Photovoltaic diode manufacturing parameter optimization method based on twinborn simulation

Abstract

The invention provides a photovoltaic diode manufacturing parameter optimization method based on twin simulation, and relates to the technical field of data processing, and the method comprises the steps: obtaining the diode feature data of a target photovoltaic diode; retrieving in a diode database to obtain a same-family test data set; constructing a diode test model based on a digital twinning technology; performing a simulation test on the manufactured photovoltaic diode sample to generate a simulation test result; judging the plurality of photoelectric conversion efficiencies, and obtaining N unqualified photoelectric conversion efficiencies which do not meet a photoelectric conversion efficiency threshold value; on the basis of the N unqualified photoelectric conversion efficiencies, manufacturing parameter optimization of the target photovoltaic diode is carried out, and an optimal manufacturing parameter combination is obtained; and manufacturing control of the target photovoltaic diode is carried out. The technical problem that the quality of the photovoltaic diode is poor due to the fact that a traditional manufacturing parameter selection method is often based on experience and lacks systematicness and high efficiency is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for optimizing photovoltaic diode manufacturing parameters based on twin simulation. Background Art

[0002] As an important component of clean energy, solar photovoltaic technology has been widely used in the energy field. However, there are still some technical problems in the manufacturing process of photovoltaic diodes. On the one hand, the photoelectric conversion efficiency of photovoltaic diodes is affected by many factors, and traditional manufacturing methods often make it difficult to ensure the quality stability of photovoltaic diodes under different production batches and working conditions; on the other hand, the optimization of manufacturing parameters is crucial to improving the performance of photovoltaic diodes, but traditional experience-based or trial-and-error methods are time-consuming and costly, and may not be able to find the global optimal solution, resulting in difficulties in optimizing manufacturing parameters. Summary of the invention

[0003] This application provides a photovoltaic diode manufacturing parameter optimization method based on twin simulation, aiming to solve the technical problem that traditional manufacturing parameter selection methods are often based on experience, lack systematicity and efficiency, and lead to poor quality of photovoltaic diodes.

[0004] In view of the above problems, the present application provides a photovoltaic diode manufacturing parameter optimization method based on twin simulation.

[0005] The first aspect disclosed in the present application provides a method for optimizing manufacturing parameters of photovoltaic diodes based on twin simulation, the method comprising: obtaining diode characteristic data of a target photovoltaic diode, wherein the diode characteristic data comprises material ratio characteristics and doping concentration characteristics; based on the diode characteristic data, searching in a diode database to obtain a set of test data of the same family, wherein the diode database is constructed based on a photoelectric conversion efficiency test of a diode; based on digital twin technology, constructing a diode test model based on the diode characteristic data and the set of test data of the same family; based on the diode test model, performing simulation tests on manufactured photovoltaic diode samples to generate simulation test results, wherein the simulation test results comprise multiple photoelectric conversion efficiencies under multiple working conditions; judging the multiple photoelectric conversion efficiencies to obtain N unqualified photoelectric conversion efficiencies that do not meet a photoelectric conversion efficiency threshold; based on the N unqualified photoelectric conversion efficiencies, optimizing the manufacturing parameters of the target photovoltaic diode to obtain an optimal manufacturing parameter combination; and based on the optimal manufacturing parameter combination, performing manufacturing control of the target photovoltaic diode.

[0006] The second aspect disclosed in the present application provides a photovoltaic diode manufacturing parameter optimization system based on twin simulation, and the system is used for the above-mentioned photovoltaic diode manufacturing parameter optimization method based on twin simulation, and the system includes: a feature data acquisition module, the feature data acquisition module is used to obtain the diode feature data of the target photovoltaic diode, wherein the diode feature data includes material ratio features and doping concentration features; a feature data retrieval module, the feature data retrieval module is used to search in a diode database based on the diode feature data to obtain a set of same-family test data, wherein the diode database is constructed based on the photoelectric conversion efficiency test of the diode; a test model construction module, the test model construction module is used to construct a test model based on the diode feature data and the same-family test data set based on the digital twin technology. A diode test model is constructed; a simulation test module is used to perform simulation tests on the manufactured photovoltaic diode samples based on the diode test model to generate simulation test results, wherein the simulation test results include multiple photoelectric conversion efficiencies under multiple working conditions; a conversion efficiency judgment module is used to judge the multiple photoelectric conversion efficiencies and obtain N unqualified photoelectric conversion efficiencies that do not meet the photoelectric conversion efficiency threshold; a manufacturing parameter optimization module is used to optimize the manufacturing parameters of the target photovoltaic diode based on the N unqualified photoelectric conversion efficiencies to obtain an optimal manufacturing parameter combination; a manufacturing control module is used to perform manufacturing control of the target photovoltaic diode based on the optimal manufacturing parameter combination.

[0007] According to a third aspect disclosed in the present application, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, any step of the first aspect disclosed in the present application is implemented.

[0008] The fourth aspect disclosed in the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the first aspect disclosed in the present application.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: Through digital twin technology, combined with actual diode characteristic data and the same family test data set, a diode test model is constructed, thereby realizing the intelligent optimization of manufacturing parameters; using the simulation test model, the completed photovoltaic diode samples can be simulated and tested quickly and efficiently, and the photoelectric conversion efficiency data under multiple working conditions can be generated, which effectively improves the test efficiency and avoids the waste of resources; by determining the unqualified photoelectric conversion efficiency and optimizing the manufacturing parameters on this basis, the generation rate of unqualified products can be effectively reduced, thereby reducing the manufacturing cost; by using the optimized manufacturing parameters to control the manufacturing of the target photovoltaic diode, the performance and quality of the photovoltaic diode can be improved, thereby improving the overall quality and performance of the product. In summary, the photovoltaic diode manufacturing parameter optimization method based on twin simulation solves the parameter optimization problem in photovoltaic diode manufacturing through digital twin technology and big data analysis, and improves manufacturing efficiency and product quality.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic flow chart of a photovoltaic diode manufacturing parameter optimization method based on twin simulation provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a photovoltaic diode manufacturing parameter optimization system based on twin simulation provided in an embodiment of the present application; Figure 3 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application.

