Battery material assembly methods, apparatus, and computer storage media

Abstract

The application discloses a battery material combination method, device and computer storage medium, relates to the technical field of new energy materials, and comprises the following steps: generating one or more groups of candidate material combinations based on battery material data; extracting attribute features of the candidate material combinations and converting the attribute features into feature vectors; and inputting the feature vectors into a pre-trained prediction model to obtain performance prediction results of the candidate material combinations. The application generates candidate material combinations and uses a prediction model to perform performance prediction on the candidate material combinations, realizes efficient screening and safety performance prediction of battery material combinations, significantly improves the research and development efficiency of battery materials, and also expands the selection range of battery material combinations.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new energy materials, and particularly relates to a battery material combination method, device and computer storage medium. BACKGROUND

[0002] As an emerging energy storage technology, the stability of sodium batteries in practical application is a key factor restricting their widespread application.

[0003] In the design of sodium batteries, the positive electrode material is usually selected from layered oxides, which have high energy density. However, in the process of electrochemical cycling, the layered oxide positive electrode material is prone to irreversible phase transition caused by relative sliding of transition metal layers, resulting in unstable battery cycling. The negative electrode material generally uses hard carbon material with high sodium storage capacity and good cycle stability. However, the hard carbon material may produce a large volume expansion during charging and discharging, thereby affecting the performance and service life of the sodium battery.

[0004] Therefore, the material combination used in sodium batteries will directly affect its performance and safety. At present, the evaluation of battery material combination mainly relies on laboratory tests and experience-based design principles. This method requires long-term experimental research on various material combinations to evaluate the stability and safety of various material combinations in the battery cycling process. However, this method requires a large amount of time and resources, and cannot cover all possible material combinations, thereby limiting the selection range of battery materials. SUMMARY

[0005] The main purpose of the present application is to provide a battery material combination method, device and computer storage medium, which aims to solve the technical problems of low evaluation efficiency and limited combination coverage of battery material combination, resulting in limited selection of battery materials.

[0006] To achieve the above-mentioned purpose, the battery material combination method provided by the embodiments of the present application comprises:

[0007] Based on the battery material data, one or more groups of candidate material combinations are generated;

[0008] The attribute features of the candidate material combinations are extracted, and the attribute features are converted into feature vectors;

[0009] The feature vectors are input into a pre-trained prediction model to obtain the performance prediction results of the candidate material combinations.

[0010] In an embodiment, the step of generating one or more groups of candidate material combinations based on the battery material data comprises:

[0011] determining interaction rules of the material combinations, the interaction rules being used to guide pairing of the material combinations;

[0012] obtaining a candidate list of the material combinations based on the interaction rules;

[0013] screening the candidate list of the material combinations according to preset material attribute standards, and determining the candidate material combinations.

[0014] In an embodiment, the step of extracting attribute features of the candidate material combinations and converting the attribute features into feature vectors comprises:

[0015] obtaining material attributes of each battery material in the candidate material combinations and attribute values corresponding to the material attributes;

[0016] mapping the attribute values of each battery material into a group of feature vectors, each attribute value corresponding to an element in the feature vectors.

[0017] In an embodiment, before the step of inputting the feature vectors into a pre-trained prediction model to obtain performance prediction results of the candidate material combinations, the method comprises:

[0018] obtaining safety performance data corresponding to the material attributes of the battery materials, the safety performance data including impact test results of the battery materials under external impact conditions;

[0019] constructing a battery material dataset according to the material attributes and the safety performance data;

[0020] training a prediction model based on the battery material dataset;

[0021] performing safety performance prediction on the candidate material combinations by using the trained prediction model, and outputting performance prediction results of the candidate material combinations.

[0022] In an embodiment, before the step of training the prediction model based on the battery material dataset, the method comprises:

[0023] dividing the battery material dataset into subsets of equal size, each subset containing the same number of data;

[0024] In each iteration training, a different subset is selected as a validation set and the remaining subsets are used as training sets, the prediction model is iteratively trained, and the prediction error is calculated using the validation set.

[0025] In an embodiment, after the step of iteratively training the prediction model and calculating the prediction error using the validation set, the method further comprises:

[0026] after each iteration training, updating the hyperparameter configuration of the prediction model based on the prediction error;

[0027] repeating the steps of selecting a different subset as the validation set and the remaining subset as the training set, performing iteration training on the training set, and calculating the prediction error using the validation set until the prediction error is reduced to a preset threshold, using the prediction model with the updated hyperparameter configuration.

[0028] In an embodiment, after the step of inputting the feature vector into the pre-trained prediction model to obtain the performance prediction result of the candidate material combination, the method further comprises:

[0029] determining a confidence interval of the safety performance of the battery material according to historical safety performance data of the battery material;

[0030] comparing the performance prediction result of the candidate material combination with the confidence interval;

[0031] determining a safety level of the candidate material combination according to the comparison result.

[0032] In an embodiment, after the step of inputting the feature vector into the pre-trained prediction model to obtain the performance prediction result of the candidate material combination, the method further comprises:

[0033] determining a material attribute that needs to be optimized according to the performance prediction result, and regenerating a new candidate material combination;

[0034] inputting the feature vector of the new candidate material combination into the prediction model to obtain a new performance prediction result;

[0035] performing iteration adjustment on the new candidate material combination based on the new performance prediction result until a preset performance target is reached or the adjustment of the candidate material combination is completed.

[0036] Embodiments of the present application also provide a battery material combination device, which comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the battery material combination method as described above.

[0037] Embodiments of the present application also provide a computer storage medium, which is a computer readable storage medium, and has a computer program stored thereon, the computer program being executable by a processor to implement the steps of the battery material combination method as described above.

