A battery health status prediction method and system

Abstract

The present application provides a battery health status prediction method and system, including: obtaining a high-dimensional data set during the battery discharge process, and normalizing the high-dimensional data set to obtain standardized data; using the Spearman correlation coefficient to analyze the correlation between the standardized data and the battery capacity to obtain a target data set; inputting the target data set into a width autoencoder, extracting the feature nodes and enhancement nodes of the width autoencoder, and obtaining an intermediate feature representation; inputting the intermediate feature representation into a random configuration network that integrates an intuitionistic fuzzy mechanism to generate a preliminary prediction result of the battery health status, thereby alleviating the technical problem of low accuracy of existing battery health status prediction.

Description

Technical Field

[0001] The present application relates to the technical field of battery health state prediction, and in particular to a battery health state prediction method and system. Background Art

[0002] With the widespread adoption of electric vehicles (EVs), renewable energy storage systems, and portable electronic devices, the demand for batteries, as key components, is increasing. Battery state of health (SOH) is an important indicator for measuring battery performance and lifespan.

[0003] Accurately predicting a battery's SOH is crucial for extending battery life, improving system reliability, and optimizing energy management. However, due to the complex electrochemical reactions within batteries and their significant influence from environmental factors, traditional methods based on empirical formulas or simple statistical models struggle to provide high-precision SOH predictions. Summary of the Invention

[0004] The present application provides a battery health status prediction method and system to solve the problem of low accuracy of existing battery health status prediction.

[0005] In a first aspect, the present application provides a battery health status prediction method, comprising: obtaining a high-dimensional data set during a battery discharge process, and normalizing the high-dimensional data set to obtain standardized data, wherein the high-dimensional data set includes at least: current data, voltage data, temperature data, battery capacity data, battery internal resistance data, and battery self-discharge rate; using the Spearman correlation coefficient to analyze the correlation between the standardized data and the battery capacity to obtain a target data set, wherein the data contained in the target data set is standardized data whose Spearman correlation coefficient is greater than a preset threshold; inputting the target data set into a width autoencoder, extracting the feature nodes and enhancement nodes of the width autoencoder, and obtaining an intermediate feature representation; inputting the intermediate feature representation into a random configuration network that integrates an intuitionistic fuzzy mechanism to generate a preliminary prediction result of the battery health status.

[0006] Furthermore, the target data set is input into a width autoencoder, and the feature nodes and enhancement nodes of the width autoencoder are extracted to obtain an intermediate feature representation, including: using the mapping layer and random weight matrix of the width autoencoder to convert the target data set into feature nodes to obtain a first-stage feature representation; expanding the first-stage feature representation into the enhancement nodes of the width autoencoder to form a second-stage feature representation; using the reconstruction layer, the second-stage feature representation and linear weights of the width autoencoder to reconstruct the target data set to obtain reconstructed data; minimizing the mean square error between the reconstructed data and the target data set to obtain the intermediate feature representation.

[0007] Furthermore, the intermediate feature representation is input into a random configuration network that incorporates an intuitionistic fuzzy mechanism to generate a preliminary prediction result of the battery health state, including: initializing the random configuration network structure; inputting the intermediate feature representation into the initialized random configuration network structure to obtain an initial network output; using the initial network output and the intuitionistic fuzzy mechanism, iteratively optimizing the initialized random configuration network structure to obtain an optimized random configuration network structure; and calculating the preliminary prediction result of the battery health state based on the optimized random configuration network structure.

[0008] Furthermore, the method also includes: combining the physical constraints under the physical information neural network framework with the optimized random configuration network structure to obtain a target model, and setting a loss function for the target model, wherein the loss function includes: data loss function, physical equation loss function and monotonicity loss function; based on the loss function and the preliminary prediction result of the battery health status, calculating the loss function value; using the loss function value, iteratively optimizing the target model to obtain an optimized target model; using the optimized target model, determining the final prediction result of the battery health status.

