Organic light-emitting display manufacturing process optimization method

Abstract

The invention relates to the technical field of organic light-emitting display manufacturing data processing, and provides an organic light-emitting display manufacturing process optimization method, which comprises the following steps of: acquiring multi-source data of an organic light-emitting display manufacturing process, performing simulation and optimization by using a digital twin model, monitoring process parameters in real time and comparing errors; and iteratively optimizing the control model by adopting a genetic algorithm or a particle swarm optimization algorithm, finally obtaining a real-time optimized control model, deploying and applying, solving the problem that the process data cannot be effectively monitored and optimized in the prior art, improving the adaptive adjustment capability of the process, reducing the trial and error cost and time, and improving the accuracy of the process data. The process stability is improved, and the organic light-emitting display manufacturing data processing capacity is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing for organic light-emitting display manufacturing, and particularly to a method for optimizing the manufacturing process of organic light-emitting displays. Background Art

[0002] The manufacturing process of organic light-emitting displays is a complex and delicate process. First, a transparent conductive substrate needs to be fabricated, usually using glass or plastic materials, and then cleaned and surface-treated. Next, organic light-emitting display materials, such as hole-transporting materials, light-emitting materials, and electron-transporting materials, are prepared through precise synthesis methods. Then, these organic material layers are deposited on the substrate to form a hole-transporting layer, a light-emitting layer, an electron-transporting layer, etc. At the same time, a metal cathode and a transparent conductive anode are fabricated, and their thickness and uniformity are controlled. After the deposition of the organic layers, a packaging process is carried out to protect the organic light-emitting display from the external environment and oxygen. Finally, the organic light-emitting display device is tested and aged to ensure its performance and stability. During the whole process, the evaporation deposition of organic thin films is one of the key technologies, and common methods include vacuum thermal evaporation and organic vapor deposition. These steps together constitute the manufacturing process of organic light-emitting display devices, making them have the characteristics of being thin, light, power-saving, high contrast, wide viewing angle, and low energy consumption.

[0003] In the manufacturing process of organic light-emitting displays, when optimizing the data processing process, there are the following technical pain points: The manufacturing of organic light-emitting displays involves the deposition of multiple layers of organic thin films, and the thickness, uniformity, and material composition of each layer of film need to be controlled. A large amount of data is generated during the manufacturing process of organic light-emitting displays, including process parameters, equipment status, environmental conditions, etc. It is necessary to quickly respond to process changes and optimize the production process. However, the existing technologies cannot monitor and optimize the data generated by the manufacturing process of organic light-emitting displays, resulting in the inability to make the manufacturing process of organic light-emitting displays adaptively adjusted. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a method for optimizing the manufacturing process of organic light-emitting displays, which solves the problem that the existing technologies cannot monitor and optimize the data generated by the manufacturing process of organic light-emitting displays, resulting in the inability to make the manufacturing process of organic light-emitting displays adaptively adjusted.

[0005] To solve the above technical problems, the specific technical solution of the present invention is as follows: The present invention provides a method for optimizing the manufacturing process of organic light-emitting displays, including: Step S101, obtaining the historical tasks of the manufacturing process of organic light-emitting displays, the process parameter data of the manufacturing process of organic light-emitting displays, the environmental condition data of the manufacturing process of organic light-emitting displays, the material composition data of the manufacturing process of organic light-emitting displays, the manufacturing control model of organic light-emitting displays, and the historical data of the manufacturing process of organic light-emitting displays; Step S102: Establish a corresponding relationship among the organic light-emitting display manufacturing process historical tasks, organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data, and organic light-emitting display manufacturing control model according to the organic light-emitting display manufacturing historical data, and obtain an organic light-emitting display manufacturing process data group; Step S103: Substitute the organic light-emitting display manufacturing process data group into the pre-constructed digital twin model in sequence to obtain the digital twin model image data and operation parameter data corresponding to each organic light-emitting display manufacturing process data in the organic light-emitting display manufacturing process data group, and summarize the digital twin model image data and operation parameter data to obtain a digital twin model operation parameter data group; Step S104: Establish a corresponding relationship between the digital twin model operation parameter data group and the organic light-emitting display manufacturing process parameter data according to the organic light-emitting display manufacturing process historical tasks, and obtain the organic light-emitting display manufacturing process parameter data corresponding to the digital twin model operation parameter data group. Compare the digital twin model operation parameter data in the digital twin model operation parameter data group with the corresponding organic light-emitting display manufacturing process parameter data in sequence to obtain an organic light-emitting display manufacturing parameter error comparison result; Step S105: Obtain the real-time organic light-emitting display manufacturing process task, match the real-time organic light-emitting display manufacturing process task with the organic light-emitting display manufacturing process historical tasks to obtain an organic light-emitting display manufacturing process historical task similar to the real-time organic light-emitting display manufacturing process task, and retrieve the organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data, and organic light-emitting display manufacturing control model corresponding to the similar organic light-emitting display manufacturing process historical task. Use an optimization algorithm to optimize the organic light-emitting display manufacturing control model based on the real-time organic light-emitting display manufacturing process task and the organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, and organic light-emitting display manufacturing process material composition data corresponding to the organic light-emitting display manufacturing process historical task similar to the real-time organic light-emitting display manufacturing process task, and obtain a real-time optimized organic light-emitting display manufacturing control model. Deploy the real-time optimized organic light-emitting display manufacturing control model as the organic light-emitting display manufacturing control model for real-time use in the organic light-emitting display manufacturing process.

[0006] Furthermore, for the organic light-emitting display manufacturing process optimization method of the present invention, the step S101 includes: The organic light-emitting display manufacturing process historical tasks include task type, task scale, and task time; The organic light-emitting display manufacturing process parameter data includes temperature, pressure, time, current, and voltage; The environmental condition data of the organic light-emitting display manufacturing process include environmental humidity, temperature, and cleanliness; The material composition data of the organic light-emitting display manufacturing process include substrate materials, light-emitting layer materials, and electrode materials; The organic light-emitting display manufacturing control model includes a model for controlling the organic light-emitting display manufacturing process; The historical data of the organic light-emitting display manufacturing include, but are not limited to, process execution records, product test results, and fault records.

[0007] Further, in the method for optimizing the organic light-emitting display manufacturing process according to the present invention, step S102 includes: Associate each historical task of the organic light-emitting display manufacturing process with the corresponding organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data, and organic light-emitting display manufacturing control model; Establish identifiers for each historical task of the organic light-emitting display manufacturing process and the organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data, and organic light-emitting display manufacturing control model. Form an organic light-emitting display manufacturing process data group with the associated data. The organic light-emitting display manufacturing process data group includes task information and the data set corresponding to each task. Establish a correspondence table, and record the association relationship between each task and the corresponding data set, as well as the association relationship between the parameters within the data set in the correspondence table.