[0012] Explanation of reference numerals: characteristic data acquisition module 10 , characteristic data retrieval module 20 , test model construction module 30 , simulation test module 40 , conversion efficiency determination module 50 , manufacturing parameter optimization module 60 , manufacturing control module 70 . DETAILED DESCRIPTION

[0013] The embodiment of the present application solves the technical problem that traditional manufacturing parameter selection methods are often based on experience, lack of systematicness and efficiency, and lead to poor quality of photovoltaic diodes by providing a photovoltaic diode manufacturing parameter optimization method based on twin simulation.

[0014] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0015] like Figure 1 As shown, the embodiment of the present application provides a photovoltaic diode manufacturing parameter optimization method based on twin simulation, the method comprising: Acquiring diode characteristic data of a target photovoltaic diode, wherein the diode characteristic data includes material ratio characteristics and doping concentration characteristics; Photovoltaic diodes are devices that convert light energy into electrical energy. Common materials include silicon, cadmium selenide, indium selenide, etc. A small amount of impurity elements, usually phosphorus or boron, are introduced into silicon crystals to change the electrical properties of silicon. This process is called doping, and the impurities introduced are called donors (n-type) or acceptors (p-type). The material proportion characteristics and doping concentration characteristics of the target photovoltaic diode can be obtained by retrieving the manufacturing records of the target photovoltaic diode, or by testing the target photovoltaic diode sample. The testing instruments include X-ray fluorescence spectrometers, etc., to determine which elements it is composed of, the proportion of each element, and the concentration of doping impurities.

[0016] Based on the diode characteristic data, searching in a diode database to obtain a set of test data of the same family, wherein the diode database is constructed based on a photoelectric conversion efficiency test of a diode; Establish a database containing different types of photovoltaic diodes. These diodes can come from different manufacturers and have different material compositions and manufacturing parameters. Test each diode to determine its photoelectric conversion efficiency, such as exposing the diode to a specific light source, measuring its output current and light intensity, and then calculating its conversion efficiency. Use the characteristic data of the target photovoltaic diode as a search condition, that is, based on the material ratio characteristics and doping concentration characteristics of the target photovoltaic diode, search in the diode database, and obtain a set of test data of the same family of diodes with similar characteristics to the target photovoltaic diode from the database according to the search conditions. These test data sets of the same family include the test results of the photoelectric conversion efficiency of the same type of photovoltaic diodes under different working conditions.

[0017] Furthermore, based on the diode characteristic data, searching is performed in a diode database to obtain a set of test data of the same family, including: Based on big data, multiple photoelectric conversion efficiency sets of multiple diode types under multiple working conditions are obtained to construct the diode database; Randomly extracting a first diode type from the diode database, obtaining a first diode feature, and a first photoelectric conversion efficiency set; Performing a similarity analysis on the diode characteristic data and the first diode characteristic to obtain a first characteristic similarity; If the first feature similarity meets a preset similarity threshold, the first photoelectric conversion efficiency set is used as the same family test data set.

[0018] Based on big data, photoelectric conversion efficiency data of multiple diode types are collected. These data can come from different research institutions, manufacturers or laboratories. The data covers different types of diodes and test results under different working conditions, such as light intensity, temperature, etc. The collected data is cleaned, including processing missing data and outliers to ensure the accuracy and consistency of the data. A database is established to store data such as diode type, working conditions and photoelectric conversion efficiency. The cleaned data is imported into the database to establish a data set of the diode database, in which each data entry includes information such as diode type, working conditions, photoelectric conversion efficiency, etc.

[0019] A diode type is randomly selected from a diode database as a first type, and characteristic data, i.e., first diode characteristics, are extracted from the database according to the selected first diode type. A first photoelectric conversion efficiency set corresponding to the selected diode type is obtained, and the efficiency data includes multiple photoelectric conversion efficiency values ​​of the diode under different working conditions.

[0020] The similarity calculation is performed on the selected first diode feature and the diode feature data of the target diode. Various similarity calculation methods, such as Euclidean distance, cosine similarity, etc., can be used to measure the similarity between the two features. After the similarity calculation, the first feature similarity is obtained, which is used to measure the similarity between the target diode and the selected first diode type.

[0021] A similarity threshold is preset to determine whether the first feature similarity meets the requirement. The setting of the similarity threshold can be determined according to specific circumstances and needs, and is usually based on actual experience or data analysis.

[0022] The calculated first feature similarity is judged to determine whether it meets the preset similarity threshold. If the first feature similarity reaches or exceeds the preset similarity threshold, the first photoelectric conversion efficiency set is used as the same family test data set, which means that the selected first diode type has sufficient similarity with the target diode. Therefore, the first photoelectric conversion efficiency set can be used as standard data to lay the foundation for subsequent model construction.

[0023] Based on the digital twin technology, a diode test model is constructed based on the diode characteristic data and the same family test data set; Digital twin is a virtual simulation technology that simulates physical processes in the real world through digital modeling and simulation. This technology can conduct experiments and tests in a virtual environment to predict the behavior of real systems. Using digital twin technology, a diode test model is constructed based on the characteristic data of the target photovoltaic diode and a collection of test data of the same family. This model can be used to predict the performance of photovoltaic diodes under different working conditions, including the prediction of key performance parameters such as photoelectric conversion efficiency, to provide support for manufacturing parameter optimization and manufacturing control.

[0024] Furthermore, based on the digital twin technology, based on the diode characteristic data and the same family test data set, a diode test model is constructed, including: Acquire basic equipment information of multiple main manufacturing equipment of the target photovoltaic diode, wherein the basic equipment information includes equipment serial information and equipment model information; Based on the equipment sequence information and equipment model information and based on digital twin technology, the plurality of main manufacturing equipment are modeled to obtain a diode manufacturing model; Mapping the diode characteristic data to the diode manufacturing model to generate a diode twin model; Based on the diode twin model, a plurality of photoelectric conversion efficiency test channels are constructed, wherein the plurality of photoelectric conversion efficiency test channels correspond to a plurality of working conditions; Based on the same family test data set, the multiple photoelectric conversion efficiency test channels are adjusted, and the adjusted multiple photoelectric conversion efficiency test channels are integrated to construct the diode test model.

