Abstract
The State of Health (SOH) estimation technology for lithium-ion batteries is crucial for the safety and reliability of electric vehicles. With the development of artificial intelligence (AI) and machine learning (ML) technologies, the field of battery management is beginning to adopt these methods to improve efficiency and stability. Especially, neural networks have shown advantages in high efficiency, low energy consumption, high robustness, and scalability in SOH simulation and prediction. The hybrid model, combined with equivalent circuit models (ECMs) and deep learning, has been proven to have potential in improving the accuracy and real-time performance of SOH estimation. Future research directions include utilizing more on-site data for health feature screening and model construction, as well as intelligent screening and combination of battery parameters to more accurately characterize actual SOH. The development of these technologies will further enhance the scientific, reliable, stable, and robust management of electric vehicle batteries.
1. Briefly
1.1 The importance of lithium-ion batteries for electric vehicles and the critical significance of SOH estimation
Lithium ion batteries are crucial for the operation of electric vehicles, and their performance is affected by various degradation processes. Accurately estimating the state of health (SOH) of batteries is crucial for ensuring the safe, reliable, and economical operation of electric vehicles. As the demand for electric vehicles grows, SOH monitoring becomes increasingly important, as lithium-ion batteries typically drop to 80% of their original capacity before the end of their lifespan. In addition, State of Charge (SOC) is also a key parameter, and its changes can reflect the aging and degradation of battery capacity. Accurate SOC prediction is helpful for SOH estimation, which in turn determines the remaining life of the battery.
1.2 Development of SOH estimation methods
Overview and progress of existing methods: Multiple SOH estimation methods have been developed, among which SOC based methods integrate real-time data such as current, voltage, and temperature to achieve more accurate SOH prediction in multiple charge and discharge cycles, optimize battery performance, prevent faults, and extend battery life. The latest advances in machine learning methods have further enhanced SOH estimation, and neural networks such as feedforward and convolutional neural networks perform well in battery modeling, outperforming traditional regression methods in complexity and accuracy, with an average error deviation of about 0.16% and a root mean square error of 5.57mV at the battery cell level.
1.3 Classification and Characteristics of Battery Modeling Methods
Analysis methods such as current integration and open circuit voltage (OCV) techniques can provide clear SOH estimates, but are affected by accumulated noise and require long periods of standing to ensure accuracy.
Model based approach
White box model: Based on detailed electrochemical principles, it simulates battery behavior through basic parameters with high accuracy. However, its high computational requirements and simplified assumptions for real-world dynamics reduce its accuracy under dynamic conditions, making it unsuitable for real-time applications.
Grey box models (such as ECM): Combining physical insights and empirical adjustments, using circuit analogy to approximate battery behavior, can estimate SOC with high accuracy (usually within 3% error), and are useful for real-time SOH estimation and remaining useful life (RUL) prediction, but face challenges in data quality and computational requirements. A simple equivalent circuit model for lithium-ion batteries (including series resistors and up to two RC elements) can be used for reliable simulation, while more complex ECMs (including multiple RC branches or constant phase elements CPE) can simulate highly dynamic processes (such as electric vehicle operation), but the increasing computational demand has driven the development of more advanced SOH estimation methods.
Black box model (data-driven approach): Based on input and output data, the model is constructed without relying on internal working principle knowledge. Machine learning techniques can predict battery status from a large amount of measurement data. Machine learning excels at identifying patterns in complex datasets, such as multi-channel neural networks that have high accuracy in capacity estimation, but rely on high-quality and diverse training data. However, in practical vehicle applications, many internal variables cannot be directly measured, and data sparsity and lack of interpretability make the model difficult to understand and maintain.
1.4 Evolution of Model Methods and Development of Hybrid Models
The evolution of model-based methods: In the past decade, model-based methods have continuously developed, including Kalman filtering (KF) and its extensions (such as Extended Kalman Filter EKF, Unscented Kalman Filter UKF). These methods have high accuracy in battery state estimation, but require precise dynamic models and are complex to implement.
