Accurate State of Health (SOH) estimation is critical for ensuring the safe operation of lithium-ion batteries. However, current data-driven approaches face significant challenges: insufficient feature extraction and ambiguous physical meaning compromise prediction accuracy, while initialization sensitivity to noise undermines stability; the inherent nonlinearity and temporal complexity of battery degradation data further lead to slow convergence or susceptibility to local optima. To address these limitations, this study proposes an enhanced CNN-BIGRU model. The model replaces conventional random initialization with a Hiking Optimization Algorithm (HOA) to identify superior initial weights, significantly improving early training stability. Furthermore, it integrates an Attention mechanism to dynamically weight features, strengthening the capture of key degradation characteristics. Rigorous experimental validation, utilizing multi-dimensional features extracted from the NASA dataset, demonstrates the model’s superior convergence speed and prediction accuracy compared to the CNN-BIGRU-Attention benchmark. Compared with other methods, the HOA-CNN-BIRGU-Attention model proposed in this study has a higher prediction accuracy and better robustness under different conditions, and the RMSEs on the NASA dataset are all controlled within 0.01, with R2 kept above 0.91. The RMSEs on the University of Maryland dataset are all below 0.006, with R2 kept above 0.98. Compared with the CNN-BIGRU-ATTENTION baseline model without HOA optimization, the RMSE is reduced by at least 0.15% across different battery groups in the NASA dataset.

Accurate state of health (SOH) estimation of lithium-ion batteries (LIBs) is critical to ensuring the safety and reliability of battery management system (BMS). To achieve precise estimation, this study proposes a hybrid framework that integrates variational mode decomposition (VMD), kernel principal component analysis (KPCA), polar lights optimizer (PLO), and physics-informed neural network (PINN) for SOH estimation. First, multidimensional health features are extracted and decomposed by VMD into intrinsic mode functions (IMFs), which are then compressed into a one-dimensional principal component via KPCA, retaining over 95% of the original information. Subsequently, the PLO algorithm is used to adaptively optimize three key hyperparameters of the PINN-based model: the learning rate, the number of collocation points, and the regularization loss weight. Finally, the optimized PINN is deployed to predict the SOH of the Center for Advanced Life Cycle Engineering (CALCE) battery dataset. Experimental results demonstrate that the proposed VMD-KPCA-PLO-PINN exhibits high prediction accuracy under both 7:3 and 5:5 training-to-testing data partitions. For example, under the 5:5 partition, the proposed model achieves an average $R^2$ of 0.983 and an average RMSE of 0.0085 on the tested CALCE cells.