model so that the model can accurately predict the product quality. For example, the forget gate can control whether to retain the information of the previous moment, the input gate determines how the new information of the current moment is added, and the output gate determines the content of the output information.

[0124] Step 204: Evaluate and optimize the trained association model using the validation set, and test the optimized association model using the test set;

[0125] Specifically, first, use the validation set to evaluate the trained model. The main evaluation metrics include mean squared error (MSE), root mean squared error (RMSE), and coefficient of determination (R 2 );

[0126] Among them, MSE measures the average of the squares of the errors between the predicted values and the actual values of the model. The smaller the MSE value, the better the prediction effect of the model. For example, if the sum of the squares of the errors between the predicted values and the actual values of 300 product quality indicators in the validation set is 600, then MSE = 600 ÷ 300 = 2; RMSE is the square root of MSE, which can more intuitively reflect the average error between the predicted value and the actual value; R 2 is used to evaluate the goodness of fit of the model to the data, and its value range is between 0 and 1. The closer it is to 1, the better the fitting effect of the model;

[0127] If the MSE of the model on the validation set is large or R 2 is low, it indicates that the model performance does not meet the expectations and needs to be optimized. The hyperparameters of the model can be adjusted, such as the learning rate and the number of hidden layer nodes of the neural network model. Taking the learning rate as an example, if the initial learning rate is 0.01 and the model training effect is not good, the learning rate can be tried to be adjusted to 0.001 or 0.1, and the model is retrained to observe the performance change of the model on the validation set; the training data volume can also be increased to further improve the generalization ability of the model; regularization methods (such as L1 regularization, L2 regularization) can also be used to prevent the model from overfitting and make the model more stable; after multiple optimization adjustments, until the model reaches better performance on the validation set;

[0128] After completing the model optimization, use the test set to finally test the optimized model. By calculating the MSE, RMSE, and R on the test set 2 and other indicators, evaluate the performance of the model on unseen data, so as to test the generalization ability of the model;

[0129] If the indicators of the model on the test set perform well, it indicates that the model can accurately reflect the association relationship between process parameters and product quality and can be applied to actual production; if the indicators are not ideal, it is necessary to recheck the model construction, training, and optimization processes, find out the problems and make improvements.

[0130] In one embodiment, specifically, in step three, the method for constructing the virtual manufacturing environment of the intelligent liquid crystal display module includes the following steps:

[0131] Step 301: According to the actual physical structure and dimensions of the intelligent liquid crystal display module, use 3D modeling software to construct 3D models of each component, and assign corresponding material properties to each component;

[0132] Specifically, first, by referring to documents such as the design drawings and specification manuals of the intelligent liquid crystal display module, obtain the detailed physical structure and precise dimension information of each component; for example, for the glass substrate, clarify parameters such as its length, width, thickness, and surface flatness; for the liquid crystal layer, determine its thickness and uniformity requirements;

[0133] Then, according to the project requirements and the team's usage habits, select professional modeling software, and construct 3D models of each component in the modeling software in sequence according to the obtained physical structure and dimension information; taking the glass substrate as an example, use basic operations such as stretching and cutting in the software to create a cuboid model that matches the actual size; for the liquid crystal layer, a thin planar model can be created to represent it;

[0134] Finally, define corresponding material properties for each component; for the glass substrate, set its material as glass and endow it with optical properties (such as light transmittance, refractive index), mechanical properties (such as elastic modulus, Poisson's ratio), etc.; for the liquid crystal material, set its dielectric constant, viscosity, birefringence and other characteristics; these properties will affect the simulation results of subsequent physical phenomena.

[0135] Step 302: Combine the process parameter and product quality correlation model to construct a process model during the manufacturing process of the intelligent liquid crystal display module;

[0136] Specifically, first, deeply study the process parameter and product quality correlation model constructed in step two, and clarify the influence laws of various process parameters (such as temperature, pressure, speed, etc.) on product quality indicators (such as brightness uniformity, color accuracy, etc.);

[0137] Then, sort out each process link in the manufacturing process of the intelligent liquid crystal display module, including glass substrate pretreatment, liquid crystal dropping, polarizer lamination, assembly, etc., and analyze the key process parameters and operation processes involved in each process link;

[0138] Finally, combine the correlation model and process analysis to construct a process model in computer software; taking the liquid crystal dropping process as an example, according to the relationship between the dropping pressure and dropping volume and the product display effect in the correlation model, establish a mathematical model of the dropping process to simulate the distribution of liquid crystal under different dropping parameters and its influence on the final display quality.