[0025] Investigate the main manufacturing equipment in the factory and identify multiple main manufacturing equipment used for photovoltaic diode manufacturing. Identify each manufacturing equipment and record its unique equipment serial number as equipment serial information, which is used to distinguish different equipment for subsequent identification. Record the model information of each manufacturing equipment, including manufacturer, model, specifications, etc. The equipment model information can provide the basic technical parameters and performance characteristics of the equipment.

[0026] Based on the collected equipment information and digital twin technology, each major manufacturing equipment is modeled. The modeling process includes the structure, working principle, control system and other aspects of the manufacturing equipment. The model can be verified using actual operation data, and the model parameters can be adjusted and optimized. After modeling, calibrating and verifying all major manufacturing equipment, the resulting digital twin model set constitutes the diode manufacturing model, which can be used to simulate various parameters in the photovoltaic diode manufacturing process.

[0027] The diode characteristic data is input into the diode manufacturing model, the characteristic data is mapped and converted, and the actual diode characteristic data is coupled with the manufacturing model using digital twin technology to generate a corresponding diode twin model, which can be used to simulate and predict the target photovoltaic diode.

[0028] For the use scenarios of photovoltaic diodes, multiple working conditions involved are determined, such as different light intensity, temperature, voltage and other conditions. These working conditions can be determined according to the actual production situation or the expected use environment. For each working condition, a corresponding photoelectric conversion efficiency test channel is established. Each test channel includes the corresponding working condition parameter settings, simulation process and output results.

[0029] According to the photoelectric conversion efficiency data in the same family test data set, multiple photoelectric conversion efficiency test channels are adjusted. The adjustment includes adjusting the model parameters based on the same family test data set to make the output of the test channel closer to the data in the same family test data set. The multiple adjusted photoelectric conversion efficiency test channels are integrated to obtain a diode test model. This model can be used to predict the photoelectric conversion efficiency of the target diode under different working conditions and provide a reference for manufacturing parameter optimization and manufacturing control.

[0030] Based on the diode test model, a simulation test is performed on the manufactured photovoltaic diode sample to generate a simulation test result, wherein the simulation test result includes multiple photoelectric conversion efficiencies under multiple working conditions; Prepare the finished photovoltaic diode samples, which are manufactured on the production line. Use the constructed diode test model to set the parameters and conditions of the simulation test, including determining the lighting conditions, temperature conditions, circuit connections, etc., to simulate different working conditions. Input the finished photovoltaic diode samples into the diode test model and perform simulation tests to simulate the electrical performance of the samples under different working conditions, including photoelectric conversion efficiency. Based on the results of the simulation test, record multiple photoelectric conversion efficiencies under multiple working conditions. These efficiency values ​​correspond to the performance under different light intensity, temperature and other conditions.

[0031] Determining the plurality of photoelectric conversion efficiencies, and obtaining N unqualified photoelectric conversion efficiencies that do not meet a photoelectric conversion efficiency threshold; Determine the threshold of photoelectric conversion efficiency, which is used to judge which conversion efficiencies belong to the qualified range and which are unqualified. The threshold of photoelectric conversion efficiency is set based on the actual situation and specific needs. Determine the multiple photoelectric conversion efficiencies generated one by one. If a photoelectric conversion efficiency is lower than the set threshold, it is judged as unqualified. All photoelectric conversion efficiencies below the threshold are recorded and counted, and finally N unqualified photoelectric conversion efficiencies are obtained, where N is the number of unqualified photoelectric conversion efficiencies, and N is an integer greater than or equal to 1. When N is equal to 0, it means that no optimization is required.

[0032] Based on the N unqualified photoelectric conversion efficiencies, optimizing the manufacturing parameters of the target photovoltaic diode to obtain an optimal manufacturing parameter combination; Analyze the reasons for the unqualified photoelectric conversion efficiency, which may include inappropriate material ratio, inaccurate doping concentration, etc. Based on the analysis results of the unqualified photoelectric conversion efficiency, design an optimization plan for manufacturing parameters, including adjusting the material ratio and optimizing the doping concentration.

[0033] Using digital twin technology, the designed manufacturing parameter optimization scheme is simulated and tested, that is, the manufacturing process is simulated in a virtual environment and its impact on the photoelectric conversion efficiency is evaluated. Based on the simulation results, the effect of the manufacturing parameter optimization scheme is evaluated. If the simulation results show that the optimized manufacturing parameters can improve the photoelectric conversion efficiency and reduce the non-conformity rate, the optimization scheme is considered to be effective. In the process of parameter optimization, the manufacturing parameters are continuously adjusted and optimized until the optimal manufacturing parameter combination is obtained. The optimal combination is a set of parameters that can show high photoelectric conversion efficiency under various working conditions.

[0034] Based on the optimal combination of manufacturing parameters, manufacturing control of the target photovoltaic diode is performed.

[0035] The determined optimal manufacturing parameter combination is applied to actual production, that is, the manufacturing equipment is adjusted using the optimal manufacturing parameter combination to ensure that various manufacturing parameters can be accurately controlled during the production process. Through this process, the manufacturing process of the target photovoltaic diode can be effectively controlled to ensure that the products produced have stable performance and excellent quality.

[0036] Furthermore, based on the N unqualified photoelectric conversion efficiencies, optimizing the manufacturing parameters of the target photovoltaic diode to obtain an optimal manufacturing parameter combination includes: Based on the N unqualified photoelectric conversion efficiencies, constructing a material ratio optimization space and a doping concentration optimization space; In the material ratio optimization space and the doping concentration optimization space, randomly generating a first material ratio and a first doping concentration as a first manufacturing parameter combination; Using the first manufacturing parameter combination, performing a simulated manufacturing test in the diode test model to generate a first simulated manufacturing test result, wherein the first simulated manufacturing test result includes a simulated photoelectric conversion efficiency set and a simulated photoelectric conversion efficiency fluctuation coefficient; Construct a diode quality assessment function as follows: ; Where FDQ is the diode quality assessment factor, is the ith simulated photoelectric conversion efficiency under the ith working condition, m is the number of working conditions, is the weight of the i-th working condition, To simulate the fluctuation coefficient of photoelectric conversion efficiency, is the first weight, is the second weight, and , The sum of is 1; Performing a quality assessment on the first simulation manufacturing test result according to the diode quality assessment function to obtain a first quality assessment coefficient; Continue to obtain a second manufacturing parameter combination and a second quality assessment coefficient, and perform manufacturing parameter combination comparison and screening based on the second quality assessment coefficient and the first quality assessment coefficient to obtain a current optimal manufacturing parameter combination; Continue iterating and optimizing until the convergence condition is met, and obtain the optimal manufacturing parameter combination.

