Interpretable Grey-Box Residual Learning Framework for State-of-Health Prognostics in Electric Vehicle Batteries Using Real-World Data
Open Access
- 11 April 2026
- journal article
- research article
- Published by MDPI AG in World Electric Vehicle Journal
- Vol. 17 (4) , 201
Abstract
Conventional black-box models for electric vehicle (EV) battery State-of-Health (SOH) prediction achieve high accuracy but lack interpretability, limiting their practical deployment in Battery Management Systems (BMSs). To circumvent these limitations, this study proposes a novel Grey-Box Residual-Driven Framework (GBRDF) that synergizes Deep Symbolic Regression (DSR) with a residual-learning BiLSTM network with two contributions: (1) the DSR component derives explicit, interpretable mathematical expressions governing global degradation trajectories based on electrochemical features, and (2) the BiLSTM network models the residual errors to capture high-frequency nonlinearities and complex sequential dependencies not addressed by the symbolic baseline. By fusing the physics-informed transparency of DSR with the data-driven refinement of BiLSTM, the GBRDF significantly enhances forecasting precision. Experimental validation across four independent EV datasets shows that the GBRDF achieves the highest coefficient of determination (R2) of 0.982, and the lowest mean absolute error (MAE) of 0.1398 and root mean square error (RMSE) of 0.3176, significantly outperforming existing methods. Furthermore, the DSR-derived SOH equation shows that battery degradation is primarily driven by high voltage exposure and charging time, with mathematical transformations reflecting how degradation accelerates initially then slows, matching real-world aging patterns where voltage stress dominates over temperature and usage variations.Keywords
Funding Information
- Taylor’s University (PARTNERSHIP/XMUM/2026/SOE/001)
This publication has 31 references indexed in Scilit:
- A survey of transformer networks for time series forecastingComputer Science Review, 2025
- Cross-domain battery SOH and RUL estimation via Domain-Adaptive TransformerEnergy, 2025
- Quantum Neural Network and Gaussian Process Framework for Lithium Battery State of Health PredictionEnergy Storage, 2025
- Exploring life warning solution of lithium-ion batteries in real-world scenarios: TCN-transformer fusion model for battery pack SOH estimationEnergy, 2025
- A novel BA-ABC-ELM model for estimating state of health of lithium-ion batteriesEnergy Reports, 2024
- Improving electric vehicles sustainability: Accurate forecasting of lithium-ion battery health using machine learning modelsJournal of Energy Storage, 2024
- State of health estimation for lithium-ion batteries based on improved bat algorithm optimization kernel extreme learning machineJournal of Energy Storage, 2024
- Prognostics of battery capacity based on charging data and data-driven methods for on-road vehiclesApplied Energy, 2023
- A state of health estimation framework based on real-world electric vehicles operating dataJournal of Energy Storage, 2023
- A review on methods for state of health forecasting of lithium-ion batteries applicable in real-world operational conditionsJournal of Energy Storage, 2022