Estimation of Lithium Battery State of Health Using Hybrid Deep Learning with Multi-Step Feature Engineering and Optimization Algorithm Integration

Accurate state of health (SOH) estimation of lithium-ion batteries is critical for maintaining reliable and safe working conditions for electric vehicles (EVs). The machine learning-based method with health features (HFs) is encouraging for health prognostics. However, the machine learning method assumes that the training and testing data have the same distribution, which restricts its application for different types of batteries. Thus, in this paper, a deep learning neural network and fine-tuning-based transfer learning strategy are proposed for accurate and robust SOH estimation toward different types of batteries. First, a universal HF extraction strategy is proposed to obtain four highly related HFs. Second, a deep learning neural network consisting of long short-term memory (LSTM) and fully connected layers is established to model the relationship between the HFs and SOH. Third, the fine-tuning-based transfer learning strategy is exploited for SOH estimation of various types of batteries. The proposed methods are comprehensively verified using three open-source datasets. Experimental results show that the proposed deep learning neural network with the HFs can estimate the SOH accurately in a single dataset without using the transfer learning strategy where the mean absolute error (MAE) and root mean square error (RMSE) are constrained to 1.21% and 1.83%. For the transfer learning between different aging datasets, the overall MAE and RMSE are limited to 1.09% and 1.41%, demonstrating the reliability of the fine-tuning strategy.

Achieving accurate battery state of health (SOH) estimation is crucial, but existing methods still face many challenges in terms of data quality, computational efficiency, and cross-scenario generalization capabilities. This study proposes a hybrid deep learning framework incorporating transfer learning to address these challenges. The framework integrates inception depthwise convolution (IDC), channel reduction attention (CRA) mechanism, and staged training strategy to improve the accuracy and generalization ability of SOH estimation. The IDC module of the proposed model is capable of extracting battery degradation time series features from multiple scales while reducing the computational overhead. The CRA module effectively reduces the computational complexity and memory usage of global feature capture by compressing the channel dimensions. A well-designed pre-training/fine-tuning two-stage training strategy achieves accurate cross-scene SOH estimation by utilizing large-scale source-domain data to learn generalized aging features and then uses a small amount of new data to quickly fine-tune the base model. The proposed method is validated using two publicly available datasets, including 54 nickel cobalt manganese oxide (NCM) cells and 16 nickel manganese cobalt oxide (NMC) cells. The experimental results show that the root mean square error (RMSE) of the model on the NCM and NMC datasets is 0.522% and 0.283%, respectively, with a coefficient of determination (R2) not less than 0.98 and mean absolute percentage error (MAPE) of 0.431% and 0.22%, respectively. The proposed method not only achieves high-precision SOH estimation among the same type of batteries but also demonstrates strong generalization ability under different battery chemistries and scenarios.

An interpretable state of health estimation method for lithium-ion batteries based on multi-category and multi-stage features

State of health estimation of lithium-ion batteries based on Mixers-bidirectional temporal convolutional neural network

A novel nonlinear decreasing step-bacterial foraging optimization algorithm and simulated annealing-back propagation model for long-term battery state of health estimation

The state of health (SOH) of lithium-ion batteries is a crucial parameter for assessing battery degradation. The aim of this study is to solve the problems of single extraction of health features (HFs) and redundancy of information between features in the SOH estimation. This article develops an SOH estimation method for lithium-ion batteries based on multifeature fusion and Bayesian optimization (BO)-bidirectional gated recurrent unit (BiGRU) model. First, a total of eight HFs in three categories, namely, time, energy, and probability, can be extracted from the charging data to accurately describe the aging mechanism of the battery. The Pearson and Spearman analysis method verified the strong correlation between HFs and SOH. Second, the multiple principal components obtained by kernel principal component analysis (KPCA) can eliminate the redundancy of information between HFs. The principal component with the highest correlation with SOH is selected by bicorrelation analysis to be defined as the fused HF. Finally, to improve SOH estimation accuracy, the BO-BiGRU model is proposed. The proposed method is validated using battery datasets from NASA. The results show that the SOH estimation accuracy of the BO-BiGRU model proposed in this article is high, while mean absolute error (MAE) is lower than 1.2%. In addition, the SOH of the lithium battery is estimated using different proportions of test sets, and the results show that the root-mean-square error (RMSE) and the mean absolute percentage error (MAPE) of the SOH remain within 3%, with high estimation accuracy and robustness.

