Qi Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qi Wei has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Ao Xu
School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
1 shared publication - Jiayan Wen
School of Automation, Guangxi University of Science and Technology, Liuzhou 545616, China
1 shared publication - Jingjing Lu
School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
1 shared publication - Kene Li
School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
1 shared publication - Yuewu Wang
School of Automation, Guangxi University of Science and Technology, Liuzhou, China
1 shared publication - Zaojun Chen
School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
1 shared publication
Latest Publications
- Open Access
- 10 December 2025
- Published by MDPI AG in Electronics
- Vol. 14 (24) , 4859
Estimation of Lithium-Ion Battery SOH Based on a Hybrid Transformer–KAN Model
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.
- 10 December 2025
- Published by MDPI AG in Electronics
- Vol. 14 (24) , 4859
Open AccessEstimation of Lithium-Ion Battery SOH Based on a Hybrid Transformer–KAN Model
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.