[0139] Step 303: Use virtual reality technology to integrate the created 3D model and process model into a virtual scene to generate a virtual manufacturing environment;

[0140] Specifically, first, according to the requirements and technology stack of the project, select a suitable virtual reality development platform, such as Unity, Unreal Engine, etc. These platforms provide rich tools and functions, facilitating the integration of 3D models and process models into virtual scenarios;

[0141] Then, import the 3D model created in step 301 and the process model constructed in step 302 into the virtual reality development platform, ensuring that the model formats are compatible with the platform and maintaining the accuracy and integrity of the models during the import process;

[0142] Next, in the virtual reality development platform, build a virtual manufacturing scenario according to the layout and environment of the actual manufacturing workshop. Arrange the imported 3D models reasonably according to the actual production process, create environmental elements such as the floor, walls, and equipment of the workshop, and create a realistic manufacturing environment;

[0143] Finally, by writing scripts and programs, implement the interaction functions of the 3D model and the process model in the virtual scenario; for example, users can operate the equipment in the virtual scenario through virtual reality devices (such as joysticks, helmets, etc.), trigger the simulation of the process, and observe the changes in the manufacturing process and product quality under different operations and parameter settings.

[0144] Step 304: Based on the integrated physical simulation engine, simulate the physical phenomena in the virtual manufacturing environment;

[0145] Specifically, first, select a suitable physical simulation engine, such as PhysX, Bullet, etc., and integrate it into the virtual reality development platform. The physical simulation engine can simulate various physical phenomena, such as mechanics, optics, fluid dynamics, etc.;

[0146] Then, according to the material properties of the components and the requirements of the process, define corresponding physical parameters for each object in the virtual manufacturing environment; for example, set mechanical parameters such as mass, density, and friction for the glass substrate; set fluid dynamics parameters such as viscosity and surface tension for the liquid crystal material;

[0147] Finally, use the physical simulation engine to simulate the physical phenomena in the virtual manufacturing environment; during the liquid crystal dropping process, simulate the flow and diffusion process of the liquid crystal, considering the influence of factors such as surface tension and gravity; during the polarizer lamination process, simulate the pressure distribution and stress changes during lamination; through the simulation of physical phenomena, more realistically reflect the problems that occur during the manufacturing process and the quality of the product.

[0148] Step 305: Develop a data interaction interface between the virtual manufacturing environment and the actual manufacturing system to perform real-time data transmission and synchronization between the two;

[0149] Specifically, first, clarify the data content and format that need to be interacted between the virtual manufacturing environment and the actual manufacturing system. For example, the actual manufacturing system needs to transmit real-time process parameter data (such as temperature, pressure, speed, etc.) to the virtual manufacturing environment, and the virtual manufacturing environment needs to feedback the predicted process defects and product quality evaluation results to the actual manufacturing system.

[0150] Then, select a suitable data interaction method according to the actual situation, such as network communication (such as TCP / IP, HTTP, etc.), industrial bus (such as Modbus, Profibus, etc.), to ensure the stability and real-time performance of data interaction.

[0151] Finally, develop a data interaction interface using programming languages (such as Python, Java, etc.) to achieve data transmission and synchronization between the virtual manufacturing environment and the actual manufacturing system. During the interface development process, follow the corresponding data protocols and standards to ensure the accuracy and compatibility of data. At the same time, encrypt and verify the data to ensure data security.

[0152] In one embodiment, specifically, in step five, the method for screening out the optimal process plan includes the following steps:

[0153] Step 501: Classify the process defects and product quality problems, analyze the causes of each problem, and combine the process parameter and product quality correlation model to determine the key process parameters related to the problem.

[0154] Specifically, first, carefully classify the predicted process defects and product quality problems. Taking the intelligent liquid crystal display module as an example, the problems can be classified into display problems (such as uneven brightness, color deviation, insufficient contrast, etc.), structural problems (such as loose fitting of glass substrates, bubbles in polarizers, uneven thickness of liquid crystal layers, etc.), and functional problems (such as too long response time, too narrow viewing angle, etc.).