[0038] The battery material combination method disclosed by the embodiments of the present application comprises the following steps: generating one or more groups of candidate material combinations based on battery material data; extracting attribute features of the candidate material combinations and converting the attribute features into feature vectors; and inputting the feature vectors into a pre-trained prediction model to obtain performance prediction results of the candidate material combinations. The embodiments of the present application generate candidate material combinations and use a prediction model to predict the performance of the candidate material combinations, thereby realizing efficient screening and safety performance prediction of battery material combinations, significantly improving the research and development efficiency of battery materials, and expanding the selection range of battery material combinations. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 FIG. 1 is a flowchart of a first embodiment of the battery material combination method according to the embodiments of the present application;

[0040] Figure 2 FIG. 2 is a flowchart of a second embodiment of the battery material combination method according to the embodiments of the present application;

[0041] Figure 3 FIG. 3 is a flowchart of a third embodiment of the battery material combination method according to the embodiments of the present application;

[0042] Figure 4 FIG. 4 is a flowchart of a fourth embodiment of the battery material combination method according to the embodiments of the present application;

[0043] Figure 5 FIG. 5 is a flowchart of a fifth embodiment of the battery material combination method according to the embodiments of the present application;

[0044] Figure 6 FIG. 6 is a structural diagram of the battery material combination device according to the embodiments of the present application.

[0045] The object, function, feature and advantage of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are merely intended to explain the present application and are not intended to limit the present application.

[0047] Sodium batteries, as an emerging energy storage technology, have attracted much attention due to their advantages in energy density, cost-effectiveness, and resource abundance. However, the stability and reliability of sodium batteries in practical applications remain a key factor limiting their widespread use. The performance and safety of sodium batteries largely depend on the material combination used, and current evaluation of battery material combinations mainly relies on laboratory tests and empirical design principles. This evaluation method requires long-term experimental research on various material combinations to assess their stability and safety during battery use. However, this method not only requires a large amount of time and resources, but also is difficult to cover all possible material combinations, thereby limiting the selection range of battery materials.

[0048] To solve the above-mentioned defects in the related art, the embodiment of the present application proposes a battery material combination method, which generates one or more groups of candidate material combinations based on battery material data; extracts the attribute features of the candidate material combinations and converts the attribute features into feature vectors; inputs the feature vectors into a pre-trained prediction model to obtain the performance prediction results of the candidate material combinations. The present application generates candidate material combinations and uses a prediction model to predict the performance of the candidate material combinations, realizes efficient screening and safety performance prediction of battery material combinations, significantly improves the research and development efficiency of battery materials, and also expands the selection range of battery material combinations.

[0049] For ease of understanding, the technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.

[0050] The battery material combination method of the first embodiment proposed in the present application, please refer to Figure 1 , which includes steps S10~S30:

[0051] Step S10: Based on battery material data, generate one or more groups of candidate material combinations.

[0052] In this embodiment, first, collect and organize existing battery material data, which includes positive electrode materials, negative electrode materials, electrolytes, and separators, etc. The collected battery material data will be used as the basis for generating candidate material combinations. Then use algorithms to generate random candidate material combinations.

[0053] Optionally, use a crawler tool to automatically capture battery material data from academic databases, material performance databases (Material Performance Database) on the Internet, etc. The crawler tool can automatically access web pages and extract the required data according to the pre-set crawling rules and keywords, and save them to local data.

[0054] Exemplarily, the Materials Project, a database of material properties, was accessed using a crawler tool, and all data entries related to sodium battery cathode materials were retrieved through an API interface, including the chemical composition, crystal structure, and electrochemical properties of the cathode materials. Subsequently, the crawler tool scraped the abstracts and citation information of research papers on sodium-ion batteries published in recent years based on search conditions such as "since 2015," "Sodium-ion battery," and "article." For electrolyte and separator materials, the crawler tool accessed the ScienceDirect database and the Web of Science (WoS) database, respectively, to extract experimental data and performance evaluations related to electrolyte and separator materials.

[0055] It should be noted that the ScienceDirect database is a comprehensive full-text literature database, and the WoS database is a multidisciplinary research achievement citation database.

[0056] Alternatively, battery material data can be collected through experimental data collection and integration. By conducting laboratory tests, the material properties of battery materials are directly measured, or by cooperating with research institutions, experimental data of battery materials are shared. After conducting measurement experiments of battery materials, record the experimental conditions and experimental results, including structural analysis of battery materials, electrochemical performance tests, etc. Then store and manage the experimental data of battery materials.

[0057] Exemplarily, X-ray Diffraction Analysis (XRD) analysis was performed on a certain cathode material to determine its crystal structure. Through Scanning Electron Microscopy (SEM) imaging, the microstructure of the cathode material was obtained. Through Electrochemical Impedance Spectroscopy (EIS) testing, the charge transport performance of the cathode material can be evaluated. Through charge and discharge cycle testing, the actual energy density and cycle life of the cathode material can be measured. After recording the experimental data of the cathode material, the experimental data of the battery material is stored and managed through the Laboratory Information Management System (LIMS) of the laboratory.

[0058] Optionally, a genetic algorithm (GA) is used to generate one or more sets of candidate material combinations. First, a fitness function is defined to evaluate the performance of each material combination. In this embodiment, key performance indicators of battery materials such as energy density, cycle life, etc. can be used as input parameters of the fitness function. By calculating the performance of each material combination on these performance indicators, a fitness value is assigned to each material combination.

[0059] Then, a population of randomly generated material combinations is initialized. Through selection, crossover, and mutation operations on these material combinations, a new generation of population is generated. Specifically, in the selection operation, a probabilistic selection is performed based on the fitness values of the material combinations, so that material combinations with higher fitness values have a higher probability of being selected. In the crossover operation, parts of the genes of two selected material combinations are exchanged to generate new material combinations. In the mutation operation, some genes of the material combinations are randomly changed to introduce new gene mutations.

[0060] By continuously iterating the above process, material combinations with higher fitness values are gradually found. A termination condition can be set, such as reaching a pre-set maximum number of iterations or finding a solution (i.e., a material combination) that meets the requirements. The final material combination obtained is used as a candidate material combination. The method of generating candidate material combinations using a genetic algorithm can quickly find potential optimal solutions in a large search space, improving the efficiency and accuracy of battery design.

[0061] Optionally, a particle swarm optimization (PSO) algorithm is used to generate one or more sets of candidate material combinations. In this embodiment, key performance indicators of battery materials such as energy density, cycle life, etc. are used as fitness function inputs to evaluate the performance of each material combination. Each particle represents a candidate material combination in the search space and has a position and a velocity, where the position corresponds to the specific parameters of the material combination and the velocity determines the direction and step size of the particle in the search space.