The rise of hybrid models: In order to address the limitations of real-world data and improve computational efficiency, hybrid models have emerged, combining model-based and data-driven methods to train machine learning models through detailed simulations. At the same time, machine learning techniques have made significant progress in the past five years, including probabilistic methods, meta learning, adversarial learning, semi supervised learning, etc. Deep learning (a subset of machine learning) has performed well in processing structured and unstructured data. Physical Information Neural Networks (PINNs) combine empirical degradation models with neural networks to improve SOH estimation, enhancing the adaptability of methods under different battery types and conditions. With the development of the automotive industry, these technological advancements are crucial for optimizing battery performance, preventing failures, and supporting the development of electric vehicles.
1.5 Overview of subsequent chapters in this article
Section 2 provides a detailed introduction to the methods for screening and selecting review literature, ensuring the systematic and comprehensive nature of the research methodology. Section 3 provides an in-depth analysis of state of charge estimation techniques, exploring the impact of battery degradation mechanisms on modeling methods for electric vehicle batteries, including Kalman filtering and its improved methods, as well as integration with aging models. Section 4 focuses on SOH estimation techniques, compares traditional methods with new methods, and emphasizes methods applicable to electric vehicles. Section 5 demonstrates the role of deep learning in SOH estimation, such as long short-term memory (LSTM) networks and hybrid models, as well as how convolutional neural networks (CNN) consider practical factors to improve health assessment accuracy. Finally, Section 6 summarizes and looks forward to future research directions for battery health management systems to support the development of the electric vehicle market and other energy storage applications.
2. Materials and Methods
2.1 Definition of Research Question
This study proposes five key questions to guide the application of machine learning technology in SOH estimation of lithium-ion batteries in electric vehicles.
Clarify the main machine learning techniques currently used for estimating the state of health (SOH) of lithium-ion batteries in electric vehicles, and explore the specific algorithms and models developed and used by researchers.
Explore the impact of different data sources (laboratory, vehicle, and field data) on the accuracy and robustness of SOH estimation machine learning models, analyze how data sources affect model performance, and determine which data is most beneficial for accurate SOH prediction.
Identify the key challenges of applying machine learning techniques in SOH estimation of lithium-ion batteries, as well as the variations of these challenges in different environmental conditions and application scenarios, such as temperature fluctuations, aging, and the impact of different usage modes on the accuracy of SOH estimation.
Compare the analysis methods of SOH estimation, the differences between traditional methods, and their evolution process, study how machine learning methods can be integrated with these traditional methods, identify their respective advantages, disadvantages, and potential synergies.
Looking ahead to future research directions to improve the accuracy, adaptability, and computational efficiency of machine learning based SOH estimation models in lithium-ion batteries for electric vehicles, identifying research gaps, technical requirements, and innovative methods.
2.2 Literature search and screening
Database selection and search strategy: Conduct a comprehensive literature search using Scopus database, determine keywords based on research questions, and use Boolean search strings (TITLE-ABS-KEY (electric AND vehicle) AND KEY (battery AND state AND of AND health) AND TITLE-ABS-KEY (lithium AND ion) AND PUBYEAR>2003 AND PUBYEAR<2025) to retrieve papers and patents published between 2003 and 2024. A total of 882 documents and 16286 patents were obtained, nearly half of which were published between 2020 and 2024, reflecting the industrial demand and progress in this field. The search results are distributed by year, major journals, national and patent offices, showing the time trend of research, journal distribution, regional diversity, and industry development priorities (such as battery management systems, modular architecture, vehicle control systems, and low resistance materials).
Literature screening and focusing: The retrieved literature covers multiple disciplinary fields, with the engineering field having the highest proportion (730 articles), followed by energy, computer science, and mathematics. After focusing on the field of computer science, 209 relevant documents were identified, of which 183 were published between 2019 and 2024, indicating the timeliness of the data. These documents include conference papers, articles, reviews, and book chapters, with 72 articles published between 2009 and 2024 as the main review basis, while manually incorporating relevant papers and book chapters from other engineering fields to ensure comprehensive coverage of research areas and capture innovative technological advances in using artificial intelligence to improve battery management systems.