[0009] Furthermore, obtaining a high-dimensional data set during the battery discharge process includes: recording the operating data of the battery under different cycle numbers according to a preset battery charge and discharge experimental plan, wherein the preset battery charge and discharge experimental plan includes a charging strategy and a discharging strategy; and performing preliminary cleaning and preprocessing on the operating data to obtain the high-dimensional data set.

[0010] Furthermore, the Spearman correlation coefficient is used to analyze the correlation between the standardized data and the battery capacity to obtain a target data set, including: using the Spearman correlation coefficient to analyze the correlation between the standardized data and the battery capacity, and calculating the Spearman correlation coefficient corresponding to each standardized data; using the standardized data whose Spearman correlation coefficient is greater than a preset threshold to construct the target data set.

[0011] Furthermore, after obtaining the final prediction result, the method also includes: obtaining the actual result of the battery health status; using the actual result and the final prediction result to calculate the error index, wherein the error index includes: MAPE value and RMSE value; using the error index, optimizing the optimized target model.

[0012] In a second aspect, the present application provides a battery health status prediction system, comprising: an acquisition module for acquiring a high-dimensional data set during the battery discharge process, and normalizing the high-dimensional data set to obtain standardized data, wherein the high-dimensional data set includes at least: current data, voltage data, temperature data, battery capacity data, battery internal resistance data, and battery self-discharge rate; an analysis module for analyzing the correlation between the standardized data and the battery capacity using the Spearman correlation coefficient to obtain a target data set, wherein the data contained in the target data set is standardized data whose Spearman correlation coefficient is greater than a preset threshold; an extraction module for inputting the target data set into a width autoencoder, extracting the feature nodes and enhancement nodes of the width autoencoder, and obtaining an intermediate feature representation; a generation module for inputting the intermediate feature representation into a random configuration network that integrates an intuitionistic fuzzy mechanism to generate a preliminary prediction result of the battery health status.

[0013] In a third aspect, the present application provides a computing device comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the method described in the first aspect above.

[0014] In a fourth aspect, the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements the method described in the first aspect above.

[0015] In the present invention, a high-dimensional data set during the battery discharge process is obtained and normalized to obtain standardized data; the Spearman correlation coefficient is used to analyze the correlation between the standardized data and the battery capacity to obtain a target data set; the target data set is input into a width autoencoder, and the feature nodes and enhancement nodes of the width autoencoder are extracted to obtain an intermediate feature representation; the intermediate feature representation is input into a random configuration network that incorporates an intuitionistic fuzzy mechanism to generate a preliminary prediction result of the battery health state, thereby achieving the purpose of accurately predicting the battery health state and solving the technical problem of low accuracy of the existing battery health state prediction.

[0016] These and other aspects of the present application will become more readily apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in this application or the prior art, a brief introduction will be given below to the drawings required for use in the description of the prior art. Obviously, the drawings described below are some of the drawings in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A flowchart of a battery health status prediction method provided in this application;

[0019] Figure 2 A schematic diagram of a battery health status prediction system provided in this application;

[0020] Figure 3 This application provides a schematic diagram of a computing device. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] Embodiment 1: According to an embodiment of the present invention, an embodiment of a battery health status prediction method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0023] Figure 1 FIG. 1 is a flow chart of a method for predicting battery health status according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0024] Step S101, obtaining a high-dimensional data set during battery discharge, and normalizing the high-dimensional data set to obtain standardized data, wherein the high-dimensional data set at least includes: current data, voltage data, temperature data, battery capacity data, battery internal resistance data, and battery self-discharge rate;

[0025] In this embodiment of the present invention, before beginning battery health status prediction, it is necessary to first obtain a high-dimensional dataset of the battery discharge process. This data includes, but is not limited to, current data, voltage data, temperature data, battery capacity data, battery internal resistance data, and battery self-discharge rate. This data can be collected by a battery management system (BMS) or other sensor devices.