[0062] At initialization, a group of particles is randomly generated, each representing a possible material combination solution. In each iteration, the particle updates its own velocity and position by tracking its own historical best position and the best position of the entire group. When updating the velocity, the experience of the particle itself and the experience of neighboring particles are considered, so that the particle can move towards a better solution.

[0063] As the iteration proceeds, the swarm gradually converges to the optimal region in the search space. After each iteration, the fitness value of each particle is recalculated, and the global and individual optimal positions are updated according to the fitness value. This process continues until a termination condition is met, such as reaching a preset maximum number of iterations, the fitness value exceeding a certain threshold, or the improvement of the swarm's best position no longer being significant. Finally, a set or multiple sets of candidate material combinations with higher fitness values are output according to the positions of the particles.

[0064] Step S20: Extract the attribute features of the candidate material combinations and convert the attribute features into feature vectors.

[0065] In this embodiment, the attribute features of the candidate material combinations are a set of attributes that have a decisive impact on the material combinations. For example, for the positive electrode material, the main concerns are its crystal structure, electrochemical activity, ion diffusion rate, etc.; for the negative electrode material, the main concerns are its specific capacity, electronic conductivity, stability, etc.

[0066] Optionally, each material attribute of the candidate material combinations is directly mapped to a dimension of the feature vector. First, each material attribute is quantized to ensure that its numerical value can be processed by the model.

[0067] Specifically, the material attributes of each battery material in the candidate material combination are obtained, as well as the attribute values corresponding to the material attributes. Then, the attribute values of each battery material are mapped to a set of feature vectors, with each attribute value corresponding to an element in the feature vector.

[0068] For example, the crystal structure of the positive electrode material can be quantified by its lattice parameters, the electrochemical activity can be represented by its open-circuit voltage, and the ion diffusion rate can be quantified by its electrical conductivity. The specific capacity of the negative electrode material can be quantified by its theoretical capacity, the electronic conductivity can be measured by its electrical conductivity, and the stability can be evaluated by the results of the thermal stability test. Then, the quantized attribute values are arranged in a certain order to form a feature vector. For example, a certain candidate material combination consists of two positive electrode materials and three negative electrode materials, so its feature vector contains at least five quantized values of material attributes, with each attribute value corresponding to a dimension of the feature vector.

[0069] Optionally, the attribute features are reduced in dimension using Principal Component Analysis (PCA) technique. In this embodiment, first, the material attribute feature data of all candidate material combinations are collected to form a feature matrix. Then, the feature matrix is decomposed using PCA algorithm to extract several principal components that can explain most of the variability in the material attribute feature data. Each principal component is a projection of the original feature vector in a new coordinate space, and the first several principal components are selected according to their contribution rates and combined into new feature vectors.

[0070] For example, assume that the data of 100 candidate material combinations are collected, each of which is described by 10 different attribute features, such as the crystal structure parameters, electrochemical activity, ion diffusion rate of the positive electrode material, and specific capacity, electronic conductivity, stability of the negative electrode material, etc.

[0071] The data of these candidate material combinations are organized into a 100-row 10-column feature matrix, where each row represents a candidate material combination and each column represents an attribute feature. A PCA algorithm is applied to obtain a principal component analysis result, which shows that the first three principal components can explain more than 85% of the variability in the data. Therefore, the first three principal components are selected as new feature vectors, each of which is a projection of the original 10-dimensional feature vector in a new three-dimensional space. In a specific implementation, first, the feature matrix is standardized to ensure that the mean of each attribute feature is 0 and the standard deviation is 1. Then, the covariance matrix of the feature matrix is calculated using the PCA algorithm, and the eigenvalues and eigenvectors of the covariance matrix are found. According to the contribution rates of the eigenvalues, the eigenvectors corresponding to the first three largest eigenvalues are selected, which are the new principal components. Finally, the original feature matrix is multiplied by the eigenvectors of the three principal components to obtain a new 100-row 3-column feature matrix, which is the set of reduced feature vectors.

[0072] Optionally, the attribute features are processed using feature engineering, which includes feature construction, feature selection, and feature transformation.

[0073] In the feature construction stage, new features can be created by calculating the ratios, differences, or interactions between material attributes. For example, the ratio of the electrochemical activity of the positive electrode material to its ion diffusion rate may have an important impact on the battery performance, and this ratio can be used as a new feature.

[0074] In the feature selection stage, statistical methods or model selection methods are used to determine which features are most useful for predicting battery performance. For example, Recursive Feature Elimination (RFE) can be used to select the most influential features.

[0075] In the feature transformation stage, the selected attribute features are subjected to appropriate mathematical transformation, such as standardization or normalization, to eliminate the influence of the dimension between different attribute features. After the three steps of feature engineering are completed, the transformed feature values are combined into a feature vector.

[0076] Step S30: inputting the feature vector into a pre-trained prediction model to obtain a performance prediction result of the candidate material combination.

[0077] In this embodiment, a machine learning model or a deep learning model can be used for training, such as a support vector machine (SVM), a convolutional neural network (CNN), a long short-term memory network (LSTM), or a deep neural network (DNN), to establish a prediction model for predicting the safety performance of a material combination.

[0078] Optionally, an SVM model is used to construct a prediction model for predicting the safety performance of a material combination. In this embodiment, the optimal model parameters, including the kernel function type, the penalty parameter, and the kernel function parameter, are first determined by techniques such as grid search and cross-validation. Then, the SVM model is trained using these model parameters until the SVM model achieves satisfactory accuracy on the training set, and the prediction model training is completed. After the training is completed, the feature vector of the candidate material combination is input into the prediction model, and the prediction model outputs the performance prediction result of the candidate material combination.

[0079] For example, a radial basis function (RBF) is selected as the kernel function, and the optimal penalty parameter C and kernel function parameter γ are found in the parameter space by grid search. After multiple iterations and cross-validation, C = 10 and γ = 0.1 are determined as the optimal parameters. Subsequently, the optimal parameters are used to train the SVM model on a material combination dataset containing 100 samples. After about 20 iterations, the accuracy of the SVM model on the training set reaches more than 95%, indicating that the prediction model training is completed. Finally, the feature vectors of 100 candidate material combinations are input into the trained prediction model to obtain the performance prediction results of the 100 candidate material combinations.