3. State of Charge (SOC) estimation technology
3.1 Battery degradation mechanism and its impact on performance
Lithium ion batteries mainly degrade through two mechanisms: lithium inventory loss (LLI) and active material loss (LAM). LLI is related to the formation of the solid electrolyte interface (SEI) layer on the anode, which originates from the side reaction between lithium ions and the electrolyte. LAM is caused by internal mechanical stress in the battery, such as repeated expansion and contraction of electrode materials during charging and discharging, which leads to microcracks and detachment of electrode particles, reducing the active surface area available for electrochemical reactions, thereby reducing battery capacity, increasing internal resistance, and ultimately affecting battery performance. These degradation mechanisms are accelerated by factors such as high charging state, high temperature, and aggressive cycling conditions. Detailed information and modeling details of various aging mechanisms (thermal, electrochemical, etc.) can be found in relevant literature.
3.2. SOC estimation and modeling technology for electric vehicle batteries
In daily use of electric vehicles, the battery is often charged at 20% -40% SOC to maintain battery health, but the non-linear and degradation characteristics of battery capacity may result in inaccurate SOC readings, affecting the estimation of battery full capacity. The performance and maintenance of lithium-ion batteries are also affected by climate, with temperature and electrolyte freshness (determined by production and filling dates) affecting battery efficiency and lifespan. The characteristics of new electrolyte batteries may vary under different climates, and thermal management strategies can help address temperature related performance issues and improve battery durability.
The traditional equivalent circuit model (ECM) is commonly used to estimate SOC, but requires frequent calibration. The article provides a detailed introduction to the SOC calculation equations based on ECM (including continuous and discrete forms), involving state space equations, open circuit voltage and SOC relationship equations, discrete-time domain SOC update equations, and voltage update equations. Relevant parameters (such as resistance, capacitance, open circuit voltage, etc.) are closely related to SOC. Standard laboratory testing (such as mixed pulse power characteristic testing at different temperatures) is commonly used for battery model parameter identification, but model inaccuracy and measurement noise can lead to small errors in SOC estimation. To improve the accuracy of SOC estimation, various techniques such as Kalman filtering and its extensions, PI based observer, sliding mode observer, etc. have been used to compensate for these effects, and integral correction methods have also been developed to handle initial model uncertainty and measurement noise. In addition, although electrochemical impedance spectroscopy (EIS) can evaluate battery characteristics (including SOC and SOH), it is time-consuming and impractical for large-scale applications (such as electric vehicle fleets), making it difficult to capture the dynamic and changing operating conditions of electric vehicle batteries. Therefore, a more adaptive and efficient method is needed.
3.3. Improving Technology
Kalman filter and its improvement methods: Kalman filter (KF) and its extensions (such as Extended Kalman Filter EKF, Unscented Kalman Filter UKF, Volume Kalman Filter CKF) are widely used for SOC estimation. KF provides the optimal SOC estimation by minimizing the mean square error, solving the problems of cumulative error and initial SOC uncertainty. However, it is suitable for linear time-varying systems where the nonlinear dynamics of batteries require linearization approximation. Although EKF extends the KF framework to handle nonlinear models, linearization may affect accuracy and lead to estimator divergence. New methods such as UKF and CKF use sigma point estimation to estimate nonlinear transformation statistics, while CKF uses the spherical radial volume rule to calculate multivariate moment integrals to improve the accuracy of nonlinear Bayesian filtering. However, these filters typically assume that the noise characteristics are known and constant, and in practical applications, the noise is variable (such as non Gaussian noise generated by external interference). Therefore, robust adaptive filtering strategies have been developed, such as using Gaussian mixture models (GMM) to model non Gaussian noise to improve state estimation accuracy. Relevant studies have shown the applications and advantages of these methods in different fields. In addition, distributed and distributed filters (such as distributed Kalman filter DKF, distributed Kalman filter and covariance cross DKF-CI) are used to optimize state estimation of large-scale interconnected systems. Robust and nonlinear filters (such as robust Kalman filter) have superior performance in dealing with complex nonlinearities in battery systems (such as electrochemical processes). Adaptive techniques (such as adaptive EKF and adaptive UKF algorithms) dynamically adjust filter parameters to adapt to noise changes and improve SOC estimation accuracy. Relevant studies and examples have verified the effectiveness of these methods.