[0026] Specifically, obtaining a high-dimensional dataset during battery discharge includes the following steps:

[0027] Recording the operating data of the battery at different cycle times according to a preset battery charge and discharge experiment plan, wherein the preset battery charge and discharge experiment plan includes a charging strategy and a discharging strategy;

[0028] The operating data is preliminarily cleaned and preprocessed to obtain the high-dimensional data set.

[0029] Before obtaining a high-dimensional dataset of the battery discharge process, it is necessary to first record the battery's operating data at different cycle times according to a pre-set battery charge and discharge experimental plan. This experimental plan should include both charging and discharging strategies to ensure the comprehensiveness and representativeness of the data.

[0030] Charging strategy: You can choose constant current charging (CC), constant voltage charging (CV), or a mixed charging strategy. For example, in the constant current charging stage, the current remains constant until the voltage reaches the set value; in the constant voltage charging stage, the voltage remains constant and the current gradually decreases until it stops.

[0031] Discharge strategy: You can choose constant current discharge (CC) or pulse discharge strategy. For example, in the constant current discharge process, the current remains constant until the battery voltage drops to the minimum allowable value.

[0032] During the experiment, a battery management system (BMS) or other sensor equipment is used to record various battery parameters in real time, including but not limited to current, voltage, temperature, battery capacity, battery internal resistance, and self-discharge rate. This data will serve as the basis for subsequent analysis.

[0033] To ensure data quality and consistency, the collected data needs to be cleaned and preprocessed. Common processing methods include removing missing values, smoothing, and filtering.

[0034] Removing missing values: For data points with missing values, you can use interpolation or deletion. Interpolation fills the missing values by linearly interpolating adjacent data points; deletion directly deletes the data points with missing values.

[0035] Smoothing: In order to reduce the impact of noise, a moving average filter or a low-pass filter can be used to smooth the data.

[0036] Filtering: You can use a median filter to remove outliers. The median filter sorts the data points within a window and takes the median value as the output, effectively removing extreme values.

[0037] To eliminate the impact of different dimensions on model training, the processed data needs to be normalized. Common normalization methods include min-max normalization and Z-score normalization. This paper uses min-max normalization to map the data to the interval [0, 1].

[0038] Step S102, analyzing the correlation between the standardized data and the battery capacity using the Spearman correlation coefficient to obtain a target data set, wherein the data included in the target data set is standardized data having a Spearman correlation coefficient greater than a preset threshold;

[0039] Specifically, step S102 includes the following steps:

[0040] Analyzing the correlation between the standardized data and the battery capacity using the Spearman correlation coefficient, and calculating the Spearman correlation coefficient corresponding to each standardized data;

[0041] The target data set is constructed using the standardized data whose Spearman correlation coefficient is greater than a preset threshold.

[0042] In order to improve the accuracy and efficiency of the model, it is necessary to select features that are highly correlated with battery capacity from the high-dimensional data set. The present invention uses the Spearman rank correlation coefficient to evaluate the correlation between each feature and battery capacity.

[0043] For each normalized data, the Spearman correlation coefficient between it and the battery capacity was calculated.

[0044] Based on the calculated Spearman correlation coefficient, standardized data with values greater than a preset threshold are selected to construct a target data set. This set will serve as the basis for subsequent feature extraction and model training.

[0045] Specifically, the core metric of battery state of health (SOH) is battery capacity, but the correlations between multi-dimensional parameters during the charge and discharge process (such as current, voltage, and temperature) and capacity decay vary significantly. The Spearman correlation coefficient effectively measures nonlinear statistical relationships. Through threshold screening, irrelevant or weakly correlated parameters can be eliminated, retaining core features highly correlated with capacity (such as voltage slope and current dynamic characteristics). This allows the focus to be on the key physical factors influencing battery degradation, preventing redundant information from interfering with model learning.