[0008] Further, in the method for optimizing the organic light-emitting display manufacturing process according to the present invention, step S103 includes: Substitute each data group in the organic light-emitting display manufacturing process data group into the digital twin model in sequence, start the digital twin model, and run it according to each data group input in the organic light-emitting display manufacturing process data group. Input the simulation results corresponding to each data group in the organic light-emitting display manufacturing process data group. The simulation results corresponding to each data group in the organic light-emitting display manufacturing process data group include image data and operation parameter data of the organic light-emitting display manufacturing process. During the operation of the digital twin model, generate digital twin model image data and operation parameter data in real time.

[0009] Further, in the method for optimizing the organic light-emitting display manufacturing process according to the present invention, step S104 includes: Establish an index for each group of digital twin model operation parameter data, and match each parameter in the digital twin model operation parameter data group with the corresponding organic light-emitting display manufacturing process parameter data according to the index; Compare the differences between the operation parameters of the digital twin model and the actual organic light-emitting display manufacturing process parameter data in sequence, and calculate the error values of each group of comparison parameters; Summarize the error values of the comparison parameters to form the error comparison result of the organic light-emitting display manufacturing parameters.

[0010] Furthermore, in the organic light-emitting display manufacturing process optimization method of the present invention, the step S105 includes: The real-time organic light-emitting display manufacturing process task includes task type, specification requirements, and production target; Match the real-time organic light-emitting display manufacturing process task with the organic light-emitting display manufacturing process historical task database, Use the similarity algorithm to match the real-time organic light-emitting display manufacturing process task with the closest organic light-emitting display manufacturing process historical task; Retrieve the organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data, and organic light-emitting display manufacturing control model associated with the closest organic light-emitting display manufacturing process historical task from the historical task database according to the closest organic light-emitting display manufacturing process historical task to form a basic data set for optimizing the control model; The optimization algorithms include genetic algorithm and particle swarm optimization algorithm; Take the basic data set of the optimized control model as the input, and apply the genetic algorithm to iteratively optimize the organic light-emitting display manufacturing control model to obtain the optimal parameter combination.

[0011] Furthermore, in the organic light-emitting display manufacturing process optimization method of the present invention, the step S105 includes: Obtain the real-time organic light-emitting display manufacturing process task including task objectives and constraints, retrieve the organic light-emitting display manufacturing process historical task similar to the real-time organic light-emitting display manufacturing process task from the organic light-emitting display manufacturing historical data, and extract the corresponding organic light-emitting display manufacturing process parameter data, environmental condition data, and material composition data; Initialize the particle swarm, set the size of the particle swarm, that is, the number of particles, and randomly initialize the position and velocity of each particle; Define the fitness function to evaluate the quality of each particle, calculate the fitness value of each particle, and update the individual best position and global best position of each particle according to the fitness value; Update the velocity and position of each particle using the update formula of the particle swarm optimization algorithm, and repeat the update process until the predetermined number of iterations is reached or the stopping condition is satisfied. After the optimization process ends, the global best position represents the optimized control model parameters. Extract the parameter values corresponding to the global best position as the parameters of the organic light-emitting display manufacturing control model for real-time optimization.

[0012] Advantages of the present invention: By monitoring and optimizing the data generated in the organic light-emitting display manufacturing process in real time, the present invention enables the process to be adaptively adjusted, thereby improving production efficiency and product quality. Using the digital twin model to simulate and optimize the process in a virtual environment avoids repeated trials and adjustments in actual production, significantly reducing the trial-and-error cost and time.

[0013] By optimizing the control model, the present invention improves the stability of the organic light-emitting display manufacturing process parameters within a reasonable range, thereby reducing the defective product rate in the production process of organic light-emitting display materials.

[0014] The present invention integrates multi-source data such as historical tasks, process parameters, environmental conditions, and material compositions in the organic light-emitting display manufacturing process, and realizes the association and integration of data by establishing a corresponding relationship table, improving the utilization rate of data. By introducing the digital twin model and optimization algorithm, the intelligent and automatic control of the process is realized, reducing the dependence on manual experience and improving the intelligent level of production.

[0015] The present invention can quickly match historical tasks and optimize the control model according to different real-time task requirements, support customized production, and meet the diverse needs of the market. By precisely controlling process parameters and environmental conditions, the present invention helps to optimize resource allocation, reduce material waste and energy consumption, and lower production costs. By improving production efficiency, product quality, and customized production capabilities, the present invention helps enterprises enhance their market competitiveness and win more market shares.

[0016] In summary, by providing an organic light-emitting display manufacturing process optimization method, the present invention significantly improves the adaptability, stability, and consistency of the process, reduces the trial-and-error cost and time, and improves the utilization rate of organic light-emitting display manufacturing process data and the intelligent level. Brief Description of the Drawings

[0017] To more clearly illustrate the technical solutions of the present invention, the following will briefly introduce the drawings required for use in the embodiments. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on the drawings.

[0018] Figure 1Schematic flowchart of the method for optimizing the organic light-emitting display manufacturing process provided by an embodiment of the present invention. Detailed implementation manners

[0019] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention. The following describes the technical solutions provided by the embodiments of the present invention with reference to the drawings. To better understand the objectives of the present invention, the present invention is further described below.

[0020] The present invention provides a method for optimizing the organic light-emitting display manufacturing process, including: Step S101, obtaining the historical tasks of the organic light-emitting display manufacturing process, the parameter data of the organic light-emitting display manufacturing process, the environmental condition data of the organic light-emitting display manufacturing process, the material composition data of the organic light-emitting display manufacturing process, the organic light-emitting display manufacturing control model, and the historical data of the organic light-emitting display manufacturing; Historical tasks of the organic light-emitting display manufacturing process: Extract all past organic light-emitting display manufacturing tasks from the historical database, including task types (such as manufacturing different models of display screens), task scales (such as production quantities), and task times (start and end times).

[0021] Parameter data of the organic light-emitting display manufacturing process: Collect the key parameter data during each process execution, such as temperature, pressure, time, current, and voltage.

[0022] Environmental condition data of the organic light-emitting display manufacturing process: Record the environmental conditions during each process execution, including environmental humidity, temperature, and cleanliness.