[0155] Then, for each type of problem, deeply analyze its causes. For the problem of uneven brightness, it is caused by inconsistent liquid crystal injection volume, different backlight emission intensities, or deviation of polarizer angles, etc. For the problem of loose fitting of glass substrates, it is caused by insufficient fitting pressure, too fast fitting speed, or impurities on the fitting surface, etc.

[0156] Finally, combine the process parameter and product quality correlation model to find the key process parameters closely related to each problem. If the correlation model shows that the liquid crystal injection pressure and injection volume have a great impact on the uniformity of the liquid crystal layer thickness, and the uniformity of the liquid crystal layer thickness directly affects the display brightness uniformity, then the liquid crystal injection pressure and injection volume are the key process parameters to solve the problem of uneven brightness.

[0157] Step 502: Based on the key process parameters related to the problem, determine the adjustment range of the key process parameters according to historical production data, industry experience, and simulation results in the virtual manufacturing environment;

[0158] Specifically, first, consult the production records of previous similar products, and count the problems that occurred in the products under different process parameter settings and the corresponding yield rates; if the historical data shows that when the liquid crystal dropping pressure is between 0.015 - 0.025 MPa, the problem of brightness uniformity of the product rarely occurs, then this range can be used as a preliminary reference;

[0159] Then, study the process parameter settings and experience summaries of other enterprises in the same industry when producing similar intelligent liquid crystal display modules, refer to industry standards and technical literature, and understand the general value range and adjustment principles of key process parameters;

[0160] Finally, conduct multiple sets of exploratory simulations in the virtual manufacturing environment, observe the impact of key process parameters on product quality under different values, gradually increase or decrease the value of a certain parameter, and record the changes in product quality indicators, so as to determine a reasonable adjustment range that can solve the problem without causing other new problems; for example, through simulation, it is found that when the polarizer bonding pressure is between 40 - 60 N, the bonding effect is better and the polarizer will not be damaged, then this range is the adjustment range of the polarizer bonding pressure.

[0161] Step 503: Within the adjustment range of the key process parameters, use orthogonal experimental design and response surface method to generate multiple process parameter combinations, and each process parameter combination constitutes an optimization plan;

[0162] Among them, orthogonal experimental design is an efficient experimental design method. It can select representative partial combinations from numerous process parameter combinations for experiments. According to the determined key process parameters and the adjustment range of each parameter, each parameter is divided into several levels; assume that the liquid crystal dropping pressure has three levels: 0.015 MPa, 0.02 MPa, and 0.025 MPa, and the liquid crystal dropping volume has three levels: 7 nanoliters, 8 nanoliters, and 9 nanoliters. Use the orthogonal table to arrange the experiments to obtain a set of experimental plans with different parameter combinations;

[0163] Among them, the response surface method is to predict the product quality under different parameter combinations by constructing a mathematical model between process parameters and product quality; first, select a certain number of experimental points within the adjustment range of the key process parameters for simulation experiments, and collect the product quality data corresponding to each experimental point; then, use these data to fit a response surface model, usually a quadratic polynomial model; finally, predict the product quality under different parameter combinations according to the response surface model, and select the parameter combination with the best predicted quality as the optimization plan.

[0164] Step 504: In the virtual manufacturing environment of the intelligent liquid crystal display module, simulate and rehearse each optimization plan, and evaluate it using a multi-objective optimization algorithm to obtain the comprehensive score of each optimization plan;

[0165] Specifically, first, in the virtual manufacturing environment of the intelligent liquid crystal display module, simulate the manufacturing according to the process parameter combinations of each optimization plan; simulate the entire production process, including glass substrate pretreatment, liquid crystal dropping, polarizer lamination, assembly, etc., and record the product quality index data under each plan, such as brightness uniformity, color accuracy, pixel defect rate, production cost, production efficiency, etc.;

[0166] Then, use a multi-objective optimization algorithm to evaluate the simulation results of each plan; common multi-objective optimization algorithms include the Analytic Hierarchy Process (AHP), genetic algorithm, etc.; first, determine the weight of each product quality index, for example, the weight of brightness uniformity is 0.3, the weight of color accuracy is 0.2, the weight of pixel defect rate is 0.2, the weight of production cost is 0.15, and the weight of production efficiency is 0.15; then, calculate the comprehensive score according to the performance of each plan in each index.