[0037] For material proportions, determine the variable range of each material. Based on the existing unqualified photoelectric conversion efficiency data, analyze the material composition, determine the possible proportion range of each material, and construct a multidimensional space. Each dimension represents a material, and its value range is the possible proportion range of the material. This forms a material proportion optimization space that contains all possible material proportion combinations.

[0038] For the doping concentration, the variable range is also determined. Based on the existing unqualified photoelectric conversion efficiency data, the doping concentration situation is analyzed, the possible range of doping concentration is determined, and a multi-dimensional space is constructed. Each dimension represents a doping type, and its value range is the possible concentration range of the doping type. In this way, a doping concentration optimization space is formed, which contains all possible doping concentration combinations.

[0039] In the material ratio optimization space and the doping concentration optimization space, a first material ratio and a first doping concentration are randomly generated to obtain a first manufacturing parameter combination, which provides initial parameters for subsequent simulation manufacturing tests.

[0040] The first manufacturing parameter combination is input into the diode test model as the parameter setting for simulated manufacturing, and the diode test model is used to simulate the manufacturing process of the photovoltaic diode, and the manufacturing results are tested. After the simulated manufacturing test is completed, a set of simulated photoelectric conversion efficiencies is obtained, that is, the photoelectric conversion efficiencies simulated under different working conditions; at the same time, the fluctuation coefficient of the simulated photoelectric conversion efficiency is calculated to evaluate the stability of the manufacturing process. The fluctuation coefficient is obtained by calculating the standard deviation of the set of simulated photoelectric conversion efficiencies. The standard deviation is a measure of the average distance of the data from the mean, and the calculation formula is as follows: ; in, is the standard deviation of the data series, represents the i-th data point, represents the mean of the data, and n represents the total number of data points.

[0041] The diode quality evaluation function is constructed as follows: ; Among them, FDQ is the diode quality assessment factor, which is used to indicate the overall quality of the photovoltaic diode; is the ith simulated photoelectric conversion efficiency under the ith working condition, indicating the photoelectric conversion efficiency simulated under different working conditions; is the weight of the i-th working condition, which is used to weight the impact of different working conditions and can be determined according to the importance or priority in practical applications. This evaluation function comprehensively evaluates the quality of photovoltaic diodes by weighted summing the photoelectric conversion efficiency and simulated photoelectric conversion efficiency fluctuation coefficient under different working conditions.

[0042] The simulated photoelectric conversion efficiency set and the simulated photoelectric conversion efficiency fluctuation coefficient of the first simulated manufacturing test result are substituted into the diode quality evaluation function. The first quality evaluation coefficient is calculated according to the weight in the function and the operating condition weight. The first quality evaluation coefficient indicates the quality of the photovoltaic diode represented by the first simulated manufacturing test result. The higher the value, the better the quality.

[0043] Similar to the previous process of obtaining the first manufacturing parameter combination, a second material ratio and a second doping concentration are randomly generated from the material ratio optimization space and the doping concentration optimization space as the second manufacturing parameter combination. The second manufacturing parameter combination is applied to the diode test model to perform a simulated manufacturing test to obtain a second simulated manufacturing test result, including a simulated photoelectric conversion efficiency set and a simulated photoelectric conversion efficiency fluctuation coefficient. For the second simulated manufacturing test result, a diode quality evaluation function is used to calculate and obtain a second quality evaluation coefficient.

[0044] The first quality assessment coefficient is compared with the second quality assessment coefficient. If the second quality assessment coefficient is higher, the second manufacturing parameter combination is used as the current optimal manufacturing parameter combination; otherwise, the second quality assessment coefficient is used as the current optimal manufacturing parameter combination according to probability.

[0045] Define a convergence condition, such as setting a difference threshold. When the difference between the optimal manufacturing parameter combinations in two iterations is less than the difference threshold, the algorithm is considered to have converged. Alternatively, set an iteration number threshold. When the iteration number threshold is reached, it is considered to have converged. In each round of iteration, check the difference between the current optimal manufacturing parameter combination and the optimal manufacturing parameter combination of the previous round, or the number of iterations. If the convergence condition is reached, stop the iteration. The current optimal manufacturing parameter combination at this time is the optimal manufacturing parameter combination.

[0046] Furthermore, based on the N unqualified photoelectric conversion efficiencies, a material ratio optimization space and a doping concentration optimization space are constructed, including: Obtain a first operating condition of a first unqualified photoelectric conversion efficiency, and obtain a first photovoltaic diode manufacturing parameter record that meets a photoelectric conversion efficiency threshold under the first operating condition; Extracting a first material ratio information set and a first doping concentration information set based on the first photovoltaic diode manufacturing parameter record; Based on the first material ratio information set and the first doping concentration information set, obtaining a first material ratio interval and a first doping concentration interval; Sequentially obtain a second material ratio interval, a third material ratio interval, and an Mth material ratio interval, and calculate the interval intersection of the first material ratio interval, the second material ratio interval, the third material ratio interval, and the Mth material ratio interval to obtain a target material ratio interval; sequentially obtaining a second doping concentration interval, a third doping concentration interval, and an Mth doping concentration interval, and calculating the interval intersection of the first doping concentration interval, the second doping concentration interval, the third doping concentration interval, and the Mth doping concentration interval to obtain a target doping concentration interval; A material ratio optimization space is established based on the target material ratio interval, and a doping concentration optimization space is established based on the target doping concentration interval.

