Enhanced Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM) attention model with adaptive loss for lithium-ion battery state of health estimation

This study proposes an enhanced deep learning framework for accurately estimating the state of health (SOH) of lithium-ion batteries (LIBs), leveraging a refined Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM)-Attention architecture. To improve prediction accuracy and robustness, a novel Multi-Scale Adaptive Wasserstein-Huber Loss (MSAWH Loss) is introduced, which combines the strengths of Huber loss and multi-scale Wasserstein distance to effectively handle outliers and capture complex degradation patterns. Furthermore, an Uncertainty-Guided Adaptive Bayesian Optimization (UGABO) algorithm is employed to optimize model hyperparameters, achieving efficient convergence in high-dimensional and noisy parameter spaces while maintaining a balance between exploration and exploitation. To enhance generalization, four complementary data augmentation techniques—linear interpolation, data slicing, sequence flipping, and cross-sample mixing—are applied to the National Aeronautics and Space Administration (NASA) charge-discharge dataset, significantly enriching the training data. Additionally, a Model Predictive Control (MPC) mechanism is integrated to correct long-horizon prediction errors, dynamically refining outputs based on recent deviations and maintaining consistency with real-world battery constraints. Experimental results demonstrate that the proposed framework outperforms baseline models, achieving a 20.6% reduction in mean absolute error (MAE), an 18.6% reduction in root mean squared error (RMSE), and a 0.1% improvement in R-squared (R 2 ). These findings highlight the effectiveness of integrating adaptive loss design, automated hyperparameter optimization, strategic data augmentation, and feedback-based error correction in advancing SOH prediction performance for lithium-ion batteries.