Other improvement methods: such as the Adaptive Integral Correction State of Charge Estimation (AIC-SE) method proposed in 2022, which is based on the ECM model and improves the accuracy of SOC estimation through real-time correction mechanisms (including resistance and battery capacity correction) (maximum error ± 0.8%, RMS error less than 0.3%). The computational efficiency is higher than UKF (AIC-SE about 5n operations, UKF about n ^ 2 operations), effectively addressing the challenges of battery aging and degradation. The Variational Bayesian Maximum Correlation Entropy Volume Kalman Filter (VBMCCKF) in 2023 combines advanced filtering and statistical techniques to improve measurement error covariance estimation using the Variational Bayesian method. The Maximum Correlation Entropy criterion is used to handle non Gaussian noise measurement outliers, significantly improving SOC estimation accuracy (compared with EKF, CKF, and Variational Bayesian Volume Kalman Filter, the average absolute error is reduced by 77%, 68%, and 49%, respectively), and enhancing the robustness of the battery management system.
3.4 Integration with Aging Models
The battery aging model is closely related to SOC estimation, and recent research has innovated in both aspects. The battery aging model proposed in 2024 comprehensively considers the effects of SOC, battery temperature, time, and fully equivalent cycle times (NFECs) on battery aging. The model consists of two parts: the first part focuses on SOC and temperature related aging (calculating capacity loss through specific formulas), and the second part considers the impact of NFECs on aging. This model innovatively integrates battery aging as an electric vehicle subsystem with the battery model, covering all operating modes such as parking, driving, and charging. It achieves accurate interaction simulation between different subsystems through the formal method of energy macroscopic representation (EMR) (a graphical tool developed in 2000 for organizing subsystem connections, representing power flow, and causal relationships). Research has shown that reducing the charging frequency (such as changing from daily charging to every four days) can significantly prolong the time for the battery to reach 80% SOH. This integrated approach provides important progress in optimizing battery management and understanding the impact of charging practices on battery aging.
New methods such as AIC-SE and VBMCCKF have significant advantages in SOC estimation accuracy and computational efficiency. AIC-SE performs well in computational efficiency, while VBMCCKF performs better in handling dynamic estimation of measurement errors and noisy environments. If accuracy and noise processing are given priority, combining variational Bayesian and maximum correlation entropy criteria may be the current best choice; If we focus on computational efficiency and real-time applications, AIC-SE is a good choice, indicating that ECM modeling methods still have advantages in this area. In addition, the battery aging model studied in 2024 comprehensively considers the impact of multiple factors on battery degradation, which is of great significance for optimizing battery life (based on charging practice). Overall, these developments not only improve the accuracy of SOC estimation, but also contribute to extending battery life and enhancing battery operational reliability.
4. State of Health (SOH) assessment techniques
4.1 Traditional SOH estimation methods
The traditional SOH estimation method is widely used in academic and industrial fields, mainly based on basic parameters such as capacity degradation, internal resistance, and cycle life to evaluate battery SOH (see Table 4 for relevant formulas and parameter meanings). These methods provide a foundation for battery health assessment and help understand battery performance. By understanding these traditional methods, we can better understand the improvements of new estimation methods in subsequent chapters. New methods often use more complex data analysis and predictive modeling techniques to address the limitations of traditional methods. Comparing the two can clarify the development and evolution of SOH estimation technology and demonstrate how modern methods can improve the accuracy and adaptability of battery management systems.