[0047] The photovoltaic diode manufacturing parameter records include photovoltaic diodes based on different process parameters and the photoelectric conversion efficiency of the photovoltaic diodes under different working conditions. The first working condition corresponding to the first unqualified photoelectric conversion efficiency is determined, and for the determined first working condition, the records that meet the photoelectric conversion efficiency threshold are selected from the photovoltaic diode manufacturing parameter records as the first photovoltaic diode manufacturing parameter records, and the photoelectric conversion efficiency of the photovoltaic diodes corresponding to these records under the first working condition meets the requirements.

[0048] A plurality of photovoltaic diodes with different manufacturing processes are extracted from the manufacturing parameter record of the first photovoltaic diode, and their material ratios and doping concentrations are obtained to obtain a first material ratio information set and a first doping concentration information set.

[0049] Based on the extracted first material ratio information set, the interval range of the material ratio is determined, which can be the minimum and maximum values ​​of each material ratio; similarly, based on the extracted first doping concentration information set, the interval range of the doping concentration is determined, which can be the minimum and maximum values ​​of the doping concentration.

[0050] In this way, a first material ratio interval and a first doping concentration interval are obtained, which will be used in the subsequent manufacturing parameter optimization process to ensure that the new manufacturing parameters are adjusted within a suitable range, thereby improving the quality and performance of the photovoltaic diode.

[0051] Similar to the step of obtaining the first material ratio interval, the second, third, and up to the Mth material ratio intervals are obtained in sequence, and these intervals are the value ranges of different material ratios. The first material ratio interval and the second to Mth material ratio intervals are calculated one by one for the interval intersection, and the interval intersection refers to the common part of all intervals. The target material ratio interval finally obtained is the intersection of all material ratio intervals, that is, the intersection part of all intervals.

[0052] Similar to the step of obtaining the first doping concentration interval, the second, third, and up to the Mth doping concentration intervals are obtained in sequence, and these intervals are value ranges of different doping concentrations. The first doping concentration interval and the second to the Mth doping concentration intervals are calculated one by one, and the target doping concentration interval finally obtained is the intersection of all doping concentration intervals, that is, the intersection of all intervals.

[0053] Use the target material ratio interval to determine the feasible range of material ratio. These ranges may be the minimum and maximum values ​​of each material ratio. These ranges are combined to form the optimization space of material ratio. Use the target doping concentration interval to determine the feasible range of doping concentration. These ranges may be the minimum and maximum values ​​of doping concentration. These ranges are combined to form the optimization space of doping concentration.

[0054] Establishing these optimization spaces helps determine the search range of manufacturing parameters so that effective searches can be performed in the subsequent manufacturing parameter optimization process, which ensures that new manufacturing parameters are adjusted within a suitable range, thereby improving the quality of photovoltaic diodes.

[0055] Furthermore, based on the second quality assessment coefficient and the first quality assessment coefficient, performing comparison and screening of manufacturing parameter combinations to obtain the current optimal manufacturing parameter combination includes: Determine whether the second quality assessment coefficient is greater than the first quality assessment coefficient, and if so, use the second manufacturing parameter combination as the current optimal manufacturing parameter combination; If not, the second manufacturing parameter combination is used as the current optimal manufacturing parameter combination according to probability, wherein the calculation formula of the probability is as follows: ; in, is the natural logarithm, is the second quality assessment coefficient, is the first quality assessment coefficient, and C is the optimization rate factor.

[0056] The second quality assessment coefficient is compared with the first quality assessment coefficient. If the second quality assessment coefficient is greater than the first quality assessment coefficient, it means that the quality of the second manufacturing parameter combination is better, and the second manufacturing parameter combination is set as the current optimal manufacturing parameter combination.

[0057] Set the probability calculation formula as follows: ; The probability is obtained by dividing the difference in evaluation coefficients by the optimization rate factor and converting it through a natural logarithmic function. The purpose of setting this probability formula is to allow acceptance of manufacturing parameter combinations corresponding to poor quality evaluation coefficients to a certain extent, so as to jump out of the local optimal solution during the search process, thereby better optimizing the manufacturing parameters of photovoltaic diodes.

[0058] Determine whether to accept the second manufacturing parameter combination as the current optimal manufacturing parameter combination based on the calculated probability. For example, if the probability is greater than a randomly generated value, such as a random number between 0 and 1, the second manufacturing parameter combination is accepted as the current optimal manufacturing parameter combination. Otherwise, the first manufacturing parameter combination is used as the current optimal manufacturing parameter combination.

[0059] Furthermore, using the first manufacturing parameter combination, performing a simulated manufacturing test in the diode test model to generate a first simulated manufacturing test result also includes: Obtain constraints based on preset manufacturing requirements; Acquire a first simulation manufacturing result based on the first manufacturing parameter combination in a diode manufacturing model; Determine whether the first simulation manufacturing result satisfies the constraint condition, and if so, retain the first simulation manufacturing test result and continue to search for the best result; If not, the first manufacturing parameter combination is abandoned and the optimization process continues.

[0060] Define preset manufacturing requirements, including but not limited to material requirements, process requirements, performance requirements, etc. Based on the preset manufacturing requirements, derive constraints on various parameters and variables in the manufacturing process. These constraints include restrictions on material ratio, doping concentration, process flow, equipment use, structural characteristics, etc.

[0061] The first manufacturing parameter combination is applied to the diode manufacturing model. The diode manufacturing model is used to simulate the manufacturing process of the photovoltaic diode. During the manufacturing process, various manufacturing parameters, such as material ratio, doping concentration, etc., as well as the influence of manufacturing equipment are considered to obtain various data and indicators generated in the simulated manufacturing process, including but not limited to photoelectric conversion efficiency, material distribution, structural characteristics, etc.

[0062] The first simulation manufacturing result is checked to determine whether the first simulation manufacturing result meets all the constraints. If all the constraints are met, it means that the manufacturing parameter combination is acceptable. In this case, it is retained as a reference for the subsequent optimization process, and the manufacturing parameter optimization process is continued to find a better manufacturing parameter combination.