[0080] Optionally, a CNN model is used to build a prediction model for predicting the safety performance of the material combination. In this embodiment, a multi-layer convolutional neural network is designed, which includes multiple convolutional layers and pooling layers to extract complex patterns and correlations in the feature vectors. At the end of the neural network, a fully connected layer and an output layer are connected to perform performance prediction. During the training process of the prediction model, the network weights are optimized using the backpropagation algorithm and the gradient descent method until the loss function of the prediction model on the validation set reaches a minimum. The trained CNN model receives the feature vectors of the candidate material combination and predicts the performance prediction result of the candidate material combination through its deep network structure.

[0081] For example, a CNN model with three convolutional layers and two pooling layers is constructed, and a ReLU (Rectified Linear Unit) activation function is added after each convolutional layer to introduce nonlinearity. At the end of the neural network, two fully connected layers are added, the first fully connected layer has 128 neurons, and the second fully connected layer directly outputs the performance prediction result. During the model training phase, the Adam (Adaptive Moment Estimation) optimizer and the cross-entropy loss function are used, and 20 cycles of training are performed on a dataset containing 100 samples. After training, the loss of the CNN model on the validation set is reduced to below 0.02, indicating that the prediction model trained based on the CNN model has good prediction ability. Subsequently, the reduced feature vectors are input into the prediction model to obtain the performance prediction data of the 100 candidate material combinations.

[0082] It should be noted that the Adam optimizer is a high-efficiency stochastic optimization algorithm used in deep learning, which can adaptively adjust the learning rate for different parameters.

[0083] Please refer to Figure 2 The battery material combination method of the second embodiment proposed in this application can further include the following steps S110-S130 in step S10:

[0084] Step S110: Determine the interaction rule of the material combination, which is used to guide the pairing of the material combination.

[0085] In this embodiment, the interaction rule defines the possible interaction mechanisms between different battery materials, including but not limited to chemical compatibility, complementary electrochemical performance, and matching degree of physical properties. The interaction rule serves as a guiding principle in the material combination pairing process, ensuring that the generated material combination has a synergistic effect in theory, thereby improving the quality and efficiency of material combination prediction, and also improving the overall performance of the material combination.

[0086] Step S120: obtaining a candidate list of material combinations based on the interaction rules.

[0087] In this embodiment, the candidate list of material combinations contains a plurality of pairing schemes of material combinations screened according to the interaction rules, and each pairing scheme is likely to be a potential material combination for forming an efficient battery material. The generation of the candidate list considers all possible pairs of battery materials and their interactions.

[0088] Step S130: screening the candidate list of material combinations according to a preset material property standard to determine the candidate material combination.

[0089] It should be noted that the material property standard can include the electrical conductivity, ion diffusion rate, stability and cost of the battery material. By evaluating the material properties of each material combination in the candidate list, the material combination that meets the preset standard can be screened to determine the final candidate material combination.

[0090] Please refer to Figure 3 The battery material combination method of the third embodiment of the present application can include the following steps S310-S340 before step S30:

[0091] Step S310: obtaining safety performance data corresponding to the material properties of the battery material, the safety performance data including impact test results of the battery material under external impact conditions.

[0092] In this embodiment, the material properties of the battery material include physical property data and chemical property data. The physical property data includes density, electrical conductivity, ion diffusion rate, etc. The chemical property data includes capacity, cycle life, rate performance, etc. The safety performance data corresponding to these material properties is obtained, in particular, the impact test results of the battery material under external impact conditions. The impact test results are used to evaluate the safety response of the battery material when subjected to mechanical impact, puncture, extrusion, drop or other forms of external force, such as whether thermal runaway, explosion or leakage occurs, etc.

[0093] Specifically, before obtaining the safety performance data corresponding to the material properties of the battery material, impact tests are performed on the battery material and the impact test results are recorded. Then, according to the impact test results, the safety performance data of the battery material is determined.

[0094] Exemplarily, the battery material is subjected to impact tests, such as by using a pendulum of a specified weight to impact the battery material sample at different speeds, recording the deformation of the battery material sample after impact; or using a sharp object to pierce the battery material sample, recording the safety response during the piercing process; or simulating the performance of the battery material sample when subjected to extrusion and falling, etc. Subsequently, the results of the corresponding impact tests are recorded, including the morphological changes of the battery material sample after being subjected to impact, the temperature rise, and whether the safety performance data such as thermal runaway, explosion or leakage occurs.

[0095] After completing the impact test, the safety performance data of the battery material is determined according to the impact test results. For example, the brittle fracture of a certain battery material in the mechanical impact test is related to its low density and high electrical conductivity, and the material prone to thermal runaway in the piercing test usually has a low ion diffusion rate, and a certain positive electrode material shows good safety in the drop test, and its chemical property data shows high rate performance and cycle stability, etc.

[0096] Step S320: constructing a battery material dataset according to the material attributes and the safety performance data.

[0097] Optionally, key attributes are selected from the material attributes of the battery material, and attribute features of these key attributes are extracted, which will be used as input of the prediction model to predict the safety performance of the battery material. Then the safety performance data obtained from the impact test results are used as labels corresponding to the attribute features of the key attributes to form a battery material dataset for training. The battery material dataset contains the attribute features of each battery material and the labels of the corresponding safety performance data.

[0098] Specifically, first, the material attributes and safety performance data are preprocessed, including data cleaning to remove outliers and missing values, ensuring the quality and integrity of the data; standardizing or normalizing the data so that different dimension material attributes can be compared on the same scale; the data can also be transformed, such as linearizing the non-linear relationship, or using logarithmic transformation and other methods to improve the distribution characteristics of the data, etc. When processing the safety performance data, the classification labels need to be encoded, such as using One-Hot Encoding to convert the classification data into a numerical form suitable for the model. Then the impact test results are associated with the material attributes of the corresponding battery material.

[0099] Exemplarily, it is assumed that a set of material attributes and safety performance data of battery materials are received, including density, electrical conductivity, ion diffusion rate, capacity, cycle life, etc. material attributes, and impact test results, thermal runaway risk, etc. safety performance data.