[0023] Material composition data of the organic light-emitting display manufacturing process: Obtain information on the substrate material, light-emitting layer material, and electrode material used in each process, including the composition, supplier, batch number, etc. of the materials to analyze the impact of the materials on the process.

[0024] Organic light-emitting display manufacturing control model: Collect the currently used control model and its parameter settings, which are used to guide and control the entire process.

[0025] Historical data of the organic light-emitting display manufacturing: Including but not limited to process execution records (such as equipment operating status, operation logs), product test results (such as yield rate, performance indicators), and fault records (fault types, occurrence times, solutions).

[0026] Clean the collected data to remove duplicates, errors, or outliers, ensuring data accuracy and consistency. Standardize data from different sources and formats, such as unifying units, converting data formats, etc., to facilitate subsequent data analysis and model applications.

[0027] Associate and integrate historical tasks, process parameters, environmental conditions, material compositions, control models, and historical data based on the task ID or other unique identifier to form a complete dataset.

[0028] Classify and store data according to data types and uses. For example, store process parameter data in a parameter library and historical task data in a task database for subsequent querying and calling.

[0029] Step S102: Establish corresponding relationships for the organic light-emitting display manufacturing process historical tasks, organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data, and organic light-emitting display manufacturing control model based on the organic light-emitting display manufacturing historical data to obtain the organic light-emitting display manufacturing process data group; Based on the task ID or unique identifier in the organic light-emitting display manufacturing historical data, associate each historical task with the corresponding process parameter data, environmental condition data, material composition data, and control model. This association ensures that in subsequent analysis, the specific data and models used for each task can be accurately traced.

[0030] When associating data, it is also necessary to establish the association relationships between parameters. For example, specific process parameters (such as temperature and time) are associated with specific environmental conditions (such as humidity and temperature) because these factors jointly affect the deposition effect of the organic layer. By identifying the association relationships, the interactions and influences in the process can be understood more deeply.

[0031] Establish a unique identifier (such as UUID) for each organic light-emitting display manufacturing process historical task, process parameter data, environmental condition data, material composition data, and control model. These identifiers are used to uniquely identify each data item in the database and ensure the accuracy of data association.

[0032] Create a correspondence table to record the association relationships between each task and the corresponding dataset. This table should contain the following fields: task ID, process parameter ID, environmental condition ID, material composition ID, control model ID, and any necessary association metadata (such as association time, associated person, etc.).

[0033] According to the data association strategy, each task is recorded in the corresponding relationship table with the corresponding dataset. This includes associating the task ID with the relevant process parameter IDs, environmental condition IDs, material composition IDs, and control model IDs, and filling in the corresponding fields.

[0034] Data group definition: The organic light-emitting display manufacturing process data group refers to the set that contains a specific task and all its related data (process parameters, environmental conditions, material composition, control model). Each data group is independent and complete, and can comprehensively reflect the process characteristics and requirements of the task.

[0035] Data group generation: According to the corresponding relationship table, the organic light-emitting display manufacturing process data group for each task is automatically generated. This includes retrieving all data items associated with the task ID from the database and combining them into a data group. Each data group should contain task information (such as task type, task scale, task time) and the corresponding datasets for each task (such as process parameter dataset, environmental condition dataset, etc.).

[0036] Step S103, substitute the organic light-emitting display manufacturing process data group into the pre-constructed digital twin model in sequence, obtain the digital twin model image data and operation parameter data corresponding to each organic light-emitting display manufacturing process data in the organic light-emitting display manufacturing process data group, and summarize the digital twin model image data and operation parameter data to obtain the digital twin model operation parameter data group; Model design: First, according to the characteristics and requirements of the organic light-emitting display manufacturing process, design the structure and function of the digital twin model. This model should be able to simulate all aspects of the organic light-emitting display manufacturing process, including material deposition, thin film growth, equipment operation, etc.

[0037] Parameter configuration: Configure the parameters of the digital twin model according to the pre-collected data such as process parameters, environmental conditions, and material composition. These parameters will be used to simulate various conditions and variables in the actual process.

[0038] Model verification: After the model is constructed, use historical data for verification to ensure that the model can accurately simulate the actual process and produce reasonable output results.

[0039] Data group preparation: Use the organic light-emitting display manufacturing process data group formed in step S102 as the input and prepare to substitute it into the digital twin model for simulation.

[0040] Simulation run: Substitute each data group into the digital twin model in sequence and start the model for simulation run. During the simulation, the model will simulate the corresponding process and results according to the information such as process parameters, environmental conditions, and material composition in the input data group.

[0041] Image data and operating parameter generation: During the simulation process, the digital twin model will generate simulated image data and operating parameter data in real time. Image data is used to visualize the simulated process to help understand and analyze process characteristics; operating parameter data includes various key indicators (such as temperature, pressure, deposition rate, etc.) to evaluate the rationality and accuracy of simulation results.

[0042] Collect the image data and operating parameter data generated after each data group is substituted into the model to ensure that no key information is missed. Summarize all the collected image data and operating parameter data to form a digital twin model operating parameter data group. This data group should contain the simulation results and related parameter data corresponding to each data group. Sort the summarized data, including deduplication, sorting, formatting and other operations, to facilitate subsequent data analysis and processing. At the same time, establish data indexes and associations to facilitate rapid retrieval and call of related data.

[0043] Step S104, establishing a correspondence between the digital twin model operation parameter data group and the organic light-emitting display manufacturing process parameter data according to the organic light-emitting display manufacturing process historical tasks, obtaining the organic light-emitting display manufacturing process parameter data corresponding to the digital twin model operation parameter data group, and comparing the digital twin model operation parameter data in the digital twin model operation parameter data group with the corresponding organic light-emitting display manufacturing process parameter data in turn to obtain the organic light-emitting display manufacturing parameter error comparison result; Task and parameter association: First, according to the corresponding relationship table established in step S102, each item in the digital twin model operation parameter data group is associated with the organic light-emitting display manufacturing process history task and the corresponding process parameter data. This improves the ability to accurately correspond the simulation results to the actual process parameters in subsequent comparative analysis.

[0044] Index and identifier application: Using the identifiers and indexes established for data and tasks in step S102, the digital twin model operation parameter data set and the actual process parameter data are quickly located and matched. This improves the efficiency and accuracy of data processing.

[0045] Parameter matching: For each parameter in the digital twin model operation parameter data group, find its corresponding actual process parameter data based on the established correspondence.

[0046] Item-by-item comparison: The operating parameter data obtained by the digital twin model simulation is compared with the actual process parameter data item by item. This includes the comparison of key process parameters such as temperature, pressure, time, current, and voltage.