4.2 New Developments in Replacing Traditional Methods
New health indicators combined with machine learning: To improve the accuracy of SOH prediction, research has introduced new health indicators such as Degradation Rate Ratio (DSR). The formula for calculating DSR from the slope of the charging voltage curve is:
By comparing the slopes of multiple charging cycles, the degradation rate (in mV/s) of the battery within a specific voltage range (such as [3.8-3.9V]) is determined, which is closely related to the battery capacity and can be used as a key indicator to determine the end of the battery life. Combining Gaussian Process Regression (GPR) and Multi Layer Perceptron Neural Network (MLPNN) models can more accurately estimate capacity loss and degradation. Compared with traditional models, sensitivity and accuracy are significantly improved, effectively solving the problem of traditional models being difficult to detect degradation early.
Improvement of equivalent circuit model: Early methods for improving traditional equivalent circuit models (ECM) continued to develop, such as estimating SOH by analyzing the body capacitance of the equivalent RC circuit model in 2015, using innovative algorithms to calculate the body capacitance attenuation factor, and combining it with discrete nonlinear observers to improve accuracy and reliability; In 2024, a second-order hybrid equivalent circuit model combined with adaptive update rate and nonlinear observer was adopted to consider the influence of temperature, achieving high accuracy in SOH estimation (average absolute error less than 0.5%, RMS error less than 0.2%); The cloud solution for 2023 utilizes long-term monitoring data and real-time data to estimate battery model parameters by adjusting the moving window least squares algorithm. Based on the ECM model, high-precision SOH evaluation is achieved, indicating that the improved ECM method still has significant importance in SOH estimation, consistent with the trend of continuous improvement of ECM methods in SOC estimation technology.
Hybrid Framework Method: The new framework integrates Linear Statistical k-Nearest Neighbor (LSKNN), Maximum Information Entropy Search (MIES), and Collective Sparse Variational Gaussian Process Regression (CSVGPR) for processing data interpolation, noise filtering, feature selection, and uncertainty management. LSKNN estimates missing data points and filters noise, MIES selects features with high correlation to SOH, and CSVGPR processes data uncertainty to improve prediction accuracy. This framework was tested using the NASA battery dataset, and compared with methods such as ElasticNet, Support Vector Regression (SVR), Random Forest, and Gradient Boosting, the Root Mean Square Error (RMSE) was reduced by 77.8% (from 0.0510 in ElasticNet to 0.0113). Compared with Gaussian process models with different kernels, the RMSE was reduced by 55.5% (from 0.0254 to 0.0113), confirming the robustness and high accuracy of the framework and providing a more accurate method for SOH estimation.
The development trend of SOH estimation technology is shifting from traditional methods to more complex models suitable for electric vehicles. New methods include combining degradation models with classical machine learning, ECM based methods, and hybrid methods. DSR is an important innovation that reduces reliance on a complete charging cycle (reducing waiting time by approximately 84%) and, when combined with machine learning, improves the accuracy of capacity loss estimation, overcoming the difficulty of early degradation detection in traditional models. The improved ECM method has achieved good results in SOH estimation, which is consistent with the importance of ECM method in SOC estimation. Hybrid technologies (such as the new framework mentioned above) have high accuracy. Although real-time applications pose challenges, effectively solving key data processing problems is a significant improvement over traditional SOH estimation methods. Overall, these developments focus on real-time applications and data-driven methods, significantly improving the reliability of electric vehicle battery management systems. Deep learning methods such as LSTM, CNNs, and hybrid techniques have become the mainstream methods for SOH estimation. Subsequent chapters will present relevant research results and contributions.