[0100] First, the data is cleaned, for example, the boxplot method is used to detect an abnormal value in the conductivity data, and it is automatically excluded; at the same time, the interpolation method is used to automatically fill in the missing values in the capacity data. Then the data is standardized, the material properties such as density, conductivity, ion diffusivity, etc. are scaled to the range [0, 1] by the min-max standardization method; the material properties such as capacity, cycle life, etc. are converted to standard normal distribution using Z-score standardization method. Then, the nonlinear relationship between capacity, cycle life, etc. is converted to a linear relationship by logarithmic transformation, which is convenient for model training and prediction. Finally, the one-hot encoding method is used to convert the impact test results, thermal runaway risk, etc. classification labels into binary vectors, each category corresponds to a binary bit.

[0101] Exemplarily, after completing the preprocessing operation, the preprocessed material properties are associated with the corresponding preprocessed safety performance data to form a battery material dataset. For example, for a certain battery material sample, its ion diffusivity is associated with the thermal runaway risk in the impact test result to form a data point containing material properties and safety performance data.

[0102] Step S330: based on the battery material dataset, a prediction model is trained.

[0103] It should be noted that in terms of model selection, various deep learning architectures can be used, such as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory networks (LSTM) or Deep Neural Networks (DNN), etc. These network structures can learn complex features and nonlinear relationships from battery material data.

[0104] Exemplarily, according to the characteristics of the battery material data, a deep neural network with multiple hidden layers is selected as the base model, because the deep neural network can effectively process high-dimensional data and capture nonlinear features in the data.

[0105] In the model construction process, the structure of the deep neural network is first determined, including the number of nodes in the input layer, hidden layer, and output layer. The number of input layer nodes matches the material attribute dimension of the battery material. The number of nodes in each hidden layer is determined according to an empirical formula or through experiments to balance the expression ability and computational complexity of the model. The design of the output layer depends on the type of safety performance data. If it is a classification problem, the number of nodes in the output layer is equal to the number of categories, and the softmax function is used to output the probability distribution. If it is a regression problem, the output layer has only one node, and a linear activation function is used.

[0106] In this embodiment, a deep neural network model is used to train the material attributes and safety performance data of the battery material to construct a prediction model that can predict the safety performance of the battery material combination.

[0107] Optionally, the battery material dataset is divided into a training set and a test set. The training set is used for training the prediction model, and the test set is used to evaluate the generalization ability of the prediction model. During the training process of the prediction model, the parameter settings of the prediction model are adjusted on the training set to optimize the performance of the prediction model. Subsequently, the test set is used to verify the generalization ability of the prediction model, and the verification result is obtained. The verification result is evaluated by calculating the performance indicators of the prediction model, including accuracy, recall, F1 score, mean square error, or confusion matrix, etc.

[0108] It can be understood that the test set does not participate in the training of the prediction model, so the test set can provide the performance of the prediction model on unknown data, i.e., the generalization ability of the prediction model.

[0109] Specifically, during the dataset division process, the samples in the battery material dataset are allocated to the training set and the test set according to a predetermined proportion. Generally, the training set contains most of the sample data, for example, 70%-80% of the sample data is used as the training set, and the remaining 20%-30% of the sample data constitutes the test set. This division can ensure that the prediction model can fully learn the complex relationship between the material attributes and safety performance of the battery material during the training process, and at the same time, the prediction ability of the prediction model can be verified on the independent test set.

[0110] On the training set, the prediction model will learn the mapping relationship from the feature data to the safety performance label by adjusting the internal parameters. This learning process involves multiple iterations, and the prediction model gradually optimizes its prediction accuracy in each iteration. After training is completed, the test set is used to evaluate and verify the performance of the prediction model.

[0111] To evaluate the performance of the prediction model, the performance indicator data of the prediction model will be calculated, including accuracy, recall rate, etc. By calculating the performance indicator data, the comprehensive performance of the prediction model on the test set can be obtained, so as to determine whether the prediction model has reached the expected performance level. If the prediction model performs well on the test set, it means that the prediction model has good generalization ability and can be used for actual battery material screening and risk assessment. If the prediction model performs poorly on the test set, further adjustment of the prediction model parameters is needed, and the iterative training process is re-performed to improve its generalization ability.

[0112] It should be noted that the accuracy reflects the proportion of samples that are actually positive among those predicted to be positive by the prediction model.

[0113] For example, assume there is a dataset containing 100 battery material samples, of which 70% are divided into the training set and the remaining 30% are used as the test set, i.e., the training set contains 70 samples and the test set contains 30 samples.

[0114] In the iterative training on the training set, the prediction model learns the mapping relationship from the feature data to the safety performance label by adjusting the internal parameters.

[0115] After training is completed, the test set is used to evaluate and verify the performance of the prediction model, and the accuracy of the prediction model is calculated. For example, on the test set, the prediction model predicts the safety performance of 30 samples, of which 26 are predicted to be positive and 4 are predicted to be negative. Among the 26 samples predicted to be positive, 24 are actually positive, so the accuracy is 24 / 26=92.3%, indicating that the prediction model has good generalization ability and can be used for actual battery material screening and risk assessment.

[0116] Optionally, the cross-validation method is adopted, and the battery material dataset is divided into several equal-sized subsets, each containing the same number of data. In each iteration of training, a different subset is selected as the validation set, and the remaining subsets are used as the training set to train the prediction model, and the prediction error is calculated using the validation set.

[0117] It should be noted that the battery material dataset is divided into several equal-sized subsets to ensure that each subset can represent the characteristics of the overall battery material dataset, so that the prediction model can learn comprehensive and balanced features in the subsequent prediction model training and verification process.

[0118] Specifically, the training set is divided into K subsets, and in each iteration training, one subset is selected as the validation set, and the remaining K-1 subsets are combined as the training set. In each iteration, the prediction model is trained on the new training set and the prediction error is calculated on the selected validation set, including comparing the difference between the prediction model prediction result and the actual safety performance data label. The process of iterative training will continue until each subset has been used as a validation set once. Through cross-validation, the prediction model is tested on multiple different training combinations, which helps to more accurately evaluate the generalization ability of the prediction model. After each iteration, the prediction error of the prediction model is recorded, which will be used to adjust the hyperparameter settings of the prediction model.