[0047] Error calculation: Calculate the error values for each comparison parameter. The error values can be calculated in various ways, such as absolute error, relative error, etc., depending on the requirements and purposes of the analysis. Record the calculated error values to form a preliminary error comparison result.

[0048] Error summary: Summarize the error values of all comparison parameters to form an error comparison result for organic light-emitting display manufacturing parameters. This includes the calculation and recording of indicators such as total error, average error, maximum error, etc.

[0049] Error analysis: Conduct an in-depth analysis of the error summary result to identify the main sources and influencing factors of the errors. This includes multiple aspects such as model accuracy, data accuracy, environmental interference, etc.

[0050] Optimization suggestions: Based on the error analysis results, put forward targeted optimization suggestions. For example, if the error mainly stems from insufficient model accuracy, consider further optimizing and adjusting the digital twin model; if the error is due to inaccurate data, strengthen the quality control of data collection and processing.

[0051] In step S105, obtain the real-time organic light-emitting display manufacturing process task, match the real-time organic light-emitting display manufacturing process task with the historical organic light-emitting display manufacturing process tasks, obtain the historical organic light-emitting display manufacturing process tasks approximate to the real-time organic light-emitting display manufacturing process task, and retrieve the corresponding organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data, and organic light-emitting display manufacturing control model of the approximate historical organic light-emitting display manufacturing process task. Use an optimization algorithm to optimize the organic light-emitting display manufacturing control model based on the real-time organic light-emitting display manufacturing process task and the corresponding organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, and organic light-emitting display manufacturing process material composition data of the historical organic light-emitting display manufacturing process tasks approximate to the real-time organic light-emitting display manufacturing process task, to obtain a real-time optimized organic light-emitting display manufacturing control model, and deploy the real-time optimized organic light-emitting display manufacturing control model as the organic light-emitting display manufacturing control model for real-time use in the organic light-emitting display manufacturing process.

[0052] Through the production management system or the real-time data acquisition system, obtain the real-time organic light-emitting display manufacturing process task that is currently being executed or about to be executed. The real-time organic light-emitting display manufacturing process task contains key information such as task type, scale, requirements, etc.

[0053] Task Matching Strategy: Design and implement a task matching algorithm to match real-time tasks with historical tasks of organic light-emitting display manufacturing processes. The matching basis includes multiple dimensions such as task type, scale, process requirements, etc. The algorithm should be able to quickly and accurately find the historical task most similar to the real-time task.

[0054] Approximate Task Determination: Based on the results of the task matching algorithm, determine the historical task of organic light-emitting display manufacturing process that is most similar to the real-time task. This includes identifying key information such as the task ID, process parameters, environmental conditions, material composition, etc. of the similar task.

[0055] Data Retrieval: Retrieve the organic light-emitting display manufacturing process parameter data, environmental condition data, material composition data, and control model corresponding to the approximate task from the database. These data will serve as the basis for optimizing the control model.

[0056] Data Preprocessing: Preprocess the retrieved data, including data cleaning, format conversion, standardization, etc., to improve the accuracy and consistency of the data. At the same time, make appropriate adjustments or supplements to some data according to the requirements of the real-time task.

[0057] Optimization Algorithm Selection: According to the nature and requirements of the problem, select a suitable optimization algorithm, such as genetic algorithm, particle swarm algorithm, gradient descent method, etc. The algorithm should be able to efficiently process large-scale data and find the optimal or approximate optimal solution.

[0058] Optimization Goal Setting: Clearly define the goals for optimizing the control model, such as improving the yield rate, reducing production costs, shortening the production cycle, etc. The goals should be specific, quantifiable, and consistent with the expectations of management.

[0059] Optimization Process Implementation: Use the selected optimization algorithm to optimize the organic light-emitting display manufacturing control model based on the requirements of the real-time task and the data of the approximate task. The optimization process should include multiple steps such as parameter adjustment, model verification, result evaluation, etc.

[0060] Optimization Result Determination: Based on the output of the optimization algorithm, determine the real-time optimized organic light-emitting display manufacturing control model. The real-time optimized organic light-emitting display manufacturing control model should be able to better adapt to the requirements of the real-time task and improve production efficiency and product quality.

[0061] Before deploying the optimized model to the production line, conduct sufficient tests to ensure the stability and reliability of the model. The tests include multiple links such as simulation tests and actual production tests.

[0062] Deploy the real-time optimized organic light-emitting display manufacturing control model that has passed the test to the production line as the control model for real-time use in the organic light-emitting display manufacturing process. This includes integrating the model into the production control system, setting corresponding parameters and thresholds, etc.

[0063] During the model application process, continuously monitor the performance and effects of the model, and make necessary adjustments and optimizations according to the actual situation, including collecting production data, analyzing the model performance, adjusting model parameters, etc., to ensure that the model always remains in the best state.

[0064] Specifically, for the organic light-emitting display manufacturing process optimization method described in the present invention, step S101 includes: The historical tasks of the organic light-emitting display manufacturing process include task type, task scale, and task time; The parameter data of the organic light-emitting display manufacturing process includes temperature, pressure, time, current, and voltage; The environmental condition data of the organic light-emitting display manufacturing process includes environmental humidity, temperature, and cleanliness; The material composition data of the organic light-emitting display manufacturing process includes substrate material, light-emitting layer material, and electrode material; The organic light-emitting display manufacturing control model includes a model for controlling the organic light-emitting display manufacturing process; The historical data of the organic light-emitting display manufacturing includes but is not limited to process execution records, product test results, and fault records.

[0065] Task type: Classify different types of organic light-emitting display manufacturing process tasks, such as thin film deposition, lithography, etching, encapsulation, etc. Each task type corresponds to specific process steps and parameter requirements.

[0066] Task scale: Define the scale of the task according to production requirements, such as small batch trial production, large-scale production, etc. Different scales will affect the setting of process parameters and optimization strategies.

[0067] Task time: Record the execution time of each task, including start time, end time, and duration, for analyzing process efficiency and identifying bottleneck links.

[0068] The parameter data of the organic light-emitting display manufacturing process; Temperature: Accurately record the temperature parameters during the process, including reaction chamber temperature, substrate temperature, etc. Temperature has an important impact on processes such as material deposition and chemical reactions.

[0069] Pressure: Record the pressure value in the reaction chamber or production environment. Changes in pressure will affect the deposition rate and uniformity of materials.

[0070] Time: Record the execution time of each process step and the total time of the entire process flow for optimizing the production cycle.

[0071] Current: In process steps that require current control, record the magnitude and variation of the current, such as the current density during electroplating.