[0063] If the first simulation manufacturing result does not meet the constraint condition, it means that the manufacturing parameter combination is unacceptable, and the first manufacturing parameter combination currently used is abandoned, and the manufacturing parameter optimization process is continued to find a new manufacturing parameter combination.

[0064] In summary, the photovoltaic diode manufacturing parameter optimization method based on twin simulation provided in the embodiment of the present application has the following technical effects: 1. Through digital twin technology, the diode test model is constructed by combining the actual diode characteristic data and the same family test data set, thereby realizing the intelligent optimization of manufacturing parameters; 2. The simulation test model can be used to quickly and efficiently perform simulation tests on the manufactured photovoltaic diode samples, generate photoelectric conversion efficiency data under multiple working conditions, effectively improve test efficiency, and avoid waste of resources; 3. By determining the unqualified photoelectric conversion efficiency and optimizing the manufacturing parameters based on this, the generation rate of unqualified products can be effectively reduced, thereby reducing manufacturing costs; 4. By using optimized manufacturing parameters to control the manufacturing of the target photovoltaic diode, the performance and quality of the photovoltaic diode can be improved, thereby improving the overall quality and performance of the product.

[0065] In summary, this photovoltaic diode manufacturing parameter optimization method based on twin simulation solves the parameter optimization problem in photovoltaic diode manufacturing through digital twin technology and big data analysis, and improves manufacturing efficiency and product quality.

[0066] Based on the same inventive concept as the photovoltaic diode manufacturing parameter optimization method based on twin simulation in the aforementioned embodiment, Figure 2 As shown, the present application provides a photovoltaic diode manufacturing parameter optimization system based on twin simulation, the system comprising: A characteristic data acquisition module 10, wherein the characteristic data acquisition module 10 is used to acquire diode characteristic data of a target photovoltaic diode, wherein the diode characteristic data includes material ratio characteristics and doping concentration characteristics; A characteristic data retrieval module 20, the characteristic data retrieval module 20 is used to search in a diode database based on the diode characteristic data to obtain a set of test data of the same family, wherein the diode database is constructed based on a photoelectric conversion efficiency test of the diode; A test model construction module 30, wherein the test model construction module 30 is used to construct a diode test model based on the digital twin technology, the diode characteristic data, and the same family test data set; A simulation test module 40, the simulation test module 40 is used to perform a simulation test on the manufactured photovoltaic diode sample based on the diode test model to generate a simulation test result, wherein the simulation test result includes a plurality of photoelectric conversion efficiencies under a plurality of working conditions; A conversion efficiency determination module 50, wherein the conversion efficiency determination module 50 is used to determine the multiple photoelectric conversion efficiencies and obtain N unqualified photoelectric conversion efficiencies that do not meet the photoelectric conversion efficiency threshold; A manufacturing parameter optimization module 60, wherein the manufacturing parameter optimization module 60 is used to optimize the manufacturing parameters of the target photovoltaic diode based on the N unqualified photoelectric conversion efficiencies to obtain an optimal manufacturing parameter combination; A manufacturing control module 70 is used to perform manufacturing control of the target photovoltaic diode based on the optimal manufacturing parameter combination.

[0067] Furthermore, the system further includes a homogeneous test data set acquisition module to perform the following operation steps: Based on big data, multiple photoelectric conversion efficiency sets of multiple diode types under multiple working conditions are obtained to construct the diode database; Randomly extracting a first diode type from the diode database, obtaining a first diode feature, and a first photoelectric conversion efficiency set; Performing a similarity analysis on the diode characteristic data and the first diode characteristic to obtain a first characteristic similarity; If the first feature similarity meets a preset similarity threshold, the first photoelectric conversion efficiency set is used as the same family test data set.

[0068] Furthermore, the system further includes a diode test model building module to perform the following operation steps: Acquire basic equipment information of multiple main manufacturing equipment of the target photovoltaic diode, wherein the basic equipment information includes equipment serial information and equipment model information; Based on the equipment sequence information and equipment model information and based on digital twin technology, the plurality of main manufacturing equipment are modeled to obtain a diode manufacturing model; Mapping the diode characteristic data to the diode manufacturing model to generate a diode twin model; Based on the diode twin model, a plurality of photoelectric conversion efficiency test channels are constructed, wherein the plurality of photoelectric conversion efficiency test channels correspond to a plurality of working conditions; Based on the same family test data set, the multiple photoelectric conversion efficiency test channels are adjusted, and the adjusted multiple photoelectric conversion efficiency test channels are integrated to construct the diode test model.

[0069] Furthermore, the system also includes an optimization module to perform the following operation steps: Based on the N unqualified photoelectric conversion efficiencies, constructing a material ratio optimization space and a doping concentration optimization space; In the material ratio optimization space and the doping concentration optimization space, randomly generating a first material ratio and a first doping concentration as a first manufacturing parameter combination; Using the first manufacturing parameter combination, performing a simulated manufacturing test in the diode test model to generate a first simulated manufacturing test result, wherein the first simulated manufacturing test result includes a simulated photoelectric conversion efficiency set and a simulated photoelectric conversion efficiency fluctuation coefficient; Construct a diode quality assessment function as follows: ; Where FDQ is the diode quality assessment factor, is the ith simulated photoelectric conversion efficiency under the ith working condition, m is the number of working conditions, is the weight of the i-th working condition, To simulate the fluctuation coefficient of photoelectric conversion efficiency, is the first weight, is the second weight, and , The sum of is 1; Performing a quality assessment on the first simulation manufacturing test result according to the diode quality assessment function to obtain a first quality assessment coefficient; Continue to obtain a second manufacturing parameter combination and a second quality assessment coefficient, and perform manufacturing parameter combination comparison and screening based on the second quality assessment coefficient and the first quality assessment coefficient to obtain a current optimal manufacturing parameter combination; Continue iterating and optimizing until the convergence condition is met, and obtain the optimal manufacturing parameter combination.