[0167] Step 505: Compare the comprehensive scores of all optimization plans, and select the plan with the highest comprehensive score as the optimal process plan;

[0168] Specifically, compare the comprehensive scores of all optimization plans, and select the plan with the highest comprehensive score as the optimal process plan; this plan achieves a relatively good balance in multiple aspects such as product quality, production cost, and production efficiency, and can effectively avoid or reduce the predicted process defects and product quality problems, providing the best process parameter settings for actual production; in practical applications, the optimal plan can also be further verified and fine-tuned to ensure its effectiveness and stability in the actual production environment.

[0169] In one embodiment, specifically, in step six, the parameter window is the normal fluctuation range of process parameters determined by statistically analyzing historical production data and combining product quality standards;

[0170] Specifically, the statistical analysis of historical production data is as follows:

[0171] Comprehensively collect various process parameter data in the past production process of the intelligent liquid crystal display module, covering the temperature and humidity in the glass substrate pretreatment link; the pressure and dropping amount in the liquid crystal dropping stage; the speed and pressure in the polarizer lamination process, etc.; at the same time, record the quality inspection data of the corresponding products, such as brightness uniformity, color accuracy, pixel defect rate, etc.;

[0172] Clean the collected data, removing outliers and incorrect data. Data that is significantly deviated from the normal range due to equipment failures or human operation errors should be corrected or deleted to ensure the accuracy and reliability of the data. Then, classify and organize the data according to different process steps and product models for convenient subsequent statistical analysis.

[0173] Calculate statistical measures such as the mean and median of each process parameter to understand the central tendency of the parameters. For example, calculating the mean of the pre-treatment temperature of the glass substrate can help grasp the average level of this parameter in historical production.

[0174] Analyze the dispersion degree of process parameters by calculating statistical measures such as the standard deviation and variance. The smaller the standard deviation, the smaller the parameter fluctuations and the more stable the production process.

[0175] Study the correlations between different process parameters and between process parameters and product quality indicators. If a strong positive correlation is found between the liquid crystal dripping volume and the display brightness uniformity, this factor needs to be considered key when determining the parameter window.

[0176] Use process capability indices (such as Cp, Cpk) to evaluate the stability and capability of the production process. The higher the process capability index, the more stable the production process can operate within the specified range and the more guaranteed the product quality.

[0177] The specific implementation method for determining the parameter window in combination with the product quality standard is as follows:

[0178] Based on the design requirements of the product and market demands, clarify the standard ranges of various product quality indicators. For example, it is stipulated that the brightness uniformity of the display module should be not less than 90%, and the Delta E value of color accuracy should be less than 3, etc.

[0179] Based on the statistical analysis results, establish a mathematical model between process parameters and product quality indicators. Through methods such as regression analysis and machine learning, find out the influence law of process parameters on product quality.

[0180] According to the parameter-quality relationship model and the product quality standard, determine the normal fluctuation range of each process parameter, that is, the parameter window. Taking the liquid crystal dripping pressure as an example, combining model analysis and quality standards, set its parameter window as 0.022 - 0.026 MPa.

[0181] In addition, new production data should be regularly collected to update and supplement the historical data, and then re - conduct statistical analysis to evaluate the rationality and effectiveness of the parameter window. According to the new analysis results and the actual production situation, dynamically adjust the parameter window. If it is found that with the improvement of the production process, the fluctuation range of a certain process parameter can be appropriately expanded, then correspondingly adjust the window range of this parameter. By continuously optimizing the parameter window and the adaptive adjustment mechanism, improve the stability of the production process and the consistency of product quality, and achieve the precise manufacturing of intelligent liquid crystal display modules.

[0182] In one embodiment, specifically, in step one, the process parameter data is obtained by arranging sensors at each key link in the manufacturing process of the liquid crystal display module.

[0183] The process parameter data includes the temperature and humidity data in the glass substrate pretreatment stage, the dropping pressure and dropping volume data during the liquid crystal dropping process, and the bonding speed and bonding pressure data when bonding the polarizer.