[0072] Voltage: Record the voltage value applied during the process. The stability and accuracy of the voltage have a direct impact on the process results.

[0073] Data on environmental conditions for organic light-emitting display manufacturing process; Environmental humidity: Monitor and record the humidity level of the production environment. Excessive or insufficient humidity affects the properties of materials and process results.

[0074] Temperature: In addition to the temperature during the process, also record the overall temperature of the production environment to ensure that the environmental temperature is within an appropriate range.

[0075] Cleanliness: Evaluate and record the cleanliness of the production environment, including the number of dust particles and microbial content in the air. Cleanliness is crucial for preventing product contamination.

[0076] Data on material compositions for organic light-emitting display manufacturing process; Substrate material: Clearly record the type, specifications, and properties of the substrate material used, such as glass, plastic, metal, etc. The choice of substrate material affects subsequent processes and product performance.

[0077] Light-emitting layer material: Record the material composition, ratio, and characteristics of the light-emitting layer. The light-emitting layer is the core part of the organic light-emitting display, and the choice and ratio of its materials directly affect the display effect.

[0078] Electrode material: Record the type, thickness, and electrical conductivity of the electrode material. The electrode material has an important impact on current conduction and luminous efficiency.

[0079] Control model for organic light-emitting display manufacturing; Model description: Clearly define the structure, algorithm, and input / output parameters of the control model. The control model should be able to adjust process parameters based on real-time data to ensure the stability and consistency of the process.

[0080] Functional role: Explain the specific role of the control model in the organic light-emitting display manufacturing process, such as automatically adjusting parameters like temperature and pressure, preventing faults, and improving production efficiency.

[0081] Historical data for organic light-emitting display manufacturing; Process execution record: Record the process data of each process execution, including parameter settings, environmental conditions, material usage, etc.

[0082] Product inspection results: Collect and record the quality inspection data of the product, such as brightness, chromaticity, uniformity, lifespan, etc., for evaluating the process effect and product performance.

[0083] Fault record: Record the types, causes, and handling measures of faults occurring during the process, providing experience for subsequent fault prevention and process optimization.

[0084] Specifically, for the method for optimizing the organic light-emitting display manufacturing process described in the present invention, step S102 includes: Associate each historical task of the organic light-emitting display manufacturing process with the corresponding organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data, and organic light-emitting display manufacturing control model; Establish identifiers for each historical task of the organic light-emitting display manufacturing process and the organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data, and organic light-emitting display manufacturing control model. Form an organic light-emitting display manufacturing process data group with the associated data. The organic light-emitting display manufacturing process data group includes task information and the data set corresponding to each task. Establish a corresponding relationship table, and record the association relationship between each task and the corresponding data set, as well as the association relationship between the parameters within the data set in the corresponding relationship table.

[0085] Task-data association: For each historical task of the organic light-emitting display manufacturing process, associate it with the corresponding process parameter data (such as temperature, pressure, etc.), environmental condition data (such as humidity, cleanliness, etc.), material composition data (such as substrate material, light-emitting layer material, etc.), and control model. This association can be achieved through an association table or pointer in the database to ensure that each task can quickly find its corresponding data set.

[0086] Internal data association: Within the data set, associations between parameters also need to be established. For example, there is a direct relationship between the temperature in the process parameters and the thermal stability of a certain material in the material composition, and this relationship needs to be clearly recorded during data association.

[0087] Task identifier: Assign a unique identifier, such as a task ID, to each historical task of the organic light-emitting display manufacturing process for quickly locating and referring to this task in subsequent data processing.

[0088] Data identifier: For each data set corresponding to a task (including process parameter data, environmental condition data, material composition data, etc.), also establish identifiers respectively, such as parameter ID, environment ID, material ID, etc., to ensure the uniqueness and traceability of the data.

[0089] Model Identifier: Assign a unique identifier, such as model ID, to each control model for easy management during model updates or optimizations.

[0090] Task Information Sorting: Sort the basic information of each task, including task type, scale, time, etc., to form a task information set.

[0091] Dataset Integration: Integrate the process parameter data, environmental condition data, material composition data, and control model corresponding to each task into a complete dataset.

[0092] Data Group Construction: Combine the task information set with the corresponding dataset to form an organic light-emitting display manufacturing process data group. Each data group contains all relevant information and data for a task.

[0093] Table Structure Design: Design the structure of the correspondence table, including task identifiers, data identifiers, identifiers for each parameter within the dataset, and their association relationships.

[0094] Association Relationship Recording: Record the association relationships between each task and the corresponding dataset, as well as the association relationships between the parameters within the dataset in the correspondence table. This can be achieved by establishing indexes, using association fields, or creating association tables, etc.

[0095] Table Maintenance and Management: Establish a maintenance and management mechanism for the correspondence table to ensure data accuracy and consistency. As new tasks are added or old tasks are updated, the correspondence table needs to be updated and maintained accordingly.

[0096] Specifically, for the organic light-emitting display manufacturing process optimization method described in the present invention, step S103 includes: Substitute each data group in the organic light-emitting display manufacturing process data group into the digital twin model in sequence, start the digital twin model, and run it according to each data group input in the organic light-emitting display manufacturing process data group. Input the simulation results corresponding to each data group in the organic light-emitting display manufacturing process data group. The simulation results corresponding to each data group in the organic light-emitting display manufacturing process data group include image data and operation parameter data of the organic light-emitting display manufacturing process. During the operation of the digital twin model, generate digital twin model image data and operation parameter data in real time.

[0097] Data Group Selection: Select a data group as the input for the current simulation from the established organic light-emitting display manufacturing process data group in a predetermined order or according to specific screening conditions.

[0098] Model Configuration: Configure the parameters and settings of the digital twin model according to the characteristics of the selected data group and simulation requirements to ensure that the model can accurately reflect the actual process.

[0099] Data import: Import task information, process parameter data, environmental condition data, material composition data, control models, and other data in the selected data group into the digital twin model.

[0100] Model startup: Start the digital twin model to begin the simulation process.

[0101] Image data simulation: The digital twin model simulates the image data of the organic light-emitting display manufacturing process based on the input data group. This includes simulating the visual effects at various stages of the process, such as the uniformity of thin-film deposition and the clarity of lithography patterns.

[0102] Operating parameter data simulation: Meanwhile, the model also simulates the operating parameter data during the process, such as the changes in temperature, pressure, current, voltage, etc., and the impact of these parameters on the process results.

