Performance prediction method and system for full-process technology of copper-indium-gallium-selenium solar cell

Abstract

The application provides a performance prediction method and system for a whole-process technology of a copper-indium-gallium-selenium solar cell, the method comprising the following steps: obtaining experimental data covering a complete device structure and a preparation technology, and removing redundant features through data cleaning, standardization and feature correlation analysis; introducing a SHAP game theory method to analyze a model and quantize marginal contribution of process parameters to photovoltaic performance; and finally determining a parameter convergence interval of a high-efficiency device by using a parallel coordinate technology, and outputting a performance prediction value. The application effectively solves the modeling problem of copper-indium-gallium-selenium solar hybrid heterogeneous data, ensures that the prediction result conforms to the device physical law through physical constraints, reveals the trade-off effect between complex process parameters, provides clear parameter guidance for high-efficiency cell preparation, and greatly reduces the trial-and-error cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of photovoltaic device manufacturing and artificial intelligence application, and particularly relates to a performance prediction method and system for a full-process technology of a copper-indium-gallium-selenium solar cell. BACKGROUND

[0002] Copper-indium-gallium-selenium (CIGS) thin-film solar cells have become one of the most competitive thin-film photovoltaic technologies due to their high photoelectric conversion efficiency and good long-term stability. However, CIGS cells are typical multilayer heterojunction complex systems, and their preparation process involves a long and delicate full-process technology chain, including substrate cleaning, back electrode sputtering, absorption layer growth (such as co-evaporation method, sputtering and seleniumization method), buffer layer chemical water bath deposition, high-resistance window layer and conductive window layer preparation, metal gate electrode evaporation, and anti-reflection layer coating.

[0003] In this full process, there are as many as dozens of process parameters (for example: deposition temperature, element composition ratio, layer material, layer thickness, doping process, etc.). There is a strong nonlinear coupling relationship and complex physical trade-off effect between these parameters. For example, increasing the gallium (Ga) content can increase the band gap and improve the open circuit voltage, but it often leads to a decrease in short circuit current. The traditional CIGS research and development mode mainly relies on the "trial and error method", and researchers need to conduct a large number of orthogonal experiments to find the optimal parameter combination, which not only leads to a long research and development cycle and large reagent consumption, but also makes it difficult to locate the global optimal solution in a multi-dimensional parameter space.

[0004] Existing auxiliary research and development methods mainly include physical simulation software (such as SCAPS-1D, AMPS, etc.), but the prediction accuracy of such software is highly dependent on the input of microscopic physical parameters such as defect energy level density and interface recombination rate, and these microscopic parameters are difficult to accurately determine in actual experiments, resulting in a large deviation between the simulation results and the experimental preparation.

[0005] In recent years, machine learning technology has demonstrated tremendous potential in the field of materials science. However, existing research in the CIGS field has limitations: First, CIGS process data exhibits a typical "hybrid heterogeneous" characteristic, simultaneously containing continuous "numerical features" (e.g., temperature: 550℃, thickness: 2.5μm) and discrete "categorical features" (e.g., substrate type: soda-lime glass / polyimide; buffer layer material: CdS / Zn(O,S)). Traditional algorithms (e.g., linear regression, support vector regression, random forest) typically require one-hot encoding when processing high-dimensional categorical features, leading to an extremely sparse feature matrix. This not only increases the computational burden but also severs the potential connections between categorical features, resulting in limited prediction accuracy. Second, most existing research is limited to parameter optimization at the single level of the absorption layer (e.g., focusing only on the CGI and GGI ratios), neglecting the synergistic impact of the overall device structure parameters, such as the interface layer, window layer, and back contact layer, on the final efficiency. Third, many high-precision models are considered "black boxes," unable to explain the specific physical mechanisms to process engineers or provide intuitive parameter optimization ranges, making it difficult to implement these models in actual production lines. Summary of the Invention

[0006] In view of the above, the main objective of this invention is to propose a performance prediction method and system for the entire process of copper indium gallium selenide (CIGS) solar cells, in order to solve the aforementioned technical problems.

[0007] This invention proposes a performance prediction method for the entire process of copper indium gallium selenide (CIGS) solar cells, the method comprising the following steps:

[0008] Step 1: Obtain experimental data of copper indium gallium selenide (CIGS) solar cells, and perform data cleaning and standardization to obtain a standard dataset;

[0009] Step 2: Based on the device physics principle of copper indium gallium selenide solar cells, calculate the physical derived feature set from the fabrication process parameters in the standard dataset, and fuse the physical derived features with the fabrication process parameters to construct the physical enhancement feature matrix.