5. Application of Deep Learning in SOH Estimation
5.1 LSTM and Hybrid Models
Multiple studies have used improved aging models combined with deep learning techniques to enhance the accuracy of SOH estimation. Deep learning is indispensable in predicting Remaining Useful Life (RUL). For example, by integrating the SOH degradation model and considering various operating conditions such as charging/discharging current and temperature, a specific formula can be used to:
Among them, I2 {c} and I2 {d} are normalized charge and discharge currents, T3 {c} and T4 {d} are normalized battery and ambient temperatures, T3 {c} and T4 {d} are charge and discharge times, and (d1-d4) is a weight), which more accurately simulates battery degradation. The RUL prediction model based on LSTM network improves the prediction accuracy, but the computational complexity increases, and real-time applications face challenges. Neural networks can handle time-varying battery processes, continuously learn to adapt to changes in battery behavior, and maintain model reliability.
By extracting key features (such as 6 key features) to optimize SOH estimation, combined with machine learning algorithms to achieve high accuracy and low computational load, voltage features play a significant role in improving the accuracy of battery state assessment. Combining multiple deep learning models (such as CNN, LSTM, GRU, and their bidirectional variants) into a hybrid framework (such as CNN-LSTM-DNN, CNN-GRU-DNN) to predict RUL, utilizing a wide range of features to improve accuracy, reduced RMSE by 90.5% in NASA dataset testing, but the computational strength and complexity limit real-time applications. Multi model methods (such as LSTM model libraries) and advanced optimization strategies (such as integrating LSTM into the AI-BMS framework and implementing it on FPGA) can improve prediction accuracy and system efficiency, but the application of FPGA in commercial electric vehicles faces cost and practicality challenges.
The combination of GRU and soft sensing methods has the potential for long-term RUL prediction in laboratory environments, but practical applications require adaptation to different charging conditions. Using data-driven methods such as LSTM, DNN, and GRU to process NASA datasets, GRU has strong performance (RMSE of 0.003, MAE of 0.003, R-squared error of 0.004), and combining GRU and LSTM networks results in better performance. The LSTM based method extracts features (such as 5 manual features) by analyzing the battery charge discharge curve, and uses optimization algorithms (such as Adam) to improve training efficiency and prediction accuracy. Under the training of single battery partial data, the SOH estimation error for other batteries is low, which is better than traditional models.
The MDA-LSTM network combines multiple features and temporal information, and improves the accuracy of RUL prediction through multiple feature fusion modules and dual attention modules. It performs well in multi dataset validation, with robustness and generalization. The stacked BiLSTM network is used to predict SOH using constant current charging data, and the bidirectional structure improves prediction reliability, making it suitable for real-time SOH estimation during fast charging. The TCN-LSTM model utilizes synthetic data and Bayesian optimization to accurately reconstruct open circuit voltage (OCV) and estimate State of Health (SOH) (MAE below 22mV, MAPE below 2.2%). It can be extended to different battery chemical systems through transfer learning, but there are extrapolation limitations when data is insufficient. The deep fusion method (such as utilizing historical data and multiple health indicators) achieves high accuracy (MAPE below 2.97%) through full charge discharge testing, and both the global framework based on GPR and the DFTN model for individual electric vehicles have achieved good results.
5.2. CNN and CNN-LSTM Integrated Model
The CNN-WNN-WLSTM method integrates CNN, WNN, and WLSTM networks. CNN extracts features, WNN and WLSTM process features and estimate SOH. The RMSprop optimizer is used to improve performance and outperforms traditional methods in NASA dataset testing, providing a promising approach for battery health management. The CNN-LSTM-CRF model is inspired by natural language processing, with the CRF layer capturing output variable dependencies to improve the accuracy and intuitiveness of battery capacity prediction. However, the computational requirements are high and exceed the capabilities of onboard processors. In the future, research is needed to improve its practicality (such as through transfer learning). The LSTNet model improves battery capacity prediction performance by segmenting data, integrating ConvLSTM and AR components, and optimizing the structure (for example, in NASA dataset testing, RMSE was 0.65%, MAE was 0.58%, and MAPE was 0.435% when trained on 40% data).