To address the problem of predicting the state of health (SOH) of lithium-ion batteries, this study develops three models optimized using the particle swarm optimization (PSO) algorithm, including the long short-term memory (LSTM) network, convolutional neural network (CNN), and support vector regression (SVR), for accurate SOH estimation. Key features were extracted by analyzing the temperature, voltage, and current curves of the battery, and health factors with high correlation to SOH were selected as model inputs using the Pearson correlation coefficient. The PSO algorithm was employed to optimize model parameters, resulting in the construction of three predictive models: PSO-LSTM, PSO-CNN, and PSO-SVR. The models were validated using the NASA PCoE battery aging datasets B0005, B0006, and B0007, with prediction accuracy evaluated based on Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R2). Results indicate that the optimized models achieved significant improvements in prediction accuracy, with RMSE and MAE reduced by over 0.5%, a minimum reduction of 38% in MAPE, and R2 exceeding 0.8, demonstrating strong fitting capabilities and validating the effectiveness of the PSO strategy. Among the three models, PSO-LSTM exhibited the best predictive performance, achieving a minimum MAE of 0.67%, RMSE of 0.94%, MAPE of 45.82%, and R2 as high as 0.9298 across the three datasets. These findings suggest that the PSO-LSTM model provides a robust reference for accurate SOH prediction of lithium-ion batteries and shows promising potential for practical applications.

Co-estimation of state of health and remaining useful life for lithium-ion batteries using a hybrid optimized framework

Efficient and accurate state of health (SoH) estimation is an important challenge for safe and efficient management of batteries. This paper proposes a fast and efficient online estimation method for lithium-ion batteries based on incremental capacity analysis (ICA), which can estimate SoH through the relationship between SoH and capacity differentiation over voltage (dQ/dV) at different states of charge (SoC). This method estimates SoH using arbitrary dQ/dV over a large range of charging processes, rather than just one or a limited number of incremental capacity peaks, and reduces the SoH estimation time greatly. Specifically, this method establishes a black box model based on fitting curves first, which has a smaller amount of calculation. Then, this paper analyzes the influence of different SoC ranges to obtain reasonable fitting curves. Additionally, the selection of a reasonable dV is taken into account to balance the efficiency and accuracy of the SoH estimation. Finally, experimental results validate the feasibility and accuracy of the method. The SoH estimation error is within 5% and the mean absolute error is 1.08%. The estimation time of this method is less than six minutes. Compared to traditional methods, this method is easier to obtain effective calculation samples and saves computation time.

Accurate estimation of lithium-ion batteries' state of health (SOH) is critical for ensuring the efficient, safe, and long-lasting operation of battery systems. To address the challenge of insufficient feature information extraction and SOH estimation under complex operating conditions, a SOH estimation method based on multisource feature extraction and the Sparrow Search Algorithm-Long Short-term Memory Network (SSA-LSTM) is proposed. First, the initial health feature set is constructed by fusing the empirical, statistical and mechanistic dimensions of features. Second, to mitigate the impact of feature redundancy, the features are evaluated and ranked based on both correlation and importance, thereby optimizing the balance between feature quality and quantity. Finally, the obtained optimal feature set is used as input to the SSA-LSTM algorithm, which constructs a SOH estimation algorithm for accurate battery SOH estimation. Experimental results demonstrate that the proposed feature selection method successfully identifies the optimal feature set. Compared with other estimation algorithms, the SSA-LSTM algorithm outperforms in all evaluation indexes, with the maximum root-mean-square error (RMSE) and mean absolute percentage error (MAPE) of the estimation results reaching 0.73% and 0.53%, respectively, across various test cases.