[0010] Step 3: Analyze the correlation between the features in the physical enhancement feature matrix to remove redundant features with multicollinearity, and identify numerical and categorical features to construct a hybrid feature input matrix; divide the dataset based on the hybrid feature input matrix into a training set and a test set.

[0011] Step 4: Construct a prediction model based on a classification boosting tree model; train the prediction model using the training set and optimize it using a loss function guided by physical constraints to obtain the trained prediction model.

[0012] Step 5, introducing a game theory-based explainability analysis method to analyze the trained prediction model to obtain the marginal contribution of each process parameter to the photovoltaic performance index;

[0013] Step 6, screening key process parameters based on marginal contribution, and using parallel coordinate visualization technology to map the distribution trajectory of high photovoltaic performance samples on the key process parameter axis to identify the dense convergence area of the sample trajectory; the dense convergence area of the sample trajectory is determined as the optimal process parameter convergence interval.

[0014] The application also provides a performance prediction system for a full-process technology of a copper-indium-gallium-selenium solar cell.

[0015] The data management module is configured to:

[0016] Obtain experimental data of the copper-indium-gallium-selenium solar cell, and perform data cleaning and standardization processing to obtain a standard data set;

[0017] The data processing module is configured to:

[0018] Based on the device physics principle of the copper-indium-gallium-selenium solar cell, a physical derived feature set is calculated from the preparation process parameters in the standard data set, the physical derived features are fused with the preparation process parameters to construct a physical enhanced feature matrix;

[0019] The correlation between the features in the physical enhanced feature matrix is analyzed to eliminate redundant features with multiple collinearity, and the numerical features and the categorical features are identified to construct a mixed feature input matrix; the data set based on the mixed feature input matrix is divided into a training set and a test set;

[0020] The model calculation module is configured to:

[0021] Construct a prediction model based on a classification boosting tree model; the training set is used to train the prediction model, and a loss function guided by physical constraints is used for optimization to obtain a trained prediction model;

[0022] The intelligent analysis module is configured to:

[0023] Introducing a game theory-based explainability analysis method to analyze the trained prediction model to obtain the marginal contribution of each process parameter to the photovoltaic performance index;

[0024] Based on marginal contribution degree, key process parameters are screened, and the distribution trajectory of high photovoltaic performance samples on the key process parameter axis is mapped by using parallel coordinate visualization technology to identify the dense convergence area of the sample trajectory; the dense convergence area of the sample trajectory is determined as the optimal process parameter convergence interval.

[0025] Compared with the prior art, the beneficial effects of the present application are:

[0026] 1、The machine learning model constructed by the present application covers more than 20 key parameters from the substrate to the anti-reflection layer, which can better reflect the multi-layer heterojunction synergistic effect and full-process process coupling mechanism of the real device compared with single absorption layer research.

[0027] 2、The present application embeds the band theory, carrier transport theory and optical theory of CIGS solar cells into the machine learning model by constructing a set of physical derived features (equivalent band gap, interface barrier height, optical loss coefficient, etc.), realizing the leap from pure data-driven to physical knowledge-guided, so that the model can not only fit the data, but also understand the physical mechanism.

[0028] 3、The loss function guided by physical constraints proposed by the present application introduces theoretical limit constraints, current-voltage-fill factor consistency constraints, band gap-open circuit voltage relationship constraints and other physical mechanism constraint terms to ensure that the model prediction results do not violate the physical laws of the device, avoiding the high-precision but unreasonable prediction of pure black box model, and significantly improving the reliability and engineering practicability of the model in extrapolation scenarios.

[0029] 4、The present application perfectly solves the high-dimensional sparse matrix problem caused by the mixing of "material category" and "process value" in CIGS process by introducing adaptive ordered target statistics technology, which not only avoids the dimension explosion compared with traditional one-hot encoding method, but also retains the association information between category features and target values, significantly improving the prediction accuracy.

[0030] 5、The "parameter convergence interval" determined by parallel coordinate visualization provides a clear process window for experimenters, greatly reducing the trial and error cost.

[0031] Additional aspects and advantages of the present application will be partially given in the following description, partially become obvious from the following description, or be understood by embodiments of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 A step flow chart of a performance prediction method for a copper-indium-gallium-selenium solar cell full-process technology proposed by the present application. DETAILED DESCRIPTION

[0033] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0034] These and other aspects of the embodiments of the present invention will become clear from the following description and accompanying drawings. In these descriptions and drawings, some specific embodiments of the present invention are specifically disclosed to illustrate some ways of implementing the principles of the embodiments of the present invention; however, it should be understood that the scope of the embodiments of the present invention is not limited thereto.