[0184] Among them, in the glass substrate pretreatment link, for the temperature sensor, a high - precision and fast - response thermocouple temperature sensor or a thermistor temperature sensor is selected and arranged in the heating area of the glass substrate pretreatment equipment and on the surface of the glass substrate to accurately measure the temperature change during the pretreatment process. The humidity sensor uses a capacitive humidity sensor, which has the characteristics of high measurement accuracy and good stability, and is installed in the internal space of the pretreatment equipment to monitor the humidity situation in real - time.

[0185] In the liquid crystal dropping link, a strain - type pressure sensor is selected as the pressure sensor, which can accurately measure the pressure change during the dropping process. It is installed on the infusion pipeline of the dropping equipment, close to the dropper position, to ensure accurate acquisition of the dropping pressure data. The flow sensor can use a positive - displacement flow sensor or a mass flow sensor, which is installed in the infusion pipeline to monitor the dropping volume of the liquid crystal in real - time.

[0186] In the polarizer bonding link, an optoelectronic speed sensor or an encoder is used as the speed sensor, which is installed on the transmission component of the bonding equipment to measure the bonding speed. The pressure sensor also selects a strain - type pressure sensor, which is installed on the pressing head part of the bonding equipment to monitor the bonding pressure in real - time.

[0187] The pretreatment includes data cleaning, data standardization, and data missing value handling. The specific handling methods are as follows:

[0188] Data cleaning: The data collected by sensors contains interference information such as noise and outliers, which needs to be cleaned. Outliers are removed by setting reasonable data ranges. For example, the normal range of the liquid crystal infusion volume is between 5 and 10 nanoliters. If the collected infusion volume data is less than 1 nanoliter or greater than 20 nanoliters, it can be judged as an outlier and removed. For noise data, filtering algorithms are used for processing, such as the mean filtering algorithm. By calculating the average value of the data within a certain time window, the data is smoothed and the influence of random noise is removed. Suppose a set of collected infusion pressure data is [1.2, 1.3, 1.1, 1.5, 1.4]. After mean filtering, the new data is [(1.2 + 1.3 + 1.1) / 3, (1.3 + 1.1 + 1.5) / 3, (1.1 + 1.5 + 1.4) / 3], that is, [1.2, 1.3, 1.3], making the data smoother and more stable.

[0189] Data standardization: Different types of process parameter data have different dimensions and value ranges. To facilitate subsequent data analysis and model construction, the data needs to be standardized. The normalization method is adopted to map the data into the interval of 0 - 1.

[0190] For temperature data, assuming its value range is 20 - 40 °C, the formula:

[0191]

[0192] is used for normalization, where x is the original data, x min = 20, x max = 40;

[0193] If a certain temperature data is 30 °C, then after normalization, it is:

[0194]

[0195] For pressure data, normalization is also carried out according to its actual value range to ensure that all data is analyzed on a unified scale.

[0196] Data missing value handling: In the data collection process, data missing may occur. For a small amount of missing data, the interpolation method is used for supplementation.

[0197] Such as the linear interpolation method. Suppose in the humidity data collected within a certain time period, there is a missing data point. Given that the two adjacent data points are x1 and x2, and the corresponding time points are t1 and t2, and the time point of the missing data point is t, then the missing data x can be calculated by the formula:

[0198]

[0199] for calculation.

[0200] For the case of a large amount of missing data, it is necessary to re-check the working status of the sensor, and after repairing or replacing the faulty sensor, collect data again.

[0201] In one embodiment, specifically, in step seven, the detection indicators include the brightness uniformity, color accuracy, and pixel defects of the display module;

[0202] Among them, the brightness uniformity is detected using a high-precision luminance meter or an imaging luminance analysis system. To ensure the accuracy of the detection results, it is necessary to operate in a darkroom environment to avoid interference from external light. The walls of the darkroom are made of light-absorbing materials, and the lighting equipment is turned off to prevent light reflection from affecting the measurement. The display module is fixed on a stable test bench, and the angle and position are adjusted so that the detection equipment can completely and accurately collect the light data emitted by the display module;

[0203] The color accuracy is precisely measured using a spectral analyzer to analyze the spectral characteristics of the light emitted by the display module. The spectral analyzer can analyze the spectral components of the light emitted by the display module to determine the difference between its color performance and the standard color;

[0204] Pixel defects are captured by using a high-resolution industrial camera with a suitable lens. The resolution of the industrial camera should be high enough to clearly distinguish each pixel. Before detection, it is necessary to adjust the focal length, aperture, and exposure time of the camera to ensure that the captured image is clear and accurate and can truly reflect the state of the pixel.