By integrating enhanced CNN and ECSSA optimization algorithms to predict the RUL of solid-state lithium-ion batteries, CNN improves feature extraction and prediction accuracy by optimizing hyperparameters and structures (such as using advanced convolutional layers, activation functions, and residual connections), while ECSSA optimizes model parameters through innovative mathematical methods (such as Circle Chaotic Mapping, Nonlinear Absorption Coefficient, and Cauchy Mutation) to improve RUL prediction accuracy and robustness. Combining PCA and CNN for feature optimization and dimensionality reduction improves the accuracy and efficiency of SOH estimation (compared to traditional CNN and fixed dimensional PCA-CNN models, MAE increases by more than 20% and RMSE increases by more than 30%). The real-time SOH estimation model integrates 1D-CNN and BiGRU, using BMS data to avoid complex feature extraction, and achieving high accuracy through Bayesian optimization of hyperparameters (such as in NASA dataset testing, MAE is 2.080%, RMSE is 2.516%, and EOL index error is zero).
5.3. Optimization Strategies for Deep Learning Models
Firstly, the random forest algorithm was used to identify key health factors, and then the genetic algorithm particle swarm optimization (GA-PSO) technique was used to optimize the support vector regression (SVR) model parameters for estimating State of Health (SOH). The effectiveness was verified on four batteries, improving accuracy and convergence speed (RMSE of 0.40%, MAPE of 0.56%), which is superior to other related methods. The GWO-BRNN hybrid method utilizes grey wolf optimization (GWO) to select hyperparameters for Bayesian regularized neural networks (BRNN). Based on the NASA dataset, the SOH estimation error is less than 1%, but the computational complexity is high and practical applications are limited. Directly using the raw data of electric vehicles to evaluate SOH and predict RUL, improving accuracy by introducing new evaluation features and interpolation correction methods (reducing the relative error of current integration to 0.94%), combined with D-NSGA-II optimization method to further optimize SOH estimation and reduce computation time. In response to the difficulty in estimating State of Health (SOH) caused by incomplete charging and discharging of lithium-ion batteries in electric vehicles, an indirect estimation method (ATAGA-BP) is proposed. The method utilizes the characteristics of constant voltage charging stage as a health indicator and is validated through simulation with NASA data. The method has a high correlation with battery capacity (over 85%), with an SOH estimation error of 3.7% and an iterative efficiency improvement of 17.8%.
Deep learning has made significant progress in SOH estimation, and comprehensive models considering multiple factors provide a deeper understanding of battery degradation. LSTM networks are important in capturing temporal dependencies and predicting RUL, but their computational complexity poses challenges for real-time applications. Feature extraction methods are important and can optimize SOH estimation. The combination of hybrid models and different neural network architectures for processing battery data complexity has promising prospects, but high computational requirements limit practical applications. Optimization strategies such as GA-PSO, GWO-BRNN, and D-NSGA-II have improved accuracy and efficiency, but implementing complex algorithms is difficult and requires a balance between accuracy and execution simplicity. Advanced AI technology is crucial for the application of secondary batteries (lacking detailed usage data). Subsequent chapters will provide an overview of the current state of secondary application research, particularly in the area of battery reuse.
6. Summary
This article advances the development of SOH and SOC estimation for lithium-ion batteries in electric vehicles through innovative methods and models, covering various technologies from traditional machine learning to advanced deep learning models such as LSTM and CNN. However, each method has differences in accuracy, complexity, and applicability, making direct comparison difficult. Research has found that data processing and sources have a significant impact on model performance, and further validation is needed for actual deployment. Although deep learning models have shown advantages in processing complex data, they still face challenges such as high computational resource requirements and adaptability to practical application scenarios. Future research should focus on improving feature selection, anomaly detection, adapting to diverse environmental conditions, optimizing algorithms to enhance computational efficiency, achieving real-time applications, integrating multiple data sources to improve SOH estimation model performance, while also addressing challenges in secondary battery applications, developing effective solutions, and promoting the development of battery management systems to meet the growing demands in the fields of electric vehicles and energy storage.