[0035] Please see Figure 1 This embodiment provides a method for performance prediction of the entire process of copper indium gallium selenide (CIGS) solar cells, the method including the following steps:

[0036] Step 1: Obtain experimental data of copper indium gallium selenide (CIGS) solar cells, and perform data cleaning and standardization to obtain a standard dataset.

[0037] In step 1, experimental data of copper indium gallium selenide (CIGS) solar cells are acquired and cleaned and standardized to obtain a standard dataset. The experimental data includes complete device structure parameters from substrate to top electrode, fabrication process parameters, and corresponding photovoltaic performance test indicators. The experimental data exhibits hybrid heterogeneous characteristics, containing both continuous numerical features and discrete categorical features. The complete device structure parameters and fabrication process parameters include at least: substrate type, maximum substrate temperature, back electrode material type, back electrode thickness, absorber layer fabrication process type, absorber layer thickness, gallium-indium ratio, copper-gallium-indium ratio, alkali metal doping method, potassium cyanide etching treatment, buffer layer material type, buffer layer thickness, window layer material type, window layer thickness, transparent conductive oxide layer material type, transparent conductive oxide layer thickness, grid electrode material type, grid electrode thickness, antireflection layer configuration, effective solar cell area, and grid electrode shading area ratio. The photovoltaic performance test indicators include: photoelectric conversion efficiency, open-circuit voltage, short-circuit current density, and fill factor.

[0038] Specifically, data cleaning includes: using box plots to identify and remove outliers from continuous variables;

[0039] The standardization process specifically includes: using the Z-Score standardization method to process numerical features, and the following relationship exists in the corresponding process:

[0040] ;

[0041] in, denotes a standardized parameter value, denotes an original parameter value, denotes a parameter of the mean, denotes a parameter of the standard deviation.

[0042] In step 2, based on the physical principle of the device of the copper indium gallium selenide solar cell, a set of physical derived features is calculated from the preparation process parameters in the standard data set, and the physical derived features are fused with the preparation process parameters to construct a physical enhanced feature matrix.

[0043] In step 2, based on the physical principle of the device of the copper indium gallium selenide solar cell, a set of physical derived features is calculated from the preparation process parameters in the standard data set, and the physical derived features are fused with the preparation process parameters to construct a physical enhanced feature matrix; wherein the set of physical derived features includes: equivalent band gap, interface barrier height, optical loss coefficient; the set of physical derived features is used to characterize the characteristic quantity of the internal physical mechanism of the device;

[0044] Wherein, based on the physical principle of the device of the copper indium gallium selenide solar cell, a set of physical derived features is calculated from the preparation process parameters in the standard data set, which includes the following sub-steps:

[0045] Based on the gallium-indium ratio, the equivalent band gap is calculated by using the empirical formula, and there is the following relationship in the corresponding process:

[0046] ;

[0047] Wherein, denotes the equivalent band gap, denotes the gallium-indium ratio;

[0048] Based on the gallium-indium ratio and the copper-gallium-indium ratio, the absorption layer composition is determined, the conduction band minimum energy level is determined according to the buffer layer material type and the absorption layer composition, and the conduction band offset is calculated to obtain the interface barrier height, and there is the following relationship in the corresponding process:

[0049] ;

[0050] Wherein, denotes the interface barrier height, and the interface barrier affects the interface recombination rate and the carrier transport efficiency; denotes the conduction band minimum energy level of the buffer layer material type, denotes the conduction band minimum energy level of the absorption layer composition;

[0051] Based on the anti-reflection layer setting, the thickness of the transparent conductive oxide layer and the ratio of the light shielding area of the grid electrode, the optical loss coefficient is calculated, and there is the following relationship in the corresponding process:

[0052] ;

[0053] wherein, represents an optical loss coefficient, represents a reflectivity of the anti-reflective layer, represents an absorption coefficient of the transparent conductive oxide layer, represents a thickness of the transparent conductive oxide layer, represents a ratio of the light shielding area of the gate electrode.

[0054] It should be noted that the physical derived features can explicitly represent the band structure, carrier transport and optical properties inside the CIGS solar cell, so that the model can learn the parameter-performance mapping relationship conforming to the physical law.

[0055] In step 3, the correlation between each feature in the physical enhanced feature matrix is analyzed to eliminate redundant features with multicollinearity, and the numerical features and the category features are identified to obtain a mixed feature input matrix; a data set based on the mixed feature input matrix is divided into a training set and a test set.