[0205] In summary, a precise manufacturing method for an intelligent liquid crystal display module provided by an embodiment of the present invention arranges sensors at key links in the manufacturing process to obtain process parameter data and preprocess it, constructs a correlation model between process parameters and product quality using big data analysis, constructs a virtual manufacturing environment with the help of computer-aided design and virtual reality technology, simulates the manufacturing process to predict problems and optimize the process plan, applies the optimal plan to actual production and monitors and adjusts it in real time, and finally uses optical detection technology to detect the product and provide feedback for correction, realizing precise control of the manufacturing process, significantly improving the manufacturing accuracy and yield rate of the product, reducing the influence of human factors, enhancing the market competitiveness of the product, and effectively solving problems such as low process accuracy, poor equipment performance, and poor system coordination existing in traditional manufacturing methods.

[0206] Figure 5 is a schematic diagram of the functional modules of an intelligent liquid crystal display module precise manufacturing system according to an embodiment of the present application. As Figure 5 shown, an intelligent liquid crystal display module precise manufacturing system includes: a data acquisition and processing module, a data analysis and modeling module, a virtual environment construction module, a simulation and prediction module, a scheme screening module, a production monitoring and adjustment module, and a detection and feedback module;

[0207] A data acquisition and processing module, configured to acquire process parameter data in the manufacturing process of a liquid crystal display module and perform preprocessing;

[0208] A data analysis and modeling module, configured to use big data analysis algorithms to deeply analyze the preprocessed process parameter data and construct a correlation model between process parameters and product quality;

[0209] A virtual environment construction module, configured to construct a virtual manufacturing environment for an intelligent liquid crystal display module based on the correlation model between process parameters and product quality, using computer-aided design and virtual reality technologies;

[0210] A simulation and prediction module, configured to simulate the manufacturing process based on the virtual manufacturing environment of the intelligent liquid crystal display module and predict process defects and product quality problems that occur;

[0211] A solution screening module, configured to perform process parameter adjustment and optimization solution rehearsal in the virtual manufacturing environment of the intelligent liquid crystal display module according to the predicted process defects and product quality problems, and screen out the optimal process solution;

[0212] A production monitoring and adjustment module, configured to apply the selected optimal process solution to the actual manufacturing process, monitor the change of process parameter data in real time, and automatically start an adaptive adjustment mechanism if the process parameter data deviates from the parameter window;

[0213] An inspection and feedback module, configured to inspect the assembled display module using optical inspection technology based on inspection indicators, and adjust the process equipment through a feedback control system according to the inspection results.

[0214] For other details of the implementation technical solutions of each module in the above-mentioned intelligent liquid crystal display module precision manufacturing system of the above embodiment, reference can be made to the description in the above-mentioned intelligent liquid crystal display module precision manufacturing method of the above embodiment, which will not be elaborated here.

[0215] It should be noted that each embodiment in this specification is described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts between each embodiment can be referred to each other. For system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0216] Such as Figure 6 This is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. It shows a schematic structural diagram of an electronic device suitable for implementing the electronic device in the embodiment of the present disclosure. Figure 6 The shown electronic device is only an example and should not bring any limitation to the functions and usage scope of the embodiments of the present disclosure.

[0217] As shown Figure 6 in the figure, an electronic device may include a processor (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the electronic device are also stored. The processor, ROM, and RAM are connected to each other through a bus. An input / output (I / O) interface is also connected to the bus.

[0218] Generally, the following devices may be connected to the I / O interface: an input device including, for example, a sensor or a visual information acquisition device, etc.; an output device including, for example, a display screen, etc.; a storage device including, for example, a magnetic tape, a hard disk, etc.; and a communication device. The communication device may allow the electronic device to communicate wirelessly or wiredly with other devices (such as edge computing devices) to exchange data. Although Figure 6 an electronic device with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had.

