A Lithium-Ion Battery Remaining Useful Life Prediction Framework Based on Mode Decomposition and CNN-TimeXer

Exploiting Capacity Regeneration Based on a Hybrid Model to Accurately Predict the Remaining Useful Life of Lithium-Ion Batteries

Accurate prediction of the remaining useful life (RUL) of lithium-ion batteries is essential for the reliability and safety of modern energy systems. However, the capacity regeneration phenomenon, a temporary recovery of capacity during cycling or rest, introduces non-monotonic fluctuations in degradation trajectories, posing significant challenges to existing prediction models.Many current approaches treat CR as noise or overlook its physical significance, limiting interpretability and accuracy. To address this, we propose a hybrid framework that explicitly models both regenerative and degenerative battery behaviors. The method uses Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) to decompose capacity sequences into high-and low-frequency components. A Graph Convolutional Network-Long Short-Term Memory (GCN-LSTM) branch captures dynamic regeneration features, while a Deep Neural Network (DNN) branch learns long-term degradation trends. These are fused to reconstruct the full degradation path and predict RUL. The CEEMDAN-GCN-LSTM-DNN hybrid model achieves a mean absolute percentage error below 0.15%, outperforming several state-of-the-art baselines. It also demonstrates strong robustness under data-limited conditions and effectively captures complex capacity regeneration patterns often missed by conventional methods. This study offers a new perspective for handling non-monotonic battery degradation and provides a useful tool for battery health management and predictive maintenance.

Lithium battery SOH prediction based on modal decomposition and optimized transformer-bilstm framework with multi-strategy adaptive beaver behavior optimizer

Accurate prediction of the State of Health (SOH) of lithium batteries is essential for ensuring safe operation, prolonging battery service life and optimizing energy management. Battery degradation is characterized by strong nonlinearity, multi-factor coupled interference and data redundancy. Furthermore, prevailing hybrid prediction models are constrained by several inherent limitations: insufficient feature extraction, limited optimization capacity of conventional algorithms, and oversimplified modular integration. To tackle these challenges, this paper proposes an SOH prediction method based on Variational Mode Decomposition (VMD) and the Transformer-Bidirectional Long Short-Term Memory (BiLSTM) framework optimized by the Multi-Strategy Adaptive Beaver Behavior Optimizer (MSA-BBO). First, multi-dimensional health features are extracted from raw data. Second, the VMD algorithm is employed to decompose and reconstruct multi-dimensional health features (such as charging voltage and current) in the training set, thereby suppressing noise and extracting critical aging characteristics. The obtained processing scheme is then directly applied to the test set. Subsequently, a Transformer-BiLSTM hybrid framework is established, where the Transformer captures long-range temporal dependencies and the BiLSTM extracts bidirectional correlation features of data, thereby synergistically overcoming the limitations of single-structure models. To address the deficiencies of the original Beaver Behavior Optimizer (BBO), including insufficient utilization of elite information, convergence oscillation, and non-targeted perturbation, the algorithm is improved in four aspects: population evolution, exploration-exploitation balance, local optimization, and global escape. The developed MSA-BBO is employed for adaptive hyperparameter optimization. In contrast to existing dual-module hybrid models, the proposed method establishes a three-stage collaborative framework that integrates feature processing, feature mining, and hyperparameter optimization. Finally, comparative experiments with five other models are conducted to objectively evaluate the prediction accuracy, stability, and generalization ability of the proposed model. The experimental results demonstrate that the proposed model achieves the optimal overall performance on five test sets, with all coefficients of determination (R2) above 0.94 and all Mean Absolute Percentage Error (MAPE) values below 0.04. This research can provide reliable technical support and theoretical reference for the full-life cycle health management of lithium batteries.