[0056] In step 3, the correlation between each feature in the physical enhanced feature matrix is analyzed to eliminate redundant features with multicollinearity, and the numerical features and the category features are identified to obtain a mixed feature input matrix; a data set based on the mixed feature input matrix is divided into a training set and a test set.

[0057] Based on the standard data set, the Pearson correlation coefficient between any two process parameters is calculated, and the following relationship exists in the process:

[0058] ;

[0059] wherein, represents the Pearson correlation coefficient between , represents a mathematical expectation, and both represent process parameters, represents the mean of , represents the mean of , represents the standard deviation of , represents the standard deviation of ;

[0060] If is greater than a preset correlation threshold, it is determined that and have strong collinearity, and and Features with low correlation to photovoltaic performance test indicators are selected to eliminate feature redundancy.

[0061] For example, "gate electrode thickness" is usually highly correlated with "gate electrode material type" (the choice of material determines its thickness). In this case, "gate electrode thickness" can be removed, and "gate electrode material type" with more information can be retained, thereby constructing a simplified hybrid feature input matrix.

[0062] It should be noted that the dataset based on the mixed feature input matrix is ​​divided into a training set and a test set in an 8:2 ratio, which are used for model training and model evaluation, respectively.

[0063] Step 4: Construct a prediction model based on a classification boosting tree model; train the prediction model using the training set and optimize it using a loss function guided by physical constraints to obtain the trained prediction model; the loss function includes: prediction error term, physical mechanism constraint term and process constraint.

[0064] In step 4, a prediction model based on a classification boosting tree model is constructed; the prediction model is trained using the training set and optimized using a loss function guided by physical constraints to obtain the trained prediction model; wherein, the loss function includes: a prediction error term, a physical mechanism constraint term, and a process constraint term, and the expression of the loss function is:

[0065] ;

[0066] in, Represents the loss function. This represents the prediction error term. and All represent weighting coefficients. Represents physical mechanism constraints. Indicates process constraints;

[0067] The expression for the prediction error term is as follows:

[0068] ;

[0069] in, Indicates the number of samples. Indicates the first Predicted photoelectric conversion efficiency for each sample This represents the actual photoelectric conversion efficiency;

[0070] The physical mechanism constraints include theoretical limit constraints, current-voltage-fill factor consistency constraints, and bandgap-open-circuit voltage relationship constraints. The expressions for the physical mechanism constraints are as follows:

[0071] ;

[0072] wherein, denotes the theoretical limit constraint, denotes the maximum value, denotes the predicted photoelectric conversion efficiency, denotes the theoretical efficiency upper limit, denotes the current-voltage- fill factor consistency constraint, denotes the model-predicted short-circuit current density, denotes the model-predicted open-circuit voltage, denotes the model-predicted fill factor, denotes the standard incident light power, denotes the band gap-open circuit voltage relationship constraint, denotes the electronic charge quantity, denotes the empirical voltage loss;

[0073] wherein, the expression of the process constraint term is:

[0074] ;

[0075] wherein, and both denote weight coefficients, denotes the layer thickness rationality constraint, denotes the component rationality constraint;

[0076] It should be noted that the four weight coefficients , , and are determined by cross-validation to balance the importance of data fitting and physical constraints; the loss function guided by the physical constraints ensures that the model prediction result is not only statistically accurate, but also physically reasonable, avoiding the prediction of violating physical laws that may be produced by pure data-driven models.

[0077] Further, when training the prediction model using the training set, the adaptive ordered target statistics method based on the Sigmoid function is used to process the category type features in the mixed feature input matrix, and the category type features are converted into numerical type features, and there is a relationship as follows in the corresponding process:

[0078] ;

[0079] wherein, denotes the numerical encoding value of the th category feature of the th sample after conversion, denotes the weight coefficient, denotes the ranking index of the current sample, denotes the indicator function, if the the first category feature of the i-th sample the first category feature of the i-th sample the first category feature of the i-th sample the first category feature of the i-th sample the category value of the i-th sample on the j-th feature, the category value of the i-th sample on the j-th feature, the category value of the i-th sample on the j-th feature, the category value of the i-th sample on the j-th feature, the category value of the i-th sample on the j-th feature, the category value of the i-th sample on the j-th feature, the sample index currently being calculated, the historical sample index located before the i-th sample in the random permutation, the historical sample index located before the i-th sample in the random permutation, the index of the feature, the target value of the i-th sample, the target value of the i-th sample, the sample statistical number located before the i-th sample in the random permutation and having the same category value, the sample statistical number located before the i-th sample in the random permutation and having the same category value, the infinitesimal constant preventing the denominator from being zero, the prior probability, the natural constant, the center offset parameter of the Sigmoid function, used to control the sample amount threshold of weight switching, the slope adjustment parameter of the Sigmoid function, used to control the smoothness of weight change.

