RESEARCH PAPER
Source-Free Joint SOC/SOH Estimation for Lithium-ion Batteries via Task-Specific Adapters and Interaction Attention
1
School of Computer, University of Electronic Science and Technology of China, Zhongshan Institute, China
2
School of Computer Science and Engineering, University of Electronic Science and Technology of China, China
3
Guangdong University of Technology, China
A – Conceptualization; B – Methodology; C – Software; D – Validation; E – Formal analysis; F – Investigation; G – Resources; H – Data curation; I – Writing – original draft; J – Writing – review & editing; K – Visualization; L – Supervision; M – Project administration; N – Funding acquisition
Submission date: 2026-02-14
Final revision date: 2026-04-21
Acceptance date: 2026-06-25
Online publication date: 2026-07-16
Corresponding author
Yi Lv
School of Computer, University of Electronic Science and Technology of China, Zhongshan Institute, China
School of Computer, University of Electronic Science and Technology of China, Zhongshan Institute, China
KEYWORDS
TOPICS
ABSTRACT
In some practical applications, source domain data are unavailable during transfer stage due to constraints such as data privacy and commercial confidentiality. This limitation presents a major challenge for cross-condition estimation of lithium-ion batteries. To address this scenario, this paper proposes a Source-Free Joint Estimation framework for the simultaneous prediction of State of Charge (SOC) and State of Health (SOH). The framework disentangles general and task-specific representations through a shared backbone, two parallel task-specific modules, and a subsequent task interaction attention mechanism. During the transfer stage, the backbone is frozen, and only three lightweight task modules are fine-tuned using target-domain data. This training strategy enables parameter-efficient and accurate adaptation while mitigating catastrophic forgetting. Experimental results on the MIT dataset demonstrate that the proposed method achieves improved joint SOC and SOH estimation under diverse charging policies, highlighting its strong transferability in source-free settings.
REFERENCES (46)
1.
Li D, Deng J, Zhang Z, Wang Z, Zhou L, Liu P. Battery Safety Risk Assessment in Real-World Electric Vehicles Based on Abnormal Internal Resistance Using Proposed Robust Estimation Method and Hybrid Neural Networks. IEEE Transactions on Power Electronics 2023; 38(6): 7661-7673. https://doi.org/10.1109/tpel.2....
2.
Wen J, Zhao D, Zhang C. An overview of electricity powered vehicles: Lithium-ion battery energy storage density and energy conversion efficiency. Renewable Energy 2020; 162: 1629-1648. https://doi.org/10.1016/j.rene....
3.
Xia B, Qin Z, Fu H. Rapid estimation of battery state of health using partial electrochemical impedance spectra and interpretable machine learning. Journal of Power Sources 2024; 603: 234413. https://doi.org/10.1016/j.jpow....
4.
Tao Z, Zhao Z, Wang C, Huang L, Jie H, Li H, Hao Q, Zhou Y, See KY. State of charge estimation of lithium batteries: Review for equivalent circuit model methods. Measurement 2024; 236: 115148. https://doi.org/10.1016/j.meas....
5.
Bavand A, Khajehoddin SA, Ardakani M, Tabesh A. Online Estimations of Li-Ion Battery SOC and SOH Applicable to Partial Charge/Discharge. IEEE Transactions on Transportation Electrification 2022; 8(3): 3673-3685. https://doi.org/10.1109/tte.20....
6.
Lyu Y, Wen Z, Chen A. A novel transfer learning approach based on deep degradation feature adaptive alignment for remaining useful life prediction with multi-condition data. Journal of Intelligent Manufacturing 2025; 36(1): 619-637. https://doi.org/10.1007/s10845....
7.
Luo X, Bu W, Liang H, Zheng M. Convolutional Neural Network - Gated Recurrent Unit combined with Error Correction for Lithium Battery State of Health Estimation. Eksploatacja i Niezawodność – Maintenance and Reliability 2025; 27(4): 202184. https://doi.org/10.17531/ein/2....
8.
Zhang Q, Wan G, Li C, Li J, Liu X, Li M. State of charge estimation for Li-ion battery during dynamic driving process based on dual-channel deep learning methods and conditional judgement. Energy 2024; 294: 130948. https://doi.org/10.1016/j.ener....
9.
Li C, Han X, Zhang Q, Li M, Rao Z, Liao W, Liu X, Liu X, Li G. State-of-health and remaining-useful-life estimations of lithium-ion battery based on temporal convolutional network-long short-term memory. Journal of Energy Storage 2023; 74: 109498. https://doi.org/10.1016/j.est.....
10.
Yang K, Tang Y, Zhang S, Zhang Z. A deep learning approach to state of charge estimation of lithium-ion batteries based on dual-stage attention mechanism. Energy 2022; 244: 123233. https://doi.org/10.1016/j.ener....
11.
Gu X, See KW, Li P, Shan K, Wang Y, Zhao L, Lim KC, Zhang N. A novel state-of-health estimation for the lithium-ion battery using a convolutional neural network and transformer model. Energy 2023; 262: 125501. https://doi.org/10.1016/j.ener....
12.