[0070] Furthermore, the system further includes an optimization space construction module to perform the following operation steps: Obtain a first operating condition of a first unqualified photoelectric conversion efficiency, and obtain a first photovoltaic diode manufacturing parameter record that meets a photoelectric conversion efficiency threshold under the first operating condition; Extracting a first material ratio information set and a first doping concentration information set based on the first photovoltaic diode manufacturing parameter record; Based on the first material ratio information set and the first doping concentration information set, obtaining a first material ratio interval and a first doping concentration interval; Sequentially obtain a second material ratio interval, a third material ratio interval, and an Mth material ratio interval, and calculate the interval intersection of the first material ratio interval, the second material ratio interval, the third material ratio interval, and the Mth material ratio interval to obtain a target material ratio interval; sequentially obtaining a second doping concentration interval, a third doping concentration interval, and an Mth doping concentration interval, and calculating the interval intersection of the first doping concentration interval, the second doping concentration interval, the third doping concentration interval, and the Mth doping concentration interval to obtain a target doping concentration interval; A material ratio optimization space is established based on the target material ratio interval, and a doping concentration optimization space is established based on the target doping concentration interval.

[0071] Furthermore, the system further includes a current optimal manufacturing parameter combination acquisition module to perform the following operation steps: Determine whether the second quality assessment coefficient is greater than the first quality assessment coefficient, and if so, use the second manufacturing parameter combination as the current optimal manufacturing parameter combination; If not, the second manufacturing parameter combination is used as the current optimal manufacturing parameter combination according to probability, wherein the calculation formula of the probability is as follows: ; in, is the natural logarithm, is the second quality assessment coefficient, is the first quality assessment coefficient, and C is the optimization rate factor.

[0072] Furthermore, the system also includes a constraint setting module to perform the following operation steps: Obtain constraints based on preset manufacturing requirements; Acquire a first simulation manufacturing result based on the first manufacturing parameter combination in a diode manufacturing model; Determine whether the first simulation manufacturing result satisfies the constraint condition, and if so, retain the first simulation manufacturing test result and continue to search for the best result; If not, the first manufacturing parameter combination is abandoned and the optimization process continues.

[0073] Through the aforementioned detailed description of the photovoltaic diode manufacturing parameter optimization method based on twin simulation in this specification, those skilled in the art can clearly understand the photovoltaic diode manufacturing parameter optimization system based on twin simulation in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0074] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the processor of the computer device is used to provide computing and control capabilities; the memory of the computer device includes a non-volatile storage medium and an internal memory, wherein the non-volatile storage medium stores an operating system, a computer program and a database, and the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium; the network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a photovoltaic diode manufacturing parameter optimization method based on twin simulation.

[0075] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0076] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0077] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A photovoltaic diode manufacturing parameter optimization method based on twin simulation, characterized in that: The method comprises: Acquiring diode characteristic data of a target photovoltaic diode, wherein the diode characteristic data includes material ratio characteristics and doping concentration characteristics; Based on the diode characteristic data, searching in a diode database to obtain a set of test data of the same family, wherein the diode database is constructed based on a photoelectric conversion efficiency test of a diode; Based on the digital twin technology, a diode test model is constructed based on the diode characteristic data and the same family test data set; Based on the diode test model, a simulation test is performed on the manufactured photovoltaic diode sample to generate a simulation test result, wherein the simulation test result includes multiple photoelectric conversion efficiencies under multiple working conditions; Determining the plurality of photoelectric conversion efficiencies, and obtaining N unqualified photoelectric conversion efficiencies that do not meet a photoelectric conversion efficiency threshold; Based on the N unqualified photoelectric conversion efficiencies, optimizing the manufacturing parameters of the target photovoltaic diode to obtain an optimal manufacturing parameter combination; Based on the optimal manufacturing parameter combination, performing manufacturing control of the target photovoltaic diode; The method of optimizing the manufacturing parameters of the target photovoltaic diode based on the N unqualified photoelectric conversion efficiencies to obtain the optimal manufacturing parameter combination includes: Based on the N unqualified photoelectric conversion efficiencies, constructing a material ratio optimization space and a doping concentration optimization space; In the material ratio optimization space and the doping concentration optimization space, randomly generating a first material ratio and a first doping concentration as a first manufacturing parameter combination; Using the first manufacturing parameter combination, performing a simulated manufacturing test in the diode test model to generate a first simulated manufacturing test result, wherein the first simulated manufacturing test result includes a simulated photoelectric conversion efficiency set and a simulated photoelectric conversion efficiency fluctuation coefficient; Construct a diode quality assessment function as follows: ； Where FDQ is the diode quality assessment factor, is the ith simulated photoelectric conversion efficiency under the ith working condition, m is the number of working conditions, is the weight of the i-th working condition, To simulate the fluctuation coefficient of photoelectric conversion efficiency, is the first weight, is the second weight, and , The sum of is 1; Performing a quality assessment on the first simulation manufacturing test result according to the diode quality assessment function to obtain a first quality assessment coefficient; Continue to obtain a second manufacturing parameter combination and a second quality assessment coefficient, and perform manufacturing parameter combination comparison and screening based on the second quality assessment coefficient and the first quality assessment coefficient to obtain a current optimal manufacturing parameter combination; Continue iterating and optimizing until the convergence condition is met, and obtain the optimal manufacturing parameter combination.

2. The method according to claim 1, characterized in that Based on the diode characteristic data, a search is performed in a diode database to obtain a set of test data of the same family, including: Based on big data, multiple photoelectric conversion efficiency sets of multiple diode types under multiple working conditions are obtained to construct the diode database; Randomly extracting a first diode type from the diode database, obtaining a first diode feature, and a first photoelectric conversion efficiency set; Performing a similarity analysis on the diode characteristic data and the first diode characteristic to obtain a first characteristic similarity; If the first feature similarity meets a preset similarity threshold, the first photoelectric conversion efficiency set is used as the same family test data set.

3. The method according to claim 1, characterized in that Based on the digital twin technology, based on the diode characteristic data and the same family test data set, a diode test model is constructed, including: Acquire basic equipment information of multiple main manufacturing equipment of the target photovoltaic diode, wherein the basic equipment information includes equipment serial information and equipment model information; Based on the equipment sequence information and equipment model information and based on digital twin technology, the plurality of main manufacturing equipment are modeled to obtain a diode manufacturing model; Mapping the diode characteristic data to the diode manufacturing model to generate a diode twin model; Based on the diode twin model, a plurality of photoelectric conversion efficiency test channels are constructed, wherein the plurality of photoelectric conversion efficiency test channels correspond to a plurality of working conditions; Based on the same family test data set, the multiple photoelectric conversion efficiency test channels are adjusted, and the adjusted multiple photoelectric conversion efficiency test channels are integrated to construct the diode test model.