A coordinate-aware Mamba2 framework for remaining useful life prediction of lithium-ion battery

Early Prediction of Lithium-Ion Battery Remaining Useful Life Using a GWO-Optimized CNN–Transformer–BiGRU Network

Lithium-ion batteries are widely used in various energy sectors, and accurately predicting their early remaining useful life (RUL) is crucial for shortening battery evaluation time and accelerating battery commercialization. However, information on degradation during the early cycling stages of batteries is limited, and it is difficult to fully characterize their lifespan. This study proposes a CNN–Transformer–BiGRU-based method for predicting the early RUL of lithium-ion batteries using Grey Wolf Optimization (GWO). First, using only the first 100 cycles of each battery in the MIT dataset, early degradation features are extracted from the dimensions of capacity and internal resistance, and then standardized. Second, a CNN is employed to extract local degradation features, while the Transformer’s self-attention mechanism is used to capture global correlations, and BiGRU is utilized to further extract bidirectional temporal dependency information. Building on this foundation, GWO is introduced to perform joint optimization of the model’s key hyperparameters to obtain optimal network parameters. Finally, the effectiveness of the proposed method is validated through ablation and comparison experiments. The experimental results show that the proposed model achieved an R2 of 0.9633, with RMSE, MAE, and MAPE values of 80.5608 cycles, 63.2524 cycles, and 7.29%, respectively, demonstrating overall prediction performance superior to that of the comparison models. This method can effectively mine degradation information related to battery life from limited early-cycle data, providing an effective approach for the accurate prediction of the early RUL of lithium-ion batteries.

Hybrid temporal deep learning and ensemble regression framework for remaining useful life prediction of lithium-ion batteries in energy storage systems

Accurate prediction of the remaining useful life (RUL) of lithium-ion batteries (LIBs) is essential for enhancing the reliability, operational safety, and energy management efficiency of electric vehicles and modern energy storage systems. However, battery degradation is governed by highly nonlinear electrochemical mechanisms and complex temporal dependencies that are difficult to model using conventional physics-based approaches or standalone machine learning techniques. To address these challenges, this article proposes a hybrid data-driven framework integrating a Temporal Convolutional Network (TCN), Bidirectional Long Short-Term Memory (BiLSTM), and Extreme Gradient Boosting (XGBoost) for accurate LIB RUL prediction. The proposed architecture utilizes the TCN module to capture short-term temporal degradation patterns from sequential battery operational data, while the BiLSTM network learns long-term temporal dependencies and degradation evolution across multiple charge–discharge cycles. The deep temporal representations extracted by the TCN–BiLSTM network are subsequently processed using an XGBoost regression model to effectively model nonlinear relationships between battery operational characteristics and RUL. The framework is validated using the NASA LIB aging dataset containing 14,896 charge–discharge cycle samples with operational features including cycle index, discharge time, charging duration, voltage degradation characteristics, and constant-current charging behavior. Statistical analysis and Min–Max normalization are employed to improve feature consistency, numerical stability, and model convergence. Experimental results demonstrate that the proposed framework effectively captures battery degradation dynamics and achieves highly accurate and stable prediction performance. Five-fold cross-validation results yield a low Mean Absolute Error of 0.00957, Root Mean Square Error of 0.02926, and a high coefficient of determination ( R 2 ) of 0.9882, indicating excellent predictive capability and strong generalization performance. Comparative analysis further demonstrates that the proposed hybrid framework outperforms conventional Random Forest, XGBoost, LSTM, and BiLSTM models in terms of prediction accuracy and robustness. In addition, ablation analysis confirms the complementary contribution of temporal convolutional learning, sequential dependency modeling, and ensemble nonlinear regression toward improved RUL estimation. The proposed framework provides a robust and computationally efficient solution for intelligent battery health monitoring, predictive maintenance, and smart battery management applications in electric vehicles and energy storage systems.

A review of deep learning-based methods for lithium-ion battery remaining useful life prediction

Against the backdrop of the global energy transition and the "dual carbon" goals, the safety and reliability issues caused by lithium-ion battery aging are in urgent need of resolution, and Remaining Useful Life (RUL) prediction serves as a core technical measure. Traditional mechanistic models and shallow machine learning methods struggle to adapt to the complex nonlinear characteristics of battery aging. Thanks to its strong capabilities in feature extraction and modeling, deep learning has become the core research direction for lithium-ion battery RUL prediction. This paper systematically sorts out and analyzes the application progress of four deep learning methods, namely RNN, LSTM, CNN and Transformer, elaborating on their technical principles, advantages, application scenarios and limitations. It also points out the common problems of all these models, including insufficient interpretability of the "black box" and lack of support from electrochemical mechanisms. Finally, two research directions are proposed: integrating mechanistic principles with deep learning modeling, and advancing the lightweight design of models, which provides a reference for the selection, optimization and engineering implementation of relevant models.