Zhou Z, Zhang C, Chen S, Zhang Y, Wang L. Feature-enhanced ensemble learning for accurate capacity estimation of lithium-ion batteries using partial discharging segments in initial stage based on second-order voltage derivatives. Green Energy and Intelligent Transportation 2026; 5(3): 100388. https://doi.org/10.1016/j.geit....
13.
Chen L, Xie S, Lopes AM, Li H, Bao X, Zhang C, Li P. A new SOH estimation method for Lithium-ion batteries based on model-data-fusion. Energy 2024; 286: 129597. https://doi.org/10.1016/j.ener....
14.
Bao X, Chen L, Lopes AM, Li X, Xie S, Li P, Chen YQ. Hybrid deep neural network with dimension attention for state-of-health estimation of Lithium-ion Batteries. Energy 2023; 278: 127734. https://doi.org/10.1016/j.ener....
15.
Huang H, Bian C, Wu M, An D, Yang S. A novel integrated SOC–SOH estimation framework for whole-life-cycle lithium-ion batteries. Energy 2024; 288: 129801. https://doi.org/10.1016/j.ener....
16.
Li S, Jiang Z, Zhu Z, Jiang W, Ma Y, Sang X, Yang S. A framework of joint SOC and SOH estimation for lithium-ion batteries: Using BiLSTM as a battery model. Journal of Power Sources 2025; 635: 236342. https://doi.org/10.1016/j.jpow....
17.
Lyu Y, Shen Z, Zhou N, Wen Z, Chen C. A feature separation transfer network with contrastive metric for remaining useful life prediction under different working conditions. Reliability Engineering & System Safety 2025; 256: 110790. https://doi.org/10.1016/j.ress....
18.
Lyu Y, Xiao X, Fan R, Chen C. Multisource Feature Separation and Weighted Network for Cross-Conditional Capacity Estimation of Lithium Batteries. IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025; 55(10): 6842-6856. https://doi.org/10.1109/tsmc.2....
19.
Chen X, Sun T, Lai X, Zheng Y, Han X. Transfer learning strategies for lithium-ion battery capacity estimation under domain shift differences. Journal of Energy Storage 2024; 90: 111860. https://doi.org/10.1016/j.est.....
20.
Ma Y, Shan C, Gao J, Chen H. Multiple health indicators fusion-based health prognostic for lithium-ion battery using transfer learning and hybrid deep learning method. Reliability Engineering & System Safety 2023; 229: 108818. https://doi.org/10.1016/j.ress....
21.
Mu D, Zhang W, Lin B, Lin C, Lu Y. Multi-source transfer network for cross-domain state of charge estimation of lithium-ion batteries. Journal of Energy Storage 2025; 123: 116636. https://doi.org/10.1016/j.est.....
22.
Dong G, Hua N, Chen H, Lou Y. Deep Transfer Learning Enabled State of Health Estimation of Lithium-Ion Battery Using Voltage Sample Entropy Under Fast Charging Profiles. IEEE Transactions on Transportation Electrification 2025; 11(1): 3703-3714. https://doi.org/10.1109/tte.20....
23.
Shen L, Li J, Zuo L, Zhu L, Shen HT. Source-Free Cross-Domain State of Charge Estimation of Lithium-Ion Batteries at Different Ambient Temperatures. IEEE Transactions on Power Electronics 2023; 38(6): 6851-6862. https://doi.org/10.1109/tpel.2....
24.
Han T, Yue S, Yang P, Zhou R, Yu J. Source-Free Dynamic Weighted Federated Transfer Learning for State-of-Health Estimation of Lithium-Ion Batteries With Data Privacy. IEEE Transactions on Power Electronics 2024; 39(11): 15085-15100. https://doi.org/10.1109/tpel.2....
25.
Zou W, Shen Z, Li Q, Ge J, Li C, Chen X, Shen X, Huang L, Luo B. Experimental Evaluation of Parameter-Efficient Fine-Tuning for Software Engineering Tasks. ACM Transactions on Software Engineering and Methodology 2025; 34(7): 1-34. https://doi.org/10.1145/372210....
26.
Severson KA, Attia PM, Jin N, Perkins N, Jiang B, Yang Z, Chen MH, Aykol M, Herring PK, Fraggedakis D, Bazant MZ, Harris SJ, Chueh WC, Braatz RD. Data-driven prediction of battery cycle life before capacity degradation. Nature Energy 2019; 4(5): 383-391. https://doi.org/10.1038/s41560....
27.
Wang Y, Guo S, Cui Y, Deng L, Zhao L, Li J, Wang Z. A comprehensive review of machine learning-based state of health estimation for lithium-ion batteries: data, features, algorithms, and future challenges. Renewable and Sustainable Energy Reviews 2025; 224: 116125. https://doi.org/10.1016/j.rser....
28.
Purushothaman D, Narayanamoorthi R, Ramachandramurthy VK. Charging ahead: Unlocking the potential of constant voltage and constant current modes in WPT for EVs. Journal of Energy Storage 2024; 96: 112603. https://doi.org/10.1016/j.est.....
29.
