Estimation of Lithium-Ion Battery SOH Based on a Hybrid Transformer–KAN Model
Open Access
- 10 December 2025
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 14 (24) , 4859
Abstract
As a critical energy component in electric vehicles, energy storage systems, and other applications, the accurate estimation of the State of Health (SOH) of lithium-ion batteries is crucial for performance optimization and safety assurance. To this end, this paper proposes a hybrid model named Transformer–KAN, which integrates Transformer architecture with Kolmogorov–Arnold Networks (KANs) for precise SOH estimation of lithium-ion batteries. Initially, five health features (HF1–HF5) strongly correlated with SOH degradation are extracted from the historical charge–discharge data, including constant-voltage charging duration, constant-voltage charging area, constant-current discharging area, temperature peak time, and incremental capacity curve peak. The effectiveness of these features is systematically validated through Pearson correlation analysis. The proposed Transformer–KAN model employs a Transformer encoder to capture long-term dependencies within temporal sequences, while the incorporated KAN enhances the model’s nonlinear mapping capability and intrinsic interpretability. Experimental validation conducted on the NASA lithium-ion battery dataset demonstrates that the proposed model outperforms comparative baseline models, including CNN–LSTM, Transformer, and KAN, in terms of both RMSE and MAE metrics. The results indicate that the Transformer–KAN model achieves superior estimation accuracy while exhibiting enhanced generalization capabilities across different battery instances, indicating its strong potential for practical battery management applications.Keywords
Funding Information
- Doctoral Fund Project of Guangxi University of Science and Technology (22Z23)
- Specific Research Project of Guangxi for Research Bases and Talents (AD22080004)
This publication has 26 references indexed in Scilit:
- Battery state-of-health estimation using CNNs with transfer learning and multi-modal fusion of partial voltage profiles and histogram dataApplied Energy, 2025
- EnerNet: Attention-based dilated CNN-BILSTM for state of health prediction of CS2 prismatic cells in energy systemsElectrochimica Acta, 2024
- A novel state of health estimation model for lithium-ion batteries incorporating signal processing and optimized machine learning methodsFrontiers in Energy, 2024
- State of health estimation method for lithium-ion batteries using incremental capacity and long short-term memory networkJournal of Energy Storage, 2023
- An improved method of state of health prediction for lithium batteries considering different temperatureJournal of Energy Storage, 2023
- A novel state-of-health estimation for the lithium-ion battery using a convolutional neural network and transformer modelEnergy, 2022
- State of health estimation for lithium-ion battery based on energy featuresEnergy, 2022
- Feature-based lithium-ion battery state of health estimation with artificial neural networksJournal of Energy Storage, 2022
- An electrochemical model based degradation state identification method of Lithium-ion battery for all-climate electric vehicles applicationApplied Energy, 2018
- State-of-health estimation of lithium-ion battery packs in electric vehicles based on genetic resampling particle filterApplied Energy, 2016