[0103] Real-time data generation: During the simulation process, the digital twin model generates and outputs the simulated image data and operating parameter data in real time. These data can be used for subsequent analysis, verification, and optimization.

[0104] Data recording: For the image data and operating parameter data simulated and generated for each data group, recording is required. The recorded content should include simulation time, simulation conditions, simulation results, etc.

[0105] Data storage: Store the recorded data in a specified database or file system for subsequent data processing and analysis. When storing data, data security, integrity, and traceability should be considered.

[0106] Result display: Display the simulated image data and operating parameter data in an intuitive way, such as through charts, animations, etc., for easy user understanding and analysis.

[0107] Result evaluation: Evaluate the simulation results to judge the accuracy and reliability of the simulation. If there is a large deviation between the simulation results and the expectations, the model parameters or data input need to be adjusted and the simulation needs to be performed again.

[0108] Result application: Apply the evaluated simulation results to the optimization of the actual organic light-emitting display manufacturing process. For example, process parameters can be adjusted, material formulations can be improved, or control models can be optimized based on the simulation results.

[0109] Specifically, for the method for optimizing the organic light-emitting display manufacturing process described in the present invention, step S104 includes: Establish an index for each set of digital twin model operating parameter data, and match each parameter in the digital twin model operating parameter data group with the corresponding organic light-emitting display manufacturing process parameter data according to the index; Compare the differences between the operating parameters of the digital twin model and the actual organic light-emitting display manufacturing process parameters one by one, and calculate the error values of each group of comparison parameters; Summarize the error values of the comparison parameters to form the error comparison result of the organic light-emitting display manufacturing parameters.

[0110] Index establishment: Establish a unique index for each group of digital twin model operating parameter data. This index should be able to clearly identify the source, simulation conditions, and corresponding organic light-emitting display manufacturing process stage of each group of parameter data.

[0111] Parameter matching: According to the established index, match each parameter in the digital twin model operating parameter data group with the corresponding actual organic light-emitting display manufacturing process parameter data. The matching process should ensure the consistency of both in terms of parameter type, unit, measurement conditions, etc.

[0112] Parameter comparison: Compare the differences between the operating parameters of the digital twin model and the actual organic light-emitting display manufacturing process parameters one by one. The comparison process should record the comparison results of each parameter, including the difference value, difference direction (higher or lower), etc.

[0113] Error calculation: For each compared parameter, calculate its error value. The error value can be calculated by methods such as absolute error, relative error, or mean square error. The specific method to be selected should be determined according to the characteristics of the parameter and the optimization goal.

[0114] Error analysis: Analyze the calculated error values to judge the sources and reasons of the errors. For example, the errors are caused by the inaccuracy of the model, fluctuations in the actual process, or data measurement errors, etc.

[0115] Error summary: Summarize the error values of all compared parameters to form a comprehensive error comparison result of the organic light-emitting display manufacturing parameters. The summary process should ensure that the error value of each parameter is accurately recorded and is convenient for subsequent analysis and processing.

[0116] Result display: Display the error comparison result in an intuitive way, such as through charts, reports, etc. The display content should include the error value, error distribution, main error sources, etc. of each parameter, so that users can clearly understand the differences between the digital twin model and the actual process.

[0117] Result application: According to the error comparison result, analyze the accuracy and reliability of the digital twin model, as well as the problems existing in the actual process. According to the analysis results, the digital twin model can be corrected, or the actual process can be adjusted and optimized to reduce errors and improve process quality.

[0118] Specifically, for the method for optimizing the organic light-emitting display manufacturing process according to the present invention, step S105 includes: The real-time organic light-emitting display manufacturing process tasks include task types, specification requirements, and production targets; Match the real-time organic light-emitting display manufacturing process tasks with the organic light-emitting display manufacturing process historical task database, Use a similarity algorithm to match the real-time organic light-emitting display manufacturing process tasks with the closest organic light-emitting display manufacturing process historical tasks; Retrieve from the historical task database the organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data, and organic light-emitting display manufacturing control model associated with the closest organic light-emitting display manufacturing process historical task, and form a basic data set for optimizing the control model; The optimization algorithms include genetic algorithms and particle swarm optimization algorithms; Take the basic data set of the optimized control model as the input, and apply the genetic algorithm to iteratively optimize the organic light-emitting display manufacturing control model to obtain the optimal parameter combination.

[0119] Real-time task description: Define the task type (such as new product R & D, mass production, etc.), specification requirements (such as resolution, brightness, color saturation, etc.), and production target (such as daily output, monthly output, etc.) of the real-time organic light-emitting display manufacturing process tasks.

[0120] Historical task database preparation: Ensure that the organic light-emitting display manufacturing process historical task database is complete and up-to-date, containing task information, process parameters, environmental conditions, material compositions, and control model data of historical tasks.

[0121] Similarity algorithm selection: According to the characteristics of the real-time task, select a suitable similarity algorithm (such as cosine similarity, Euclidean distance, etc.) to evaluate the similarity between the real-time task and the historical task.

[0122] Task matching: Apply the similarity algorithm to compare the real-time task with the tasks in the historical task database one by one, and find the historical task closest to the real-time task. The matching process should consider the similarity in multiple dimensions such as task type, specification requirements, and production target.

[0123] Basic data set formation: According to the matching result, retrieve from the historical task database the organic light-emitting display manufacturing process parameter data, environmental condition data, material composition data, and control model associated with the closest historical task.

[0124] Data verification: Verify the retrieved data to ensure its accuracy, integrity, and timeliness. For outdated or inaccurate data, it should be updated or corrected.

[0125] Basic dataset construction: Integrate the verified data into a basic dataset, which serves as the data basis for the optimization control model.

[0126] Introduction to optimization algorithms: Genetic algorithm and particle swarm optimization algorithm are two commonly used optimization algorithms. The genetic algorithm finds the optimal solution by simulating the biological evolution process, while the particle swarm optimization algorithm finds the optimal solution by simulating the movement and cooperation of a particle swarm.

[0127] Algorithm selection: Select a suitable optimization algorithm according to the complexity of the problem and the optimization goal. For complex multi-parameter optimization problems, the genetic algorithm can be considered; for problems that require fast convergence and have fewer parameters, the particle swarm optimization algorithm can be considered.

[0128] Optimization process: Use the basic dataset as input and apply the selected optimization algorithm to iteratively optimize the organic light-emitting display production control model. The optimization process should include steps such as parameter initialization, fitness evaluation, selection, crossover, mutation (for the genetic algorithm), or position update, velocity update (for the particle swarm optimization algorithm).