[0219] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program codes for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by the processor, all or part of the steps of a precise manufacturing method for an intelligent liquid crystal display module according to an embodiment of the present disclosure are executed.

[0220] For a detailed description of this embodiment, reference may be made to the corresponding descriptions in the foregoing embodiments, and details will not be repeated here.

[0221] A computer-readable storage medium according to an embodiment of the present disclosure stores non-transitory computer-readable instructions. When the non-transitory computer-readable instructions are run by a processor, all or part of the steps of a precise manufacturing method for an intelligent liquid crystal display module according to the foregoing embodiments of the present disclosure are executed.

[0222] The above-mentioned computer-readable storage medium includes but is not limited to: optical storage media (such as: CD-ROM and DVD), magneto-optical storage media (such as: MO), magnetic storage media (such as: magnetic tape or removable hard disk), media with built-in rewritable non-volatile memory (such as: memory card), and media with built-in ROM (such as: ROM cartridge).

[0223] For the detailed description of this embodiment, reference may be made to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0224] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are only examples and not limitations. It cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present disclosure. In addition, the above-mentioned specific details are only for illustrative and easy-to-understand purposes, rather than limitations. The above details do not limit the present disclosure to necessarily adopt the above specific details to implement.

[0225] In the present disclosure, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The block diagrams of the devices, apparatuses, equipment, and systems involved in the present disclosure are only illustrative examples and do not intend to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open-ended terms meaning "including but not limited to" and can be used interchangeably with them. The words "or" and "and" used herein refer to the word "and / or" and can be used interchangeably with it, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to" and can be used interchangeably with it.

[0226] In addition, as used herein, the "or" used in the listing of items starting with "at least one" indicates a separate listing, so that for example, the listing of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the term "exemplary" does not mean that the described examples are preferred or better than other examples.

[0227] It should also be noted that in the systems and methods of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present disclosure.

[0228] Various changes, substitutions, and alterations to the technology described herein can be made without departing from the teachings defined by the appended claims. Additionally, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and acts described above. Processes, machines, manufactures, compositions of events, means, methods, or acts that are currently available or later to be developed that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Accordingly, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or acts within their scope.

[0229] The foregoing description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein. The foregoing description has been presented for purposes of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although numerous example aspects and embodiments have been discussed above, those skilled in the art will recognize some variations, modifications, alterations, additions, and subcombinations thereof.

Claims

1. A precise manufacturing method for an intelligent liquid crystal display module, characterized in that, The steps include the following: Obtain the process parameter data during the manufacturing process of the liquid crystal display module and perform preprocessing; Use big data analysis algorithms to deeply analyze the preprocessed process parameter data and construct a correlation model between process parameters and product quality; Based on the correlation model between process parameters and product quality, use computer-aided design and virtual reality technologies to construct a virtual manufacturing environment for intelligent liquid crystal display modules; Based on the virtual manufacturing environment for intelligent liquid crystal display modules, simulate the manufacturing process and predict the process defects and product quality problems that may occur; According to the predicted process defects and product quality problems, perform process parameter adjustment and optimization plan rehearsal in the virtual manufacturing environment for intelligent liquid crystal display modules, and screen out the optimal process plan; Apply the selected optimal process plan to the actual manufacturing process, and monitor the changes in process parameter data in real time. If the process parameter data deviates from the parameter window, automatically start the adaptive adjustment mechanism; Based on the detection indicators, use optical detection technology to detect the assembled display module, and adjust the process equipment through a feedback control system according to the detection results.

2. The precise manufacturing method of an intelligent liquid crystal display module according to claim 1, characterized in that: The method for constructing the correlation model between process parameters and product quality includes the following steps: Divide the preprocessed process parameter data and the corresponding product quality data into a training set, a validation set, and a test set according to a certain proportion; Use correlation analysis or principal component analysis to perform feature analysis on the process parameter data and screen out the key features; According to the data characteristics and problem types, select a linear regression model, a convolutional neural network, or a long short-term memory network as the correlation model, and use the training set data to train the selected correlation model; Use the validation set to evaluate and optimize the trained correlation model, and use the test set to test the optimized correlation model.