Yu J, Yin H, Xia X, Chen T, Li J, Huang Z. Self-Supervised Learning for Recommender Systems: A Survey. IEEE Transactions on Knowledge and Data Engineering 2024; 36(1): 335-355. https://doi.org/10.1109/tkde.2....
30.
Yin X, Pan T, Tian J, Ni L, Lao L. Voltage-fault diagnosis for battery pack in electric vehicles using mutual information. Journal of Power Sources 2024; 608: 234636. https://doi.org/10.1016/j.jpow....
31.
Peng S, Wang Y, Tang A, Jiang Y, Kan J, Pecht M. State of health estimation joint improved grey wolf optimization algorithm and LSTM using partial discharging health features for lithium-ion batteries. Energy 2025; 315: 134293. https://doi.org/10.1016/j.ener....
32.
Zhang C, Luo L, Yang Z, Du B, Zhou Z, Wu J, Chen L. Flexible method for estimating the state of health of lithium-ion batteries using partial charging segments. Energy 2024; 295: 131009. https://doi.org/10.1016/j.ener....
33.
Pang X, Yu P, Yin C, Liu W, Zheng Z. Transformer and bidirectional gated recurrent unit hybrid network with attention mechanisms for lithium-ion battery state-of-health estimation. Journal of Power Sources 2025; 658: 238370. https://doi.org/10.1016/j.jpow.... 2025.238370.
34.
Wei Y, Grau G, Wu D. Sheet resistance prediction of laser induced graphitic carbon with transformer encoder-enabled contrastive learning. Journal of Intelligent Manufacturing 2025; 36(3): 1983-1997. https://doi.org/10.1007/s10845....
35.
Li F, Yu Y, Yuan X, Ren G. State-of-health estimation for lithium-ion batteries using unsupervised deep subdomain adaptation. Energy 2025; 324: 135862. https://doi.org/10.1016/j.ener....
36.
Xu H, Xu Q, Duanmu F, Shen J, Jin L, Gou B, Wu F, Zhang W. State-of-Charge Estimation of Lithium-Ion Batteries Based on EKF Integrated With PSO-LSTM for Electric Vehicles. IEEE Transactions on Transportation Electrification 2025; 11(1): 2311-2321. https://doi.org/10.1109/tte.20....
37.
Yu M, Zhu Y, Gu X, Zhang Q, Shang Y. Incremental Expansion Analysis and State-of-Health Estimation for Lithium-Ion Batteries. IEEE Transactions on Industrial Electronics 2026; 73(1): 546-557. https://doi.org/10.1109/tie.20....
38.
Fang P, Sui X, Zhang A, Wang D, Yin L. Fusion model based RUL prediction method of lithium-ion battery under working conditions. Eksploatacja i Niezawodność – Maintenance and Reliability 2024; 26(3): 186537. https://doi.org/10.17531/ein/1....
39.
Liu X, Gao Z, Tian J, Wei Z, Fang C, Wang P. State of Health Estimation for Lithium-Ion Batteries Using Voltage Curves Reconstruction by Conditional Generative Adversarial Network. IEEE Transactions on Transportation Electrification 2024; 10(4): 10557-10567. https://doi.org/10.1109/tte.20....
40.
Qi W, Qin W, Yun Z. Closed-loop state of charge estimation of Li-ion batteries based on deep learning and robust adaptive Kalman filter. Energy 2024; 307: 132805. https://doi.org/10.1016/j.ener....
41.
Fan X, Li B, Xie Z, Hao Y, Tang Q, Hu X. An improved Transformer incorporating fuzzy information entropy and average input strategy for SOC estimation of lithium-ion battery. Energy 2025; 330: 136953. https://doi.org/10.1016/j.ener....
42.
Zhao SY, Ou K, Gu XX, Dan ZM, Zhang JJ, Wang YX. A novel transformer‐embedded lithium‐ion battery model for joint estimation of state‐of‐charge and state‐of‐health. Rare Metals 2024; 43(11): 5637-5651. https://doi.org/10.1007/s12598....
43.
Meng J, Hu D, Lin M, Peng J, Wu J, Stroe DI. A Domain-Adversarial Neural Network for Transferable Lithium-Ion Battery State-of-Health Estimation. IEEE Transactions on Transportation Electrification 2025; 11(3): 7732-7742. https://doi.org/10.1109/tte.20....
44.
Fang Y, Yap PT, Lin W, Zhu H, Liu M. Source-free unsupervised domain adaptation: A survey. Neural Networks 2024; 174: 106230. https://doi.org/10.1016/j.neun....
45.
Lyu Y, Zhang Q, Chen A, Wen Z. Interval Prediction of Remaining Useful Life based on Convolutional Auto-Encode and Lower Upper Bound Estimation. Eksploatacja i Niezawodność – Maintenance and Reliability 2023; 25(2): 165811. https://doi.org/10.17531/ein/1....
46.
Zhu R, Hu J, Peng W. Bayesian calibrated physics-informed neural networks for second-life battery SOH estimation. Reliability Engineering & System Safety 2025; 264: 111432. https://doi.org/10.1016/j.ress....
Share
RELATED ARTICLE
| eISSN: | 2956-3860 |
| ISSN: | 1507-2711 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
