An Adaptive-Weight Physics-Informed Neural Network Optimized by Grey Wolf Optimizer for Lithium-Ion Battery State of Health Estimation
Open Access
Abstract
Reliable estimation of the State of Health (SOH) in lithium-ion batteries is critical to battery system security and dependability. However, existing Physics-Informed Neural Networks (PINNs) have drawbacks like single-feature physical constraints, rigid fixed-weight fusion of multi-feature constraints and insufficient time-series degradation modeling. To solve these problems, this study proposes an Adaptive-Weight PINN (AW-PINN) optimized by the Grey Wolf Optimizer (GWO) algorithm, which features a dual-LSTM parallel structure and takes incremental capacity peaks and charged capacity as dual physical constraints. A weight generator LSTM adaptively learns weights for monotonicity losses without manual intervention, and GWO globally optimizes physical loss weights to balance data fitting accuracy and prediction physical consistency. Validated on , NCA, and NCM batteries from CALCE and Tongji University datasets via comparative, ablation, and small-sample experiments, AW-PINN shows superior predictive performance (average RMSE = 0.0076; MAE = 0.0065; MAPE = 0.0072), robustness, and generalization. It integrates battery degradation physics with deep learning, retaining strong fitting capability while enabling physical interpretability.
Keywords
Funding Information
- shandong provincial key research and development program (ZFJH202301)
- National Natural Science Foundation of China (62133007)
This publication has 49 references indexed in Scilit:
- A sparse SOH estimation framework based on clustered voltage segments and multi-head CNN under arbitrary charging conditionEnergy, 2026
- Transformer-based framework for configuration-agnostic Li-ion battery SoH estimation by exploring novel health indicatorsChemical Engineering Journal, 2025
- Optimized FNN-Based SOH Estimation: Methodology and Performance Analysis2025
- Data driven-based health prognostics and charge estimation for lithium-ion batteries under varying discharging patternsEnergy, 2025
- A generic physics-informed neural network framework for lithium-ion batteries state of health estimationEnergy, 2025
- A method for estimating lithium-ion battery state of health based on physics-informed hybrid neural networkElectrochimica Acta, 2025
- A method for estimating the state of health of lithium-ion batteries based on physics-informed neural networkEnergy, 2024
- GWO: a review and applicationsInternational Journal of System Assurance Engineering and Management, 2020
- Particle swarm optimization (PSO). A tutorialChemometrics and Intelligent Laboratory Systems, 2015
- Grey Wolf OptimizerAdvances in Engineering Software, 2014