[0129] Determination of the optimal parameter combination: Through iterative optimization, find the parameter combination that makes the performance of the control model optimal. The optimal parameter combination should meet the specification requirements and production goals of real-time tasks and be feasible and stable in practical applications.

[0130] Result verification: Verify the optimized control model to ensure its performance and stability in practical applications. The verification process includes methods such as simulation and actual testing.

[0131] Result application: Apply the optimized control model to the actual organic light-emitting display production process to improve the stability and efficiency of the process, and reduce production costs and risks.

[0132] Specifically, for the method for optimizing the organic light-emitting display production process described in the present invention, step S105 includes: Obtain the real-time organic light-emitting display production process task including the task objective and constraints, retrieve the organic light-emitting display production historical tasks similar to the real-time organic light-emitting display production process task from the organic light-emitting display production historical data, and extract the corresponding parameter data, environmental condition data, and material composition data of the organic light-emitting display production process; Initialize the particle swarm, set the size of the particle swarm, that is, the number of particles, and randomly initialize the position and velocity of each particle; Define a fitness function to evaluate the quality of each particle, calculate the fitness value of each particle, and update the personal best position and global best position of each particle according to the fitness value; Use the update formula of the particle swarm optimization algorithm to update the velocity and position of each particle, and repeat the update process until the predetermined number of iterations is reached or the stop condition is satisfied. After the optimization process ends, the global best position represents the optimized control model parameters, and the parameter values corresponding to the global best position are extracted as the parameters of the organic light-emitting display manufacturing control model for real-time optimization.

[0133] The task objectives and constraints are clear: First, clarify the objectives (such as improving production efficiency, reducing energy consumption, etc.) and constraints (such as material costs, equipment limitations, etc.) of the real-time organic light-emitting display manufacturing process.

[0134] Historical data retrieval: From the historical database of organic light-emitting display manufacturing, use a specific retrieval algorithm or similarity evaluation method to retrieve historical tasks that are similar to the real-time task in terms of objectives, constraints, etc.

[0135] Data extraction: For the retrieved similar historical tasks, extract the corresponding organic light-emitting display manufacturing process parameter data (such as temperature, pressure, time, etc.), environmental condition data (such as humidity, cleanliness, etc.), and material composition data (such as the type and concentration of light-emitting materials, etc.).

[0136] Particle swarm initialization; Setting the size of the particle swarm: According to the complexity of the problem and computing resources, reasonably set the size of the particle swarm, that is, the number of particles. Too many particles will increase the computational burden, while too few will affect the optimization effect.

[0137] Particle initialization: Randomly initialize the position and velocity of each particle. The position can be represented as a solution to the control model parameters, and the velocity is used to update the position in subsequent iterations.

[0138] Fitness function design: Design a fitness function according to the objectives and constraints of the real-time task. This function should be able to evaluate the quality of each particle (i.e., each solution).

[0139] Fitness calculation: For each particle, calculate the fitness value according to its position (i.e., the control model parameters). The higher the fitness value, the closer the solution corresponding to the particle is to the optimal solution.

[0140] Best position update: Update the personal best position (i.e., the optimal solution found by the particle in its history) and global best position (i.e., the optimal solution found among all particles) of each particle according to the fitness value.

[0141] Particle swarm optimization iteration; Speed ​​update: Use the update formula of the particle swarm optimization algorithm to update the speed of each particle according to the individual best position, the global best position and the current speed. Speed ​​update should consider three factors: inertia, self-cognition and social cognition.

[0142] Position update: Update the position of each particle based on the updated velocity. Position update should ensure that the new position is within a reasonable parameter range.

[0143] Iteration condition judgment: judge whether the predetermined number of iterations is reached or the stopping condition is met (such as fitness value convergence, reaching the maximum calculation time, etc.). If the condition is met, the iteration ends; otherwise, the iteration continues.

[0144] Global best position extraction: After the optimization process is completed, the parameter values ​​corresponding to the global best position are extracted. These parameter values ​​are the optimized control model parameters.

[0145] Parameter verification and application: Verify the optimized parameters to ensure their feasibility and effectiveness in practical applications. After verification, apply the optimized parameters to the real-time organic light-emitting display manufacturing process to achieve process optimization.

[0146] The technical solution of the present invention solves the problem that the prior art cannot detect and optimize the data generated by the organic light-emitting display manufacturing process, resulting in the inability to adaptively adjust the organic light-emitting display manufacturing process through the following steps: Obtain historical tasks, process parameter data, environmental condition data, material composition data, control model and historical data of the organic light-emitting display manufacturing process. Associate according to historical tasks, and establish a corresponding relationship table to record the association between each task and the corresponding data set, as well as the association between the parameters within the data set.

[0147] Substitute the sorted data groups into the pre-built digital twin model in turn. The digital twin model simulates and runs according to the input data to generate image data and operation parameter data. Summarize the data to obtain the digital twin model operation parameter data group.

[0148] Compare the operation parameter data group of the digital twin model with the actual organic light-emitting display manufacturing process parameter data. Calculate the error values of each group of comparison parameters and summarize them to form an error comparison result. Obtain the real-time organic light-emitting display manufacturing process tasks and match them with historical tasks to find the closest historical task. According to the closest historical task, retrieve relevant process parameter data, environmental condition data, material composition data, and control models to form a basic data set for optimizing the control model. Use optimization algorithms such as genetic algorithms or particle swarm optimization algorithms to iteratively optimize the control model based on the basic data set to obtain the optimal parameter combination. Deploy the optimized control model for real-time use.

[0149] Through the above steps, the technical solution of the present invention can achieve comprehensive monitoring and optimization of the data generated in the organic light-emitting display manufacturing process, thereby improving the process's adaptive adjustment ability. The application of the digital twin model enables the simulation and optimization of the process in a virtual environment, reducing the trial-and-error costs and time in actual production. At the same time, by continuously optimizing the control model, the stability and efficiency of the process can be further improved.