Rapid and accurate state of health (SOH) estimation of retired batteries is a crucial pretreatment for reuse and recycling. However, data-driven methods require exhaustive data curation under random SOH and state of charge (SOC) retirement conditions. Here, we show that the generative learning-assisted SOH estimation is promising in alleviating data scarcity and heterogeneity challenges, validated through a pulse injection dataset of 2700 retired lithium-ion battery samples, covering 3 cathode material types, 3 physical formats, 4 capacity designs, and 4 historical usages with 10 SOC levels. Using generated data, a regressor realizes accurate SOH estimations, with mean absolute percentage errors below 6% under unseen SOC. We predict that assuming uniform deployment of the proposed technique, this would save 4.9 billion USD in electricity costs and 35.8 billion kg CO2 emissions by mitigating data curation costs for a 2030 worldwide battery retirement scenario. This paper highlights exploiting limited data for exploring extended data space using generative methods, given data can be time-consuming, expensive, and polluting to retrieve for many estimation and predictive tasks.

With the development of electric vehicles, the demand for lithium-ion batteries has been increasing annually. Accurately estimating the state of health (SOH) of lithium-ion batteries is crucial for their efficient and reliable use. Most of the existing research on SOH estimation is based on parameters such as current, voltage, and temperature, which are prone to fluctuations. Estimating the SOH of lithium-ion batteries based on electrochemical impedance spectroscopy (EIS) and data-driven approaches has been proven effective. In this paper, we explore a novel SOH estimation model for lithium batteries based on EIS and Convolutional Neural Network (CNN)-Vision Transformer (VIT). The EIS data are treated as a grayscale image, eliminating the need for manual feature extraction and simultaneously capturing both local and global features in the data. To validate the effectiveness of the proposed model, a series of simulation experiments are conducted, comparing it with various traditional machine learning models in terms of root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and coefficient of determination (R2). The simulation results demonstrate that the proposed model performs best overall in the testing dataset at three different temperatures. This confirms that the model can accurately and stably estimate the SOH of lithium-ion batteries without requiring manual feature extraction and knowledge of battery aging temperature.

Adaptive state of health estimation for lithium-ion batteries using impedance-based timescale information and ensemble learning

Lithium battery health state assessment based on vehicle-to-grid (V2G) real-world data and natural gradient boosting model

Lithium‐ion batteries play a crucial role in energy storage for mobile electronics, electric vehicles, and renewable energy systems, where accurate state of health (SOH) estimation is essential to ensure system reliability and operational safety. However, achieving high‐precision data‐driven SOH estimation involves overcoming significant challenges in feature extraction, processing, and model training. To tackle these challenges, this article proposes a novel SOH estimation method integrating Savitzky–Golay (SG) filter with Crested Porcupine Optimizer (CPO)‐enhanced Support Vector Machine (SVM). First, representative health features correlated with capacity degradation are systematically extracted from charge voltage, current, and incremental capacity curves using Kendall correlation analysis. Subsequently, SG filter is employed for noise reduction and data smoothing, significantly enhancing the stability and reliability of the input parameters while preserving critical information. Furthermore, to achieve high‐accuracy SOH estimation, a CPO‐SVM framework is proposed. By dynamically adjusting the penalty coefficient and kernel function hyperparameters, this approach effectively addresses the local optimum issue commonly encountered in traditional SVM methods. Finally, the proposed method is validated using datasets from NASA, CALCE, and Oxford, demonstrating superior performance with root mean square error < 0.0073, mean absolute error < 0.0058, and R2 > 98.5%. These results highlight substantial improvements in both accuracy and reliability of SOH estimation.