[0046] Furthermore, battery aging is essentially a process of nonlinear degradation of electrochemical parameters (such as active material loss and lithium deposition). The Spearman correlation coefficient can capture the nonlinear relationship between parameters and capacity, which is superior to the Pearson coefficient, which only measures linear relationships. For example, nonlinear changes in the voltage curve are closely related to capacity decay, but may not be fully represented by linear correlation. Threshold screening ensures that the input data conforms to the physical laws of battery degradation, providing an adaptive feature representation for the subsequent neural network that integrates physical constraints.

[0047] Furthermore, high-dimensional battery data often contains noise or low-information parameters (such as transient fluctuations under certain operating conditions). Threshold filtering can significantly reduce data dimensionality, reduce the model's sensitivity to noise, and enhance generalization. Furthermore, after feature dimensionality reduction, dynamic structures such as wide autoencoders and stochastic configuration networks (SCNs) can more efficiently extract hierarchical features, avoiding overfitting and wasted computational resources due to input redundancy, and achieving high-precision predictions with limited data.

[0048] In summary, by screening highly correlated features, the prediction error can be reduced, while reducing the model training time, thus achieving efficient and stable battery health status prediction while ensuring accuracy.

[0049] Step S103: inputting the target data set into a width autoencoder, extracting feature nodes and enhancement nodes of the width autoencoder, and obtaining an intermediate feature representation;

[0050] Specifically, step S103 includes the following steps:

[0051] Using the mapping layer and random weight matrix of the width autoencoder, the target data set is converted into feature nodes to obtain a first-stage feature representation;

[0052] Expanding the first stage feature representation into an enhanced node of the width autoencoder to form a second stage feature representation;

[0053] Reconstructing the target data set using the reconstruction layer of the width autoencoder, the second stage feature representation, and the linear weight to obtain reconstructed data;

[0054] Minimize the mean square error between the reconstructed data and the target data set to obtain the intermediate feature representation.

[0055] A wide autoencoder (BAE) is a deep learning model used to extract useful feature representations from input data. First, initialize the wide autoencoder structure, defining the mapping layer, expansion layer, and reconstruction layer. The mapping layer converts the input data into feature nodes, the expansion layer increases the network width to form enhanced nodes, and the reconstruction layer reconstructs the input data.

[0056] The target data set is converted into feature nodes using a mapping layer and a random weight matrix: and bias Perform linear transformation and use activation function (such as ReLU) for nonlinear transformation to obtain the first stage feature representation .

[0057] The weight matrix of the enhancement layer and bias Perform linear transformation and use activation function (such as ReLU) for nonlinear transformation to obtain enhanced nodes .

[0058] Splice the feature nodes and enhancement nodes [Z|H] and reconstruct the weight matrix of the layer Perform linear transformation to obtain reconstructed data .

[0059] Finally, the mean square error between the reconstructed data and the target data set is minimized, and the network parameters are optimized. , and obtain the final feature representation as the intermediate feature representation.

[0060] To effectively extract useful features from raw data, this application designs a wide autoencoder consisting of a mapping layer, an expansion layer, and a reconstruction layer. The mapping layer and a random weight matrix transform the target data set into feature nodes, which are then expanded into enhanced nodes, increasing the network width and improving its expressive power. The reconstruction layer reconstructs the second-stage feature representation and minimizes reconstruction error, ensuring the effectiveness and stability of feature extraction. This not only simplifies the feature selection process but also improves the performance and reliability of the model.

[0061] Step S104: input the intermediate feature representation into a random configuration network integrated with an intuitionistic fuzzy mechanism to generate a preliminary prediction result of the battery health state.

[0062] In this embodiment of the present invention, step S104 includes the following steps:

[0063] Initialize the random configuration network structure;

[0064] Initialize the random configuration network structure by inputting the intermediate feature representation to obtain the initial network output;

[0065] Iteratively optimizing the initialized random configuration network structure using the initial network output and the intuitionistic fuzzy mechanism to obtain an optimized random configuration network structure;

[0066] Based on the optimized random configuration network structure, a preliminary prediction result of the battery health state is calculated.