Claims

1. A method for optimizing the manufacturing process of an organic light-emitting display, characterized in that: include: Step S101, acquiring organic light emitting display manufacturing process historical tasks, organic light emitting display manufacturing process parameter data, organic light emitting display manufacturing process environmental condition data, organic light emitting display manufacturing process material composition data, organic light emitting display manufacturing control model and organic light emitting display manufacturing history data; Step S102, establishing a corresponding relationship between the organic light emitting display manufacturing process history tasks, the organic light emitting display manufacturing process parameter data, the organic light emitting display manufacturing process environment condition data, the organic light emitting display manufacturing process material composition data, and the organic light emitting display manufacturing control model according to the organic light emitting display manufacturing history data, so as to obtain an organic light emitting display manufacturing process data group; Step S103, sequentially substituting the organic light-emitting display manufacturing process data group into the pre-built digital twin model, obtaining the digital twin model image data and operation parameter data corresponding to each organic light-emitting display manufacturing process data in the organic light-emitting display manufacturing process data group, and aggregating the digital twin model image data and operation parameter data to obtain the digital twin model operation parameter data group; Step S104, establishing a correspondence between the digital twin model operation parameter data group and the organic light-emitting display manufacturing process parameter data according to the organic light-emitting display manufacturing process historical tasks, obtaining the organic light-emitting display manufacturing process parameter data corresponding to the digital twin model operation parameter data group, and comparing the digital twin model operation parameter data in the digital twin model operation parameter data group with the corresponding organic light-emitting display manufacturing process parameter data in turn to obtain the organic light-emitting display manufacturing parameter error comparison result; Step S105, obtaining a real-time organic light-emitting display manufacturing process task, matching the real-time organic light-emitting display manufacturing process task with an organic light-emitting display manufacturing process history task, obtaining an organic light-emitting display manufacturing process history task that is approximate to the real-time organic light-emitting display manufacturing process task, and retrieving organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data, and an organic light-emitting display manufacturing control model corresponding to the approximate organic light-emitting display manufacturing process history task, using an optimization algorithm to optimize the organic light-emitting display manufacturing control model based on the real-time organic light-emitting display manufacturing process task and the organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, and organic light-emitting display manufacturing process material composition data corresponding to the organic light-emitting display manufacturing process history task that is approximate to the real-time organic light-emitting display manufacturing process task, obtaining a real-time optimized organic light-emitting display manufacturing control model, and deploying the real-time optimized organic light-emitting display manufacturing control model as an organic light-emitting display manufacturing control model used in real time by the organic light-emitting display manufacturing process.

2. The method for optimizing the organic light emitting display manufacturing process according to claim 1, wherein: The step S101 includes: The historical tasks of organic light-emitting display manufacturing process include task type, task scale and task time; The organic light-emitting display manufacturing process parameter data includes temperature, pressure, time, current and voltage; The environmental condition data of the organic light-emitting display manufacturing process includes environmental humidity, temperature and cleanliness; The material composition data of the organic light-emitting display manufacturing process includes substrate materials, light-emitting layer materials and electrode materials; The organic light emitting display manufacturing control model includes a model for controlling the organic light emitting display manufacturing process; The organic light-emitting display manufacturing history data includes, but is not limited to, process execution records, product test results, and failure records.

3. The method for optimizing the manufacturing process of an organic light-emitting display according to claim 1, wherein: The step S102 includes: Associating each organic light emitting display manufacturing process history task with corresponding organic light emitting display manufacturing process parameter data, organic light emitting display manufacturing process environmental condition data, organic light emitting display manufacturing process material composition data, and organic light emitting display manufacturing control model; An identifier is established for each organic light-emitting display manufacturing process historical task and organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data, and organic light-emitting display manufacturing control model, and the associated data are formed into an organic light-emitting display manufacturing process data group. The organic light-emitting display manufacturing process data group includes task information and a data set corresponding to each task. A corresponding relationship table is established to record the association relationship between each task and the corresponding data set, as well as the association relationship between the parameters within the data set.

4. The method for optimizing the organic light emitting display manufacturing process according to claim 1, wherein: The step S103 includes: Each data group in the organic light-emitting display manufacturing process data group is substituted into the digital twin model in turn, the digital twin model is started, and it is run according to each data group in the input organic light-emitting display manufacturing process data group, and the simulation results corresponding to each data group in the organic light-emitting display manufacturing process data group are input. The simulation results corresponding to each data group in the organic light-emitting display manufacturing process data group include image data and operating parameter data of the organic light-emitting display manufacturing process. During the operation of the digital twin model, the digital twin model image data and operating parameter data are generated in real time.

5. The method for optimizing the manufacturing process of an organic light-emitting display according to claim 1, wherein: The step S104 includes: Establish an index for each set of digital twin model operation parameter data, and match each parameter in the digital twin model operation parameter data set with the corresponding organic light-emitting display manufacturing process parameter data according to the index; Compare the differences between the operating parameters of the digital twin model and the actual OLED manufacturing process parameter data in turn, and calculate the error value of each set of comparison parameters; The error values ​​of the comparison parameters are summarized to form an organic light-emitting display manufacturing parameter error comparison result.

6. The method for optimizing the manufacturing process of an organic light-emitting display according to claim 1, wherein: The step S105 includes: Real-time organic light-emitting display manufacturing process tasks include task types, specification requirements, and production targets; Match the real-time OLED manufacturing process tasks with the OLED manufacturing process history task database, Use a similarity algorithm to match the real-time organic light-emitting display manufacturing process task with the organic light-emitting display manufacturing process history task that is closest to it; According to the closest organic light-emitting display manufacturing process historical task, retrieve organic light-emitting display manufacturing process parameter data, organic light-emitting display manufacturing process environmental condition data, organic light-emitting display manufacturing process material composition data and organic light-emitting display manufacturing control model associated with the closest organic light-emitting display manufacturing process historical task from the historical task database to form a basic data set for optimizing the control model; Optimization algorithms include genetic algorithm and particle swarm optimization algorithm; The basic data set of the optimization control model is used as input, and the genetic algorithm is used to iteratively optimize the organic light-emitting display production control model to obtain the optimal parameter combination.

7. The method for optimizing the manufacturing process of an organic light-emitting display according to claim 1, wherein: The step S105 includes: Acquire a real-time organic light-emitting display manufacturing process task including a task objective and constraints, retrieve an organic light-emitting display manufacturing history task similar to the real-time organic light-emitting display manufacturing process task from the organic light-emitting display manufacturing history data, and extract parameter data, environmental condition data, and material composition data of the corresponding organic light-emitting display manufacturing process; Initialize the particle swarm, set the size of the particle swarm, that is, the number of particles, and randomly initialize the position and speed of each particle; Define a fitness function to evaluate the quality of each particle, calculate the fitness value of each particle, and update the individual best position and global best position of each particle according to the fitness value; The speed and position of each particle are updated using the update formula of the particle swarm optimization algorithm, and the update process is repeated until a predetermined number of iterations is reached or the stop condition is met. After the optimization process is completed, the global optimal position represents the optimized control model parameters, and the parameter values ​​corresponding to the global optimal position are extracted as the parameters of the real-time optimized organic light-emitting display production control model.

Images