3. A precise manufacturing method for an intelligent liquid crystal display module according to claim 1, characterized in that: The method for constructing the virtual manufacturing environment for intelligent liquid crystal display modules includes the following steps: According to the actual physical structure and size of the intelligent liquid crystal display module, use 3D modeling software to construct 3D models of each component and assign corresponding material properties to each component; Combine the correlation model between process parameters and product quality to construct a process model during the manufacturing process of intelligent liquid crystal display modules; Use virtual reality technology to integrate the created 3D models and process models into a virtual scene to generate a virtual manufacturing environment; Based on the integrated physical simulation engine, simulate the physical phenomena in the virtual manufacturing environment; Develop a data interaction interface between the virtual manufacturing environment and the actual manufacturing system for real-time data transmission and synchronization between the two.

4. The precise manufacturing method of an intelligent liquid crystal display module according to claim 1, characterized in that: The method for screening out the optimal process plan includes the following steps: Classify the process defects and product quality problems, analyze the causes of each problem, and combine the correlation model between process parameters and product quality to determine the key process parameters related to the problem; Based on the key process parameters related to the problem, determine the adjustment range of the key process parameters according to historical production data, industry experience, and simulation results in the virtual manufacturing environment; Within the adjustment range of the key process parameters, use orthogonal experimental design and response surface method to generate multiple combinations of process parameters, and each combination of process parameters constitutes an optimization plan; In the virtual manufacturing environment of the intelligent liquid crystal display module, each optimization plan is simulated and rehearsed, and evaluated using a multi-objective optimization algorithm to obtain the comprehensive score of each optimization plan; Compare the comprehensive scores of all optimization plans, and select the plan with the highest comprehensive score as the optimal process plan.

5. A precise manufacturing method for an intelligent liquid crystal display module according to claim 1, characterized in that: The parameter window is the normal fluctuation range of process parameters determined by statistically analyzing historical production data and combining product quality standards.

6. A precise manufacturing method for an intelligent liquid crystal display module according to claim 1, characterized in that: The process parameter data is obtained by arranging sensors at each key link in the manufacturing process of the liquid crystal display module; The process parameter data includes temperature and humidity data in the glass substrate pretreatment stage, dropping pressure and dropping volume data in the liquid crystal dropping process, and fitting speed and fitting pressure data during polarizer fitting; The pretreatment includes data cleaning, data standardization, and data missing processing.

7. A precise manufacturing method for an intelligent liquid crystal display module according to claim 1, characterized in that: The detection indicators include the brightness uniformity, color accuracy, and pixel defects of the display module.

8. An intelligent liquid crystal display module precise manufacturing system, which is applied to an intelligent liquid crystal display module precise manufacturing method according to any one of claims 1-7, and is characterized in that, The system includes: a data acquisition and processing module, a data analysis and modeling module, a virtual environment construction module, a simulation prediction module, a plan screening module, a production monitoring and adjustment module, and a detection and feedback module; The data acquisition and processing module is configured to obtain process parameter data in the manufacturing process of the liquid crystal display module and perform pretreatment; The data analysis and modeling module is configured to deeply analyze the pretreated process parameter data using big data analysis algorithms and build a correlation model between process parameters and product quality; The virtual environment construction module is configured to build a virtual manufacturing environment for the intelligent liquid crystal display module based on the correlation model between process parameters and product quality, using computer-aided design and virtual reality technologies; The simulation prediction module is configured to simulate the manufacturing process based on the virtual manufacturing environment of the intelligent liquid crystal display module and predict process defects and product quality problems that occur; The plan screening module is configured to adjust process parameters and pre-rehearse optimization plans in the virtual manufacturing environment of the intelligent liquid crystal display module according to the predicted process defects and product quality problems, and screen out the optimal process plan; The production monitoring and adjustment module is configured to apply the selected optimal process plan to the actual manufacturing process, monitor the change of process parameter data in real time, and automatically start the adaptive adjustment mechanism if the process parameter data deviates from the parameter window; The detection and feedback module is configured to detect the assembled display module using optical detection technology based on the detection indicators, and adjust the process equipment through the feedback control system according to the detection results.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute an accurate manufacturing method for an intelligent liquid crystal display module according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to execute an accurate manufacturing method for an intelligent liquid crystal display module according to any one of claims 1-7.

Images