[0067] Specifically, the stochastic configuration network (SCN) is a neural network model designed to handle complex nonlinear problems. First, the SCN structure is initialized, including setting the initial number of hidden layer nodes. Then, the intermediate feature representation is used as input, and the initial network output is calculated through forward propagation.

[0068] In each iteration, the current network output is compared with the objective function to calculate the residual vector ,in is the objective function value, is the current network output. By calculating the residual vector, we evaluate the difference between the current network output and the objective function and obtain the residual analysis result.

[0069] An intuitionistic fuzzy strategy is used to evaluate the contribution of each candidate node. Nodes with low contributions are automatically filtered out, simplifying the network structure and improving efficiency. This process helps dynamically adjust the network structure to make it more suitable for the task at hand.

[0070] The loss function is recalculated based on the updated network structure, and the loss weights are dynamically adjusted. This step ensures that the model can more accurately predict the battery state of health (SOH). Based on the adjusted loss weights, the new current network output is calculated through forward propagation. This process is iterated until the preset stopping condition is met, resulting in a preliminary prediction of the battery state of health.

[0071] To further accurately calculate the battery state of health (SOH) prediction value, a total loss function consisting of data loss, physical equation loss, and monotonicity loss is established, combining the physical constraints of the physical information neural network (PINN) framework. A cosine annealing strategy is used to adjust the learning rate, helping the model escape local optimal solutions. The model is iteratively trained until a preset stopping condition is reached. Finally, the optimized model is used to determine the final battery state of health prediction. This approach not only improves the model's generalization and interpretability, but also maintains high stability and reliability under different operating conditions.

[0072] Furthermore, after obtaining the preliminary prediction result of the battery health status, the embodiment of the present invention further includes the following steps:

[0073] Integrating the physical constraints under the physical information neural network framework into the optimized random configuration network structure to obtain a target model, and setting a loss function for the target model, wherein the loss function includes: a data loss function, a physical equation loss function, and a monotonicity loss function;

[0074] Calculating a loss function value based on the loss function and the preliminary prediction result of the battery health state;

[0075] Iteratively optimizing the target model using the loss function value to obtain an optimized target model;

[0076] The optimized target model is used to determine the final prediction result of the battery health state.

[0077] To further accurately calculate the battery state of health (SOH) prediction value, the physical constraints under the physical information neural network (PINN) framework are combined. First, the total loss function is set, which includes data loss, physical equation loss, and monotonicity loss.

[0078] To help the model escape local optimal solutions, a cosine annealing strategy was used to adjust the learning rate. The model was then trained until the preset stopping condition was reached. The optimized model parameters were obtained and used to calculate the final SOH prediction value. The final SOH prediction value was calculated using the optimized model parameters and evaluated using model performance metrics such as MAE and MSE.

[0079] After obtaining the final prediction result, the embodiment of the present invention further includes the following steps:

[0080] Get the actual result of battery health status;

[0081] Calculating an error index using the actual result and the final prediction result, wherein the error index includes: a MAPE value and a RMSE value;

[0082] The optimized target model is optimized using the error index.

[0083] After obtaining the final prediction results, it is necessary to obtain the actual results of the battery health status. The actual results can be obtained through experimental measurements or historical data. For example, the actual capacity changes of the battery can be recorded by the battery management system (BMS).

[0084] Using the actual results and the final predicted results, the error index is calculated. Common error indicators include mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE).

[0085] Use error metrics to analyze the source of errors and identify factors that may increase them. Common sources of error are data quality issues: If errors are concentrated in specific time periods or under specific conditions, they may be due to data quality issues. For example, sensor failure or environmental interference may introduce outliers.

[0086] Unreasonable model structure: If the error is large and evenly distributed, it may be due to an unreasonable model structure. For example, the model is too simple to capture complex relationships, or too complex to cause overfitting.

[0087] Improper hyperparameter settings: If the error fluctuates significantly over time, this may be due to improper hyperparameter settings. For example, a learning rate that is too large may prevent the model from converging, while a learning rate that is too small may cause excessive training time. Causes include data quality issues, an unreasonable model structure, and improper hyperparameter settings.