[0080] It should be noted that in the preparation process of the CIGS solar cell, the data has a significant "long tail distribution" characteristic. For example, the sample amount of some mainstream substrates (such as sodium calcium glass) is huge, while the sample amount of some new flexible substrates or specific doping processes is extremely small (sparse category). The traditional CatBoost ordered target statistics usually uses a fixed smoothing parameter, which has limitations when processing CIGS mixed data with a large difference in sample amount:

[0081] For categories with sufficient sample amount, the fixed smoothing parameter may introduce unnecessary prior bias;

[0082] For categories with extremely small sample amount, the fixed smoothing parameter may not be sufficient to suppress noise.

[0083] The present application creatively introduces an adaptive weight mechanism based on the Sigmoid function, which improves the above problems:

[0084] The physical meaning of the weight coefficient : it represents the confidence of the model to the "current category statistical mean".

[0085] Parameter The role: defines the "flip threshold" of confidence. When the number of samples of a certain process category is less than 100, the Sigmoid function output value is 0, and the model mainly relies on the global prior probability , so as to avoid accidental errors caused by small samples (avoid target leakage); when is greater than 100, the Sigmoid function output value is 1, and the model mainly relies on the statistical mean of the category itself, so as to accurately capture the specific impact of the process.

[0086] Parameter The role: control the sensitivity of confidence change. The smaller the weight, the steeper the switching, realizing the rapid phase change from "trust prior" to "trust data".

[0087] Step 5, introduce an explainable analysis method based on game theory to analyze the trained prediction model to obtain the marginal contribution of each process parameter to the photovoltaic performance index.

[0088] In step 5, an explainable analysis method based on game theory is introduced to analyze the trained prediction model to obtain the marginal contribution of each process parameter to the photovoltaic performance index, which includes the following sub-steps:

[0089] Introduce an explainable analysis method based on game theory to calculate the SHAP value of each process parameter. There is a relationship in the process as follows:

[0090] ;

[0091] Where, represents the SHAP value of the feature , represents the subset in the set that does not contain the feature , represents the factorial, represents the set of all input features, represents the prediction value of the target prediction model after adding the feature to the subset , and represents the prediction value of the target prediction model using only the features in the subset .

[0092] Take the absolute value of the SHAP value of each process parameter as the marginal contribution of each process parameter to the photovoltaic performance index.

[0093] ​​​​It should be noted that through SHAP analysis, the present application reveals key physical mechanisms, for example: the application of an anti-reflective layer (ARC) is the dominant factor in improving photoelectric conversion efficiency; the GGI ratio has a significant positive contribution to the open-circuit voltage, but too high GGI will lead to a decrease in short-circuit current density, revealing the trade-off effect in band gap regulation.

[0094] Step 6, screening key process parameters based on marginal contribution degree, and using parallel coordinate visualization technology to map the distribution trajectory of high photovoltaic performance samples on the key process parameter axis to identify the dense convergence area of the sample trajectory; and determining the dense convergence area of the sample trajectory as the optimal process parameter convergence interval.

[0095] In step 6, key process parameters are screened based on marginal contribution degree, and parallel coordinate visualization technology is used to map the distribution trajectory of high photovoltaic performance samples on the key process parameter axis to identify the dense convergence area of the sample trajectory; and the dense convergence area is determined as the optimal process parameter convergence interval, which includes the following sub-steps:

[0096] Based on the size of the marginal contribution degree of each process parameter to the photovoltaic performance index, each process parameter is sorted in descending order, and the process parameter with a marginal contribution degree greater than a preset threshold is selected as a key process parameter;

[0097] The key process parameters are mapped to a two-dimensional plane using parallel coordinate visualization technology to obtain a key process parameter axis;

[0098] Setting a target optimization threshold for photoelectric conversion efficiency;

[0099] Extracting a sample set with a performance prediction value higher than the target optimization threshold, and identifying a dense convergence area of the sample set on the key process parameter axis, and determining the dense convergence area as the optimal process parameter convergence interval.