[0119] Optionally, after the prediction model is iteratively trained and the prediction error is calculated using the validation set, the hyperparameter configuration of the prediction model is updated based on the change trend of the prediction error after each iteration to reduce the risk of overfitting or underfitting and improve the prediction accuracy of the prediction model. Then, using the prediction model with updated hyperparameter configuration, the steps of selecting a different subset as the validation set and the remaining subsets as the training set, iteratively training the prediction model, and calculating the prediction error using the validation set are repeated until the prediction error is reduced to a preset threshold or the prediction error is reduced to below the preset threshold or a predetermined number of iterations is reached.

[0120] It should be noted that the hyperparameter configuration refers to the parameters that can be adjusted during the training process of the prediction model, such as learning rate, hidden layer node number, batch size, regularization coefficient, etc. By analyzing the prediction error, it can be determined which hyperparameters have a significant impact on the performance of the prediction model, and then the hyperparameter configuration is adjusted to optimize the performance of the prediction model.

[0121] In this embodiment, by selecting different subsets as the validation set in each iteration training, it can be ensured that the prediction model is trained and validated on different data combinations, thereby improving the generalization ability of the prediction model. By iteratively training the training set and calculating the prediction error using the validation set, the performance of the prediction model on independent data can be monitored in real time.

[0122] For example, assume there is a battery material dataset containing 100 battery material samples, which is divided into 5 subsets, each containing 20 sample data. In each iteration of training, a different subset is selected as the validation set, and the remaining subsets are combined as the training set. For example, the first iteration of training selects the first subset as the validation set 1, and the remaining 4 subsets are combined as the training set 1. The prediction model is trained on the training set 1 and calculates the prediction error on the validation set 1. The second iteration of training is then performed, selecting the second subset as the validation set 2, and the remaining 4 subsets are combined as the training set 2, and the training continues until all subsets have been used as a validation set once.

[0123] Through cross-validation, the prediction model is trained on 5 different combinations. After each iteration, the prediction error of the prediction model is recorded, which will be used to adjust the hyperparameter settings of the prediction model. By adjusting the hyperparameters of the prediction model, the prediction model can minimize the training error and optimize the performance of the prediction model, thereby ensuring the reliability and accuracy of the prediction model in actual application.

[0124] Step S340: Using the trained prediction model, the safety performance of the candidate material combination is predicted, and the performance prediction result of the candidate material combination is output.

[0125] It should be noted that the candidate material combination refers to a battery material combination that has not been experimentally verified. Since the experimental verification process is time-consuming and costly, the prediction model can predict the safety performance of these material combinations to screen out potential high-performance material combinations, thereby guiding researchers to focus resources on those most likely to succeed.

[0126] Specifically, the material attributes of the candidate material combination are preprocessed to ensure the quality and consistency of the model input data, improving the accuracy and reliability of the prediction model. Then the feature vector of the preprocessed candidate material combination is extracted and input into the trained prediction model to obtain the performance prediction result of the candidate material combination.

[0127] For example, a set of candidate material combinations that have completed data preprocessing operations are selected for safety performance prediction. Assume that the candidate material combination includes a new positive electrode material and an existing negative electrode material, and the material attributes include: density of 0.95 g / cm³, electrical conductivity of 150 mS / cm, and ion diffusion rate of 1.2 x 10 -4 cm 2 / s. The material attributes of the battery material combination and the safety performance data corresponding to the material attributes are extracted to obtain the feature vector, which is input into the prediction model. The prediction model will output the safety performance prediction result of the candidate material combination.

[0128] Referring to Figure 4 The battery material combination method of the fourth embodiment further includes the following steps S350-S370 after step S30:

[0129] Step S350: Determine the confidence interval of the safety performance of the battery material according to the historical safety performance data of the battery material.

[0130] It should be noted that the confidence interval is a statistical tool used to estimate the reliability of performance prediction results. Specifically, the confidence interval indicates the interval in which the population parameter (such as the mean or proportion, etc.) may fall under a certain confidence level (usually 95%). In this embodiment, the confidence interval is calculated based on the historical safety performance data, indicating that there is 95% confidence that the safety performance indicators (such as thermal stability, cycle life, safety test results, etc.) of the battery material will fall within this interval.

[0131] Step S360: Compare the performance prediction results of the candidate material combination with the confidence interval.

[0132] Step S370: Determine the safety level of the candidate material combination according to the comparison result.

[0133] For example, historical safety performance data of five battery materials is selected, including impact resistance, thermal stability, and electrochemical stability indicators. Taking impact resistance as an example, the historical safety performance data shows that the average value is 85 Newton, and the standard deviation is 5 Newton, and accordingly the 95% confidence interval is calculated as [75.4, 94.6] Newton. The 95% confidence intervals of the thermal stability and electrochemical stability indicators are [300, 350] degrees Celsius and [0.95, 1.05], respectively.

[0134] In step S360, a trained prediction model is used to perform performance prediction for a set of candidate material combinations. Assuming that the candidate combination consists of materials A, B, and C, the prediction model predicts that the impact resistance of the candidate material combination is 80 Newton, the thermal stability is 320 degrees Celsius, and the electrochemical stability is 1.0. Comparing these predicted values with the previously calculated confidence intervals, the results show that the predicted value of impact resistance 80 Newton is within the confidence interval [75.4, 94.6] Newton, the predicted value of thermal stability 320 degrees Celsius is within the confidence interval [300, 350] degrees Celsius, and the predicted value of electrochemical stability 1.0 is equal to the lower limit of the confidence interval.

[0135] According to the comparison result, the safety level of the candidate material combination A-B-C is determined. Since all the predicted performance values are within the corresponding confidence intervals, the candidate material combination is classified as high safety level. This indicates that according to the historical safety performance data and the prediction of the prediction model, the candidate material combination has high safety under extreme conditions and is suitable for further use in battery research and production.

[0136] Please refer to Figure 5 The battery material combination method of the fifth embodiment further includes the following steps S380-S382 after step S30.