[0088] After adjusting model parameters or improving the model structure, the training and validation process needs to be repeated until the predetermined accuracy requirements are met and the improved model is obtained. Specific validation methods include cross-validation, holdout, and bootstrap.

[0089] To further optimize model performance, after obtaining the final prediction results, actual battery health status results are obtained. Error metrics (such as MAPE and RMSE) are calculated using both the actual and predicted results. Error analysis identifies factors that may increase the error, allowing targeted adjustments to model parameters or improvements to the model structure. The training and validation process is repeated until the predetermined accuracy requirements are met. This approach ensures that the model achieves optimal performance after multiple optimization cycles, enhancing its practical value and reliability.

[0090] This paper proposes a battery state-of-health prediction method based on an intuitionistic fuzzy random configuration physical information neural network. This method acquires a high-dimensional dataset from the battery discharge process, analyzes the correlation between the normalized data and the battery capacity using the Spearman correlation coefficient, extracts characteristic nodes and enhanced nodes, and combines a random configuration network (SCN) with a physical information neural network (PINN) to predict the battery state of health (SOH). This method demonstrates high accuracy and robustness, making it suitable for practical applications.

[0091] Example 2: The embodiment of the present invention also provides a battery health status prediction system, which is used to execute the battery health status prediction method provided in the above content of the embodiment of the present invention. The following is a detailed introduction to the battery health status prediction system provided by the embodiment of the present invention.

[0092] like Figure 2 As shown, Figure 2 FIG. 1 is a schematic diagram of the battery health status prediction system, which includes:

[0093] An acquisition module 10 is configured to acquire a high-dimensional data set during battery discharge and perform normalization processing on the high-dimensional data set to obtain standardized data, wherein the high-dimensional data set includes at least current data, voltage data, temperature data, battery capacity data, battery internal resistance data, and battery self-discharge rate;

[0094] an analysis module 20 for analyzing the correlation between the standardized data and the battery capacity using a Spearman correlation coefficient to obtain a target data set, wherein the data included in the target data set is standardized data having a Spearman correlation coefficient greater than a preset threshold;

[0095] An extraction module 30 is configured to input the target data set into a width autoencoder, extract feature nodes and enhancement nodes of the width autoencoder, and obtain an intermediate feature representation;

[0096] The generation module 40 is used to input the intermediate feature representation into a random configuration network integrated with an intuitionistic fuzzy mechanism to generate a preliminary prediction result of the battery health state.

[0097] Embodiment 3, the embodiment of the present invention further provides a computing device for executing the program of the method described in the above embodiment 1, such as Figure 3 As shown, the computing device may include a storage component 41 and a processing component 42;

[0098] The storage component 41 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 42 .

[0099] The processing component 42 may include one or more processors to execute computer instructions to complete all or part of the steps of the method of Example 1. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0100] The storage component 41 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0101] The display component 43 may be an electroluminescent (EL) element, a liquid crystal display or a micro display having a similar structure, or a retinal direct display or a similar laser scanning display.

[0102] Of course, a computing device may also include other components, such as input / output interfaces, communication components, etc.

[0103] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0104] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0105] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0106] Embodiment 4: The present application also provides a computer storage medium storing a computer program, which can achieve the above-mentioned Figure 1 The method of the embodiment shown.

[0107] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0108] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0109] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for predicting battery health status, characterized in that: include: Acquire a high-dimensional data set during the battery discharge process, and perform normalization processing on the high-dimensional data set to obtain standardized data, wherein the high-dimensional data set at least includes: current data, voltage data, temperature data, battery capacity data, battery internal resistance data, and battery self-discharge rate; Analyzing the correlation between the standardized data and the battery capacity using the Spearman correlation coefficient to obtain a target data set, wherein the data included in the target data set is standardized data having a Spearman correlation coefficient greater than a preset threshold; Inputting the target data set into a width autoencoder, extracting feature nodes and enhancement nodes of the width autoencoder, and obtaining an intermediate feature representation; The intermediate feature representation is input into a random configuration network integrated with an intuitionistic fuzzy mechanism to generate a preliminary prediction result of the battery health status.