[0100] The present embodiment also provides a performance prediction system for a copper-indium-gallium-selenium solar cell full-process technology, wherein the system applies the performance prediction method for a copper-indium-gallium-selenium solar cell full-process technology as described above, and the system comprises:

[0101] The data management module is configured to:

[0102] Obtain experimental data of a copper-indium-gallium-selenium solar cell, and perform data cleaning and standardization processing to obtain a standard data set;

[0103] The data processing module is configured to:

[0104] Based on the device physical principle of the copper indium gallium selenide solar cell, a physical derived feature set is calculated from the preparation process parameters in the standard data set, the physical derived features are fused with the preparation process parameters to construct a physical enhanced feature matrix;

[0105] Correlations between features in the physical enhanced feature matrix are analyzed to eliminate redundant features with multiple collinearity, and numerical features and categorical features are identified to construct a mixed feature input matrix; a data set based on the mixed feature input matrix is divided into a training set and a test set;

[0106] The model calculation module is configured to:

[0107] A prediction model based on a classification boosting tree model is constructed; the prediction model is trained using the training set, and a loss function guided by physical constraints is used for optimization to obtain a trained prediction model;

[0108] The intelligent analysis module is configured to:

[0109] An explainability analysis method based on game theory is introduced to analyze the trained prediction model to obtain the marginal contribution of each process parameter to the photovoltaic performance index;

[0110] Key process parameters are screened based on the marginal contribution, and parallel coordinate visualization technology is used to map the distribution trajectory of high photovoltaic performance samples on the key process parameter axis to identify the dense convergence area of the sample trajectory; the dense convergence area of the sample trajectory is determined as the optimal process parameter convergence interval.

[0111] It should be understood that although each step in the flowchart of each embodiment of the present application is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least a part of other steps or sub-steps or stages of other steps.

[0112] It should be understood that various aspects of the application can be implemented in hardware, software, firmware or a combination of them. In the above embodiments, various steps or methods can be implemented in software or firmware which is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following technologies, known in the art, can be used to implement the hardware: discrete logic circuitry having logic gates for implementing logic functions upon an application of data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0113] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in one or more embodiments or examples.

[0114] The above-described embodiments only express several implementation manners of the present application, which are described in a more specific and detailed manner, but cannot be understood as a limitation on the patent scope of the present application. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present application, which are all within the protection scope of the present application. Therefore, the patent protection scope of the present application should be subject to the appended claims.

Claims

1. A method for performance prediction of a copper indium gallium selenide (CIGS) solar cell process, characterized in that, The method comprises the following steps: Step 1, obtaining experimental data of copper-indium-gallium-selenium solar cells, and performing data cleaning and standardization processing to obtain a standard data set; Step 2, based on the device physical principle of copper-indium-gallium-selenium solar cells, the physical derived feature set is calculated from the preparation process parameters in the standard data set, the physical derived features and the preparation process parameters are fused to obtain a physical enhanced feature matrix; Step 3, analyze the correlation between each feature in the physical enhanced feature matrix to eliminate redundant features with multiple collinearity, and identify numerical features and categorical features to construct a mixed feature input matrix; Divide the data set based on the mixed feature input matrix into a training set and a test set; Step 4, constructing a prediction model based on a classification boosting tree model; training the prediction model using the training set, and using a loss function guided by physical constraints for optimization to obtain a trained prediction model; Step 5, introducing an explainability analysis method based on game theory to analyze the trained prediction model to obtain the marginal contribution of each process parameter to the photovoltaic performance index; Step 6, screening key process parameters based on marginal contribution, and using parallel coordinate visualization technology to map the distribution trajectory of high photovoltaic performance samples on the key process parameter axis to identify the dense convergence area of the sample trajectory; Determine the dense convergence area of the sample trajectory as the optimal process parameter convergence interval.

2. The method for performance prediction of a full process of a copper indium gallium selenide solar cell according to claim 1, characterized in that, In the step 1, the experimental data includes complete device structure parameters from the substrate to the top electrode, preparation process parameters and corresponding photovoltaic performance test indicators; the experimental data has mixed heterogeneous characteristics, including continuous numerical features and discrete categorical features; wherein, the complete device structure parameters and preparation process parameters at least include: substrate type, maximum substrate temperature, back electrode material type, back electrode thickness, absorption layer preparation process type, absorption layer thickness, gallium-indium ratio, copper-gallium-indium ratio, alkali metal doping treatment method, potassium cyanide etching treatment, buffer layer material type, buffer layer thickness, window layer material type, window layer thickness, transparent conductive oxide layer material type, transparent conductive oxide layer thickness, gate electrode material type, gate electrode thickness, anti-reflection layer setting, solar cell effective area, and gate electrode shading area ratio; the photovoltaic performance test indicators include: photoelectric conversion efficiency, open circuit voltage, short circuit current density, and fill factor. 3.The performance prediction method of a whole process of a copper-indium-gallium-selenium solar cell according to claim 2, characterized in that, In the step 1, the experimental data of copper-indium-gallium-selenium solar cells is obtained, and data cleaning and standardization processing is performed to obtain a standard data set, wherein the data cleaning processing specifically includes: using the box plot rule to identify and eliminate outliers in continuous variables; Wherein, the standardization processing specifically includes: using the Z-Score standardization method to process numerical features, and there is the following relationship in the corresponding process: ； wherein denotes the standardized parameter value, denotes the original parameter value, denotes the parameter of the mean, denotes the standard deviation of the parameter .