[0137] Step S380: According to the performance prediction result, determine the material properties that need to be optimized, and generate a new candidate material combination.

[0138] In this embodiment, statistical analysis is performed on the performance prediction results output by the prediction model. By calculating the correlation coefficient between each material property and the target safety performance indicator, it is identified which material properties are most relevant to the improvement or decline of safety performance. For example, if it is found that the cycle stability of the battery is highly correlated with the crystallinity of a certain material, then the crystallinity is the key property that needs to be optimized.

[0139] Optionally, the interaction rules of the material combination can be adjusted based on the correlation coefficient between each material property and the target performance indicator to optimize the random generation of the material combination.

[0140] Optionally, Pearson correlation coefficient is used to analyze the relationship between each material property and the safety performance indicator. For each material property, calculate its Pearson correlation coefficient with the battery cycle stability or other safety performance indicators. Sort the calculated correlation coefficients to find the top few material properties that are most relevant to the safety performance indicators. Set optimization goals for the top-ranked material properties, such as increasing crystallinity to enhance cycle stability. Finally, adjust the range or property value of these material properties according to the optimization goal to generate a new candidate material combination.

[0141] Optionally, multivariate regression analysis is used to identify key material properties that affect safety performance. A multivariate linear regression model is used to analyze the relationship between all material properties and the safety performance indicator, and a regression equation is established. Through the coefficient size and significance level in the regression equation, the material properties that have the greatest impact on safety performance are identified. Select the top few properties with the largest coefficients and significance as the optimization focus. Use the Design of Experiments (DOE) method to adjust different levels of these key material properties and generate a new candidate material combination.

[0142] Step S381: inputting the feature vector of the new candidate material combination into the prediction model to obtain a new performance prediction result.

[0143] Step S382: iteratively adjusting the new candidate material combination based on the new performance prediction result until a preset performance target is reached or the adjustment of the candidate material combination is completed.

[0144] In this embodiment, a performance target threshold is first set to define the acceptable safety performance range of battery materials. Then, according to the gap between the prediction result and the target safety performance indicator, the key attributes in the candidate material combination are adjusted. This adjustment process includes increasing or decreasing the content of a specific battery material, changing the processing conditions of the battery material, or adjusting the combination of battery materials, etc., to optimize the overall performance of the battery. Then, iterative optimization is performed, the material attributes are adjusted according to the results of the last iteration, new candidate material combinations are generated, and the feature vectors of these combinations are input into the prediction model again. Until the design target is reached (i.e., the performance target threshold is reached), for example, the energy density is maximized while ensuring the safety of the material structure under various test conditions, then the potential high-performance battery material combination is output.

[0145] The battery material combination method of the sixth embodiment of the present application further includes, after step S30:

[0146] Based on the optimized candidate material combination, finite element analysis (FEA) is performed on the battery design. Finite element analysis involves dividing the structural model of the candidate material combination into a finite number of small elements, each element having certain geometric and physical properties. By applying external forces to these elements, i.e., performing impact tests, and then calculating the stress and deformation of each element, the overall response of the battery structure based on the candidate material combination under specific impact or pressure can be simulated. During stress analysis, the stress distribution in the battery design and the possible damage modes, such as the initiation and propagation of cracks, are focused on.

[0147] Then, computer vision technology is used to extract key information from the FEA simulation results, including identifying and quantifying stress concentration areas and potential weaknesses in the battery structure. Among them, computer vision technology can automatically identify key features in the simulation results through image processing algorithms, reducing the dependence on manual analysis.

[0148] Finally, an interactive visualization tool is developed to graphically present the FEA results, converting complex stress data and deformation patterns into intuitive images, so that the behavior of the battery structure under impact based on the candidate material combination can be understood and analyzed in depth, so as to identify potential problems existing in the battery design based on the candidate material combination, and accordingly adjust the candidate material combination to optimize the structural strength and safety of the battery. Through the application of FEA and visualization technology, the battery material combination method of the embodiment not only improves the accuracy of the battery design, but also enhances the efficiency of the battery design process.

[0149] The application provides a battery material combination device, which comprises at least one processor and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the battery material combination method in the above embodiment one.

[0150] Reference will be made to the following description Figure 6 which shows a structural schematic diagram of the battery material combination device suitable for being used to implement the embodiments of the application. The battery material combination device in the embodiments of the application can comprise various hardware and software components for implementing the scheduling method of the inspection task. Figure 6 The battery material combination device shown is only an example, and should not bring any limitation to the functions and use range of the embodiments of the application.

[0151] As Figure 6As shown, the battery material combination device can include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. Various programs and data required for the operation of the battery material combination device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the battery material combination device to communicate with other devices wirelessly or by wire to exchange data. Although the battery material combination device with various systems is shown in the figure, it should be understood that all the shown systems are not required to be implemented or possessed. More or fewer systems can be alternatively implemented or possessed.

[0152] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of embodiments of the present disclosure are performed.

[0153] The battery material combination device provided by the present disclosure adopts the battery material combination device method in the above embodiments, which can solve the technical problems of low evaluation efficiency and limited coverage combination of battery material combination, resulting in limited selection of battery materials. Compared with the prior art, the battery material combination device provided by the present disclosure has the same beneficial effects as the battery material combination method provided by the above embodiments, and other technical features in the battery material combination device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0154] It should be understood that various aspects of the disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any appropriate manner in any one or more embodiments or examples.

[0155] The above description is merely illustrative of the application and is not intended to limit the scope of the application. Any variations and modifications that can be made by any person skilled in the art within the spirit and scope of the application are intended to be encompassed by the application. The scope of the application is defined by the appended claims.

[0156] The application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e., a computer program) for performing the battery material combination method in the above-described embodiments.

[0157] The computer readable storage medium provided by the application may, for example, be a U disk, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any appropriate combination thereof. In the present embodiment, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer readable storage medium can be transmitted in any appropriate medium, including but not limited to electrical wires, optical cables, RF (Radio Frequency), etc., or any appropriate combination thereof.

[0158] The above computer readable storage medium can be included in the battery material combination device; or can exist separately and not be assembled into the battery material combination device.