2. The method according to claim 1, characterized in that Inputting the target data set into a width autoencoder, extracting feature nodes and enhancement nodes of the width autoencoder, and obtaining an intermediate feature representation, including: Using the mapping layer and random weight matrix of the width autoencoder, the target data set is converted into feature nodes to obtain a first-stage feature representation; Expanding the first stage feature representation into an enhanced node of the width autoencoder to form a second stage feature representation; Reconstructing the target data set using the reconstruction layer of the width autoencoder, the second stage feature representation, and the linear weight to obtain reconstructed data; Minimize the mean square error between the reconstructed data and the target data set to obtain the intermediate feature representation.

3. The method according to claim 2, characterized in that The intermediate feature representation is input into a random configuration network integrated with an intuitionistic fuzzy mechanism to generate a preliminary prediction result of the battery health status, including: Initialize the random configuration network structure; Initialize the random configuration network structure by inputting the intermediate feature representation to obtain the initial network output; Iteratively optimizing the initialized random configuration network structure using the initial network output and the intuitionistic fuzzy mechanism to obtain an optimized random configuration network structure; Based on the optimized random configuration network structure, a preliminary prediction result of the battery health state is calculated.

4. The method according to claim 3, characterized in that The method further comprises: Integrating the physical constraints under the physical information neural network framework into the optimized random configuration network structure to obtain a target model, and setting a loss function for the target model, wherein the loss function includes: a data loss function, a physical equation loss function, and a monotonicity loss function; Calculating a loss function value based on the loss function and the preliminary prediction result of the battery health state; Iteratively optimizing the target model using the loss function value to obtain an optimized target model; The optimized target model is used to determine the final prediction result of the battery health state.

5. The method according to claim 1, wherein Obtain a high-dimensional dataset of the battery discharge process, including: Recording the operating data of the battery at different cycle times according to a preset battery charge and discharge experiment plan, wherein the preset battery charge and discharge experiment plan includes a charging strategy and a discharging strategy; The operating data is preliminarily cleaned and preprocessed to obtain the high-dimensional data set.

6. The method according to claim 1, characterized in that The Spearman correlation coefficient is used to analyze the correlation between the standardized data and the battery capacity to obtain a target data set, including: Analyzing the correlation between the standardized data and the battery capacity using the Spearman correlation coefficient, and calculating the Spearman correlation coefficient corresponding to each standardized data; The target data set is constructed using the standardized data whose Spearman correlation coefficient is greater than a preset threshold.

7. The method according to claim 4, characterized in that After obtaining the final prediction result, the method further includes: Get the actual result of battery health status; Calculating an error index using the actual result and the final prediction result, wherein the error index includes: a MAPE value and a RMSE value; The optimized target model is optimized using the error index.

8. A battery health status prediction system, characterized in that: include: an acquisition module, configured to acquire a high-dimensional data set during the battery discharge process and perform normalization processing on the high-dimensional data set to obtain standardized data, wherein the high-dimensional data set includes at least: current data, voltage data, temperature data, battery capacity data, battery internal resistance data, and battery self-discharge rate; an analysis module, configured to analyze the correlation between the standardized data and the battery capacity using a Spearman correlation coefficient to obtain a target data set, wherein the data included in the target data set is standardized data having a Spearman correlation coefficient greater than a preset threshold; An extraction module is used to input the target data set into a width autoencoder, extract feature nodes and enhancement nodes of the width autoencoder, and obtain an intermediate feature representation; A generation module is used to input the intermediate feature representation into a random configuration network that integrates an intuitionistic fuzzy mechanism to generate a preliminary prediction result of the battery health state.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, the method according to any one of claims 1 to 7 is implemented.

Images