4. The method according to claim 3, wherein, In the step 2, based on the device physical principle of copper-indium-gallium-selenium solar cells, the physical derived feature set is calculated from the preparation process parameters in the standard data set, the physical derived features and the preparation process parameters are fused to obtain a physical enhanced feature matrix; The physical derived feature set includes: equivalent band gap, interface barrier height, optical loss coefficient; The physical derived feature set is calculated from the preparation process parameters in the standard data set based on the physical principles of the copper-indium-gallium-selenium solar cell device, and specifically includes the following sub-steps: Based on the gallium-indium ratio, the equivalent band gap is calculated using an empirical formula, and the following relationship exists in the corresponding process: ； wherein, represents the equivalent bandgap, represents the gallium to indium ratio; Based on the gallium-indium ratio and the copper-gallium-indium ratio, the absorption layer composition is determined, the conduction band minimum is determined according to the buffer layer material type and the absorption layer composition, and the conduction band offset is calculated to obtain the interface barrier height, and the following relationship exists in the corresponding process: ； wherein, represents an interface barrier height, the interface barrier affects the interface recombination rate and the carrier transport efficiency; represents a conduction band minimum energy level of the buffer layer material type, represents a conduction band minimum energy level of the absorber layer component; Based on the anti-reflection layer setting, the thickness of the transparent conductive oxide layer and the ratio of the gate electrode light shielding area, the optical loss coefficient is calculated, and the following relationship exists in the corresponding process: ； wherein, represents an optical loss coefficient, represents a reflectance of the antireflection layer, represents an absorption coefficient of the transparent conductive oxide layer, represents a thickness of the transparent conductive oxide layer, represents a light shielding area ratio of the gate electrode. 5.The performance prediction method of a full-process technology of a copper-indium-gallium-selenium solar cell according to claim 4, characterized in that, In step 3, the correlation between each feature in the physical enhanced feature matrix is analyzed to eliminate redundant features with multiple collinearity, specifically including the following sub-steps: Based on the standard data set, the Pearson correlation coefficient between any two process parameters is calculated, and the following relationship exists in the corresponding process: ； wherein denotes the Pearson correlation coefficient between , denotes the mathematical expectation, and both denote a process parameter, denotes the mean value of , denotes the mean value of , denotes the standard deviation of , denotes the standard deviation of ; If greater than a preset correlation threshold, it is determined that there is strong collinearity between and the feature with lower correlation with the photovoltaic performance test index among is eliminated to eliminate feature redundancy. 6.The performance prediction method of a full-process technology of a copper-indium-gallium-selenium solar cell according to claim 5, wherein, In step 4, a prediction model based on a classification boosting tree model is constructed; the prediction model is trained using the training set, and a loss function guided by physical constraints is used for optimization to obtain the trained prediction model; wherein the loss function includes: a prediction error term, a physical mechanism constraint term and a process constraint term, and the expression of the loss function is: ； wherein, represents a loss function, represents a prediction error term, and both represent a weight coefficient, represents a physical mechanism constraint term, represents a process constraint term; Wherein, the expression of the prediction error term is: ； wherein, represents the number of samples, represents the predicted photoelectric conversion efficiency of the th sample, represents the true photoelectric conversion efficiency; Wherein, the physical mechanism constraint term includes a theoretical limit constraint, a current-voltage-fill factor consistency constraint and a band gap-open circuit voltage relationship constraint, and the expression of the physical mechanism constraint term is: ； wherein, denotes a theoretical limit constraint, denotes a maximum, denotes a predicted photoelectric conversion efficiency, denotes a theoretical efficiency upper limit, denotes a current-voltage- fill factor consistency constraint, denotes a model predicted short circuit current density, denotes a model predicted open circuit voltage, denotes a model predicted fill factor, denotes a standard incident light power, denotes a bandgap-open circuit voltage relationship constraint, denotes an electronic charge amount, denotes an empirical voltage loss; Wherein, the expression of the process constraint term is: ； wherein and both represent a weight coefficient, represents a layer thickness rationality constraint, represents a component rationality constraint. 7.The performance prediction method of a full-process technology of a copper-indium-gallium-selenium solar cell according to claim 6, characterized in that, In step 4, when the prediction model is trained using the training set, the adaptive ordered target statistical method based on the Sigmoid function is used to process the category type features in the mixed feature input matrix, and the category type features are converted into numerical type features, and the following relationship exists in the corresponding process: ； wherein, represents the th category feature of the th sample after conversion, represents a weight coefficient, represents a permutation index of the current sample, represents an indicator function, represents the th sample on the th feature, represents the th sample on the th feature, represents a sample index currently undergoing encoding calculation, represents a historical sample index located before the sample in a random permutation, represents an index of a feature, represents a target value of the th sample, represents a sample statistical number located before the th sample in a random permutation and having the same category value, represents a small constant to prevent the denominator from being zero, represents a prior probability, represents a natural constant, represents a center offset parameter of a Sigmoid function, represents a slope adjustment parameter of a Sigmoid function. 8.The performance prediction method of a full-process technology of a copper-indium-gallium-selenium solar cell according to claim 7, characterized in that, In step 5, a game theory-based interpretability analysis method is introduced to analyze the trained prediction model to obtain the marginal contribution of each process parameter to the photovoltaic performance index, specifically including the following sub-steps: A game theory-based interpretability analysis method is introduced to calculate the SHAP value of each process parameter, and the following relationship exists in the corresponding process: ； wherein, represents a feature SHAP value, represents a subset of the set of features represents a factorial, represents a set of all input features, represents a prediction value of the target prediction model after adding the feature to the subset , represents a prediction value of the target prediction model using only the features in the subset . The absolute value of the SHAP value of each process parameter is taken as the marginal contribution of each process parameter to the photovoltaic performance index. 9.The performance prediction method of a full-process technology of a copper-indium-gallium-selenium solar cell according to claim 8, characterized in that, In step 6, based on the marginal contribution, the key process parameters are screened, and the parallel coordinate visualization technology is used to map the distribution trajectory of the high photovoltaic performance sample on the key process parameter axis to identify the densely converging area of the sample trajectory; the densely converging area is determined as the optimal process parameter convergence interval, specifically including the following sub-steps: Based on the size of the marginal contribution of each process parameter to the photovoltaic performance index, each process parameter is sorted in descending order, and the process parameter with a marginal contribution greater than a preset threshold is selected as a key process parameter. The key process parameters are mapped to a two-dimensional plane by using parallel coordinate visualization technology to obtain a key process parameter axis; A target optimal threshold of photoelectric conversion efficiency is set; A sample set whose performance prediction value is higher than the target optimal threshold is extracted, and a dense convergence area of the sample set on the key process parameter axis is identified, and the dense convergence area is determined as an optimal process parameter convergence interval.