[0159] The computer readable storage medium described above carries one or more programs, when the one or more programs are executed by the battery material combination device, the battery material combination device is caused to: generate one or more sets of candidate material combinations based on the battery material data; extract attribute features of the candidate material combinations, and convert the attribute features into feature vectors; input the feature vectors into a pre-trained prediction model to obtain performance prediction results of the candidate material combinations.

[0160] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0161] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a procedure, or a part of code, which comprises one or more executable instructions for implementing the specified functions. It should also be noted that, in some alternative implementations, the functions noted in the blocks can occur in a different order than that noted in the figures. For example, two blocks noted in succession can in fact be executed substantially concurrently or in the opposite order, depending on the functionality involved. It should also be noted that each block in the block diagrams and / or flow diagrams, and combinations of blocks in the block diagrams and / or flow diagrams, can be implemented by dedicated hardware-based systems that perform the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0162] The modules involved in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the unit itself.

[0163] The readable storage medium provided in the application is a computer readable storage medium, which stores computer readable program instructions (i.e., a computer program) for executing the battery material combination method described above, and can solve the technical problems of low evaluation efficiency and limited combination coverage of battery material combination, resulting in limited selection of battery materials. Compared with the prior art, the beneficial effects of the computer readable storage medium provided in the application are the same as those of the battery material combination method provided in the above embodiments, and are not described here.

[0164] The embodiment of the application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the battery material combination method described above.

[0165] The computer program product provided in the application can solve the technical problems of low evaluation efficiency and limited combination coverage of battery material combination, resulting in limited selection of battery materials. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiment of the application are the same as those of the battery material combination method provided in the above embodiments, and are not described here.

[0166] The above is only the preferred embodiment of the application, and does not limit the patent scope of the application, and any equivalent structure or equivalent process transformation using the content of the specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the application.

[0167] It should be noted that in this paper, the term "includes", "contains" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or system. Without more limitations, the element defined by the sentence "includes a…" does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0168] From the above description of the embodiments, those skilled in the art can clearly understand that the above embodiment method can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment.

[0169] The above is only the preferred embodiment of the application, and does not limit the patent scope of the application, and any equivalent structure or equivalent process transformation using the content of the specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the application.

Claims

1. A battery material combination method, characterized by, The battery material combination method comprises: generating one or more groups of candidate material combinations based on battery material data, the battery material data comprising positive electrode materials, negative electrode materials, electrolytes and separators; extracting attribute features of the candidate material combinations, the attribute features comprising crystal structure, electrochemical activity and ion diffusion rate of the positive electrode materials, and specific capacity, electronic conductivity and stability of the negative electrode materials; wherein, when converting the attribute features into feature vectors, a feature matrix is constructed based on the attribute features of the candidate material combinations; principal component analysis is performed on the feature matrix to extract a preset number of principal components; and the preset number of principal components are combined to obtain the feature vectors; inputting the feature vectors into a pre-trained prediction model to obtain performance prediction results of the candidate material combinations; the step of generating one or more groups of candidate material combinations based on battery material data comprises: generating the candidate material combinations using a genetic algorithm or a particle swarm optimization algorithm; wherein, based on the energy density and cycle life of the battery materials, the fitness value of each material combination is calculated, and the final candidate material combination is determined based on the fitness value; the step of inputting the feature vectors into a pre-trained prediction model to obtain performance prediction results of the candidate material combinations comprises: obtaining safety performance data corresponding to material attributes of the battery materials, the safety performance data comprising impact test results of the battery materials under external impact conditions; constructing a battery material dataset according to the material attributes and the safety performance data; training a prediction model based on the battery material dataset; using the trained prediction model to predict the safety performance of the candidate material combinations and output the performance prediction results of the candidate material combinations.

2. The battery material combination method of claim 1, wherein, the step of generating one or more groups of candidate material combinations based on battery material data comprises: determining interaction rules of material combinations, the interaction rules being used to guide pairing of the material combinations; obtaining a candidate list of the material combinations based on the interaction rules; screening the candidate list of the material combinations according to a preset material attribute standard to determine the candidate material combinations.

3. The battery material combination method of claim 1, wherein, the step of extracting attribute features of the candidate material combinations and converting the attribute features into feature vectors comprises: obtaining material attributes of each battery material in the candidate material combinations and attribute values corresponding to the material attributes; mapping the attribute values of each battery material into a group of feature vectors, each attribute value corresponding to an element in the feature vectors.

4. The battery material combination method of claim 1, wherein, the step of training a prediction model based on the battery material dataset comprises: dividing the battery material dataset into subsets of equal size, each subset containing the same number of data; in each iteration training, selecting a different subset as a validation set and the remaining subsets as training sets, iteratively training the prediction model, and calculating prediction errors using the validation set.

5. The method of claim 4, wherein, The step of iteratively training the prediction model and calculating the prediction error using the validation set further comprises: updating the hyperparameter configuration of the prediction model based on the prediction error after each iteration training; repeating the step of selecting a different subset as the validation set and the remaining subset as the training set, iteratively training the training set, and calculating the prediction error using the validation set until the prediction error is reduced to a preset threshold.

6. The battery material combination method of claim 1, wherein, The step of inputting the feature vector into the pre-trained prediction model to obtain the performance prediction result of the candidate material combination further comprises: determining a confidence interval of the safety performance of the battery material according to the historical safety performance data of the battery material; comparing the performance prediction result of the candidate material combination with the confidence interval; determining the safety level of the candidate material combination according to the comparison result.

7. The battery material combination method of claim 1, wherein, The step of inputting the feature vector into the pre-trained prediction model to obtain the performance prediction result of the candidate material combination further comprises: determining the material attribute that needs to be optimized according to the performance prediction result, and regenerating a new candidate material combination; inputting the feature vector of the new candidate material combination into the prediction model to obtain a new performance prediction result; iteratively adjusting the new candidate material combination based on the new performance prediction result until a preset performance target is reached or the adjustment of the candidate material combination is completed.

8. A battery material assembly apparatus, comprising: The device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the battery material combination method according to any one of claims 1 to 7.

9. A computer storage medium, characterized in that The computer storage medium is a computer readable storage medium, and the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the battery material combination method according to any one of claims 1 to 7.

Images