4. The method according to claim 1, characterized in that Based on the N unqualified photoelectric conversion efficiencies, a material ratio optimization space and a doping concentration optimization space are constructed, including: Acquire a first operating condition of a first unqualified photoelectric conversion efficiency, and acquire a first photovoltaic diode manufacturing parameter record that meets a photoelectric conversion efficiency threshold under the first operating condition; Based on the first photovoltaic diode manufacturing parameter record, extracting a first material ratio information set and a first doping concentration information set; Based on the first material ratio information set and the first doping concentration information set, obtaining a first material ratio interval and a first doping concentration interval; Sequentially obtain a second material ratio interval, a third material ratio interval, and an Mth material ratio interval, and calculate the interval intersection of the first material ratio interval, the second material ratio interval, the third material ratio interval, and the Mth material ratio interval to obtain a target material ratio interval; sequentially obtaining a second doping concentration interval, a third doping concentration interval, and an Mth doping concentration interval, and calculating the interval intersection of the first doping concentration interval, the second doping concentration interval, the third doping concentration interval, and the Mth doping concentration interval to obtain a target doping concentration interval; A material ratio optimization space is established based on the target material ratio interval, and a doping concentration optimization space is established based on the target doping concentration interval.

5. The method according to claim 1, characterized in that Based on the second quality assessment coefficient and the first quality assessment coefficient, performing comparison and screening of manufacturing parameter combinations to obtain the current optimal manufacturing parameter combination includes: Determine whether the second quality assessment coefficient is greater than the first quality assessment coefficient, and if so, use the second manufacturing parameter combination as the current optimal manufacturing parameter combination; If not, the second manufacturing parameter combination is used as the current optimal manufacturing parameter combination according to probability, wherein the calculation formula of the probability is as follows: ； in, is the natural logarithm, is the second quality assessment coefficient, is the first quality assessment coefficient, and C is the optimization rate factor.

6. The method according to claim 1, characterized in that Using the first manufacturing parameter combination, performing a simulated manufacturing test in the diode test model to generate a first simulated manufacturing test result, further comprising: Obtain constraints based on preset manufacturing requirements; Acquire a first simulation manufacturing result based on the first manufacturing parameter combination in a diode manufacturing model; Determine whether the first simulation manufacturing result satisfies the constraint condition, and if so, retain the first simulation manufacturing test result and continue to search for the best result; If not, the first manufacturing parameter combination is abandoned and the optimization process continues.

7. Photovoltaic diode manufacturing parameter optimization system based on twin simulation, characterized in that: A system for implementing the photovoltaic diode manufacturing parameter optimization method based on twin simulation according to any one of claims 1 to 6, the system comprising: A characteristic data acquisition module, wherein the characteristic data acquisition module is used to acquire diode characteristic data of a target photovoltaic diode, wherein the diode characteristic data includes material ratio characteristics and doping concentration characteristics; A characteristic data retrieval module, the characteristic data retrieval module is used to search in a diode database based on the diode characteristic data to obtain a set of test data of the same family, wherein the diode database is constructed based on a photoelectric conversion efficiency test of the diode; A test model construction module, wherein the test model construction module is used to construct a diode test model based on the digital twin technology, the diode characteristic data, and the same family test data set; A simulation test module, the simulation test module is used to perform a simulation test on the manufactured photovoltaic diode sample based on the diode test model to generate a simulation test result, wherein the simulation test result includes a plurality of photoelectric conversion efficiencies under a plurality of working conditions; A conversion efficiency determination module, the conversion efficiency determination module is used to determine the multiple photoelectric conversion efficiencies and obtain N unqualified photoelectric conversion efficiencies that do not meet the photoelectric conversion efficiency threshold; A manufacturing parameter optimization module, wherein the manufacturing parameter optimization module is used to optimize the manufacturing parameters of the target photovoltaic diode based on the N unqualified photoelectric conversion efficiencies to obtain an optimal manufacturing parameter combination; A manufacturing control module, the manufacturing control module is used to perform manufacturing control of the target photovoltaic diode based on the optimal manufacturing parameter combination; The method of optimizing the manufacturing parameters of the target photovoltaic diode based on the N unqualified photoelectric conversion efficiencies to obtain the optimal manufacturing parameter combination includes: Based on the N unqualified photoelectric conversion efficiencies, constructing a material ratio optimization space and a doping concentration optimization space; In the material ratio optimization space and the doping concentration optimization space, randomly generating a first material ratio and a first doping concentration as a first manufacturing parameter combination; Using the first manufacturing parameter combination, performing a simulated manufacturing test in the diode test model to generate a first simulated manufacturing test result, wherein the first simulated manufacturing test result includes a simulated photoelectric conversion efficiency set and a simulated photoelectric conversion efficiency fluctuation coefficient; Construct a diode quality assessment function as follows: ； Where FDQ is the diode quality assessment factor, is the ith simulated photoelectric conversion efficiency under the ith working condition, m is the number of working conditions, is the weight of the i-th working condition, To simulate the fluctuation coefficient of photoelectric conversion efficiency, is the first weight, is the second weight, and , The sum of is 1; Performing a quality assessment on the first simulation manufacturing test result according to the diode quality assessment function to obtain a first quality assessment coefficient; Continue to obtain a second manufacturing parameter combination and a second quality assessment coefficient, and perform manufacturing parameter combination comparison and screening based on the second quality assessment coefficient and the first quality assessment coefficient to obtain a current optimal manufacturing parameter combination; Continue iterating and optimizing until the convergence condition is met, and obtain the optimal manufacturing parameter combination.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the photovoltaic diode manufacturing parameter optimization method based on twin simulation described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the photovoltaic diode manufacturing parameter optimization method based on twin simulation according to any one of claims 1 to 6 are implemented.

Images