10. A performance prediction system for a full process of a copper indium gallium selenide solar cell, characterized by, The system adopts the performance prediction method of the full-process technology of the copper-indium-gallium-selenium solar cell according to any one of claims 1 to 9, and the system comprises: The data management module is configured to: Obtain experimental data of the copper-indium-gallium-selenium solar cell, and perform data cleaning and standardization processing to obtain a standard data set; The data processing module is configured to: Based on the device physics principle of the copper-indium-gallium-selenium solar cell, a physical derived feature set is calculated from the preparation process parameters in the standard data set, the physical derived features and the preparation process parameters are fused to obtain a physical enhanced feature matrix; The correlation between the features in the physical enhanced feature matrix is analyzed to eliminate redundant features with multiple collinearity, and the numerical features and the categorical features are identified to obtain a mixed feature input matrix; the data set based on the mixed feature input matrix is divided into a training set and a test set; The model calculation module is configured to: Construct a prediction model based on a classification boosting tree model, train the prediction model using the training set, and optimize the prediction model using a loss function guided by physical constraints to obtain a trained prediction model; The intelligent analysis module is configured to: Introduce an explainability analysis method based on game theory to analyze the trained prediction model to obtain the marginal contribution of each process parameter to the photovoltaic performance index; Based on the marginal contribution, key process parameters are screened, and the distribution trajectory of high photovoltaic performance samples on the key process parameter axis is mapped by using parallel coordinate visualization technology to identify a dense convergence area of the sample trajectory; and the dense convergence area of the sample trajectory is determined as an optimal process parameter convergence interval.

Images