Shared Representation Learning for Generalizable SOH Estimation Across Multiple Battery Configurations
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Battery health monitoring is essential in applications such as electric vehicles and energy storage systems, where the lifespan and health state of batteries directly impact the safety and operational costs. However, existing works have demonstrated promising performance in predicting the state of health (SOH) of batteries within the same type under certain working conditions. However, batteries are produced with different types and work under different conditions in real applications. Existing methods fail to leverage the inherent correlations between related battery types and overlook the various working conditions, resulting in suboptimal robustness and prediction accuracy. To address this limitation, we propose SRSE: a novel Shared Representation learning framework that jointly learns shared representation (hidden knowledge) across multiple battery configurations for robust and generalized SOH Estimation. In particular, an adversarial training scheme is utilized to eliminate task-specific contamination in the shared feature space. SRSE captures both feature-level and logit-level shared knowledge and subsequently transfers it from the shared layer to task-specific layers, enhancing the adaptability and efficiency of each task. Extensive experiments on three large-scale battery health datasets demonstrate that our proposed method significantly improves SOH estimation performance across diverse battery types and operating conditions.
##plugins.themes.bootstrap3.article.details##
Representation learning, Battery health monitoring, State of health estimation
Baghdadi, Issam, et al. "Lithium battery aging model based on Dakin’s degradation approach." Journal of Power Sources 325 (2016): 273-285.
Ben-David, Shai, et al. "A theory of learning from different domains." Machine learning 79.1 (2010): 151-175.
Ben-David, Shai, et al. "Analysis of representations for domain adaptation." Advances in neural information processing systems 19 (2006).Chen, Shijie, Yu Zhang, and Qiang Yang. "Multi-task learning in natural language processing: An overview." ACM Computing Surveys 56.12 (2024): 1-32.
Deng, Jinliang, et al. "A multi-view multi-task learning framework for multi-variate time series forecasting." IEEE Transactions on Knowledge and Data Engineering 35.8 (2022): 7665-7680.
Dong, Guangzhong, and Jingwen Wei. "A physics-based aging model for lithium-ion battery with coupled chemical/mechanical degradation mechanisms." Electrochimica Acta 395 (2021): 139133.
Ganin, Yaroslav, and Victor Lempitsky. "Unsupervised domain adaptation by backpropagation." International conference on machine learning. PMLR, 2015.
Ganin, Yaroslav, et al. "Domain-adversarial training of neural networks." Journal of machine learning research 17.59 (2016): 1-35.
Goodfellow, Ian J., et al. "Generative adversarial nets." Advances in neural information processing systems 27 (2014).
He, Lili, et al. "A multi-task, multi-stage deep transfer learning model for early prediction of neurodevelopment in very preterm infants." Scientific Reports 10.1 (2020): 15072.
Heuer, Falk, et al. "Multitask-centernet (mcn): Efficient and diverse multitask learning using an anchor free approach." Proceedings of the IEEE/CVF International conference on computer vision. 2021.
Hinton, Geoffrey, Oriol Vinyals, and Jeff Dean. "Distilling the knowledge in a neural network." arXiv preprint arXiv:1503.02531 (2015).
Kim, Tae San, and So Young Sohn. "Multitask learning for health condition identification and remaining useful life prediction: Deep convolutional neural network approach." Journal of Intelligent Manufacturing 32.8 (2021): 2169-2179.
Li, Xiaoyu, et al. "A co-estimation framework of state of health and remaining useful life for lithium-ion batteries using the semi-supervised learning algorithm." Energy and AI 19 (2025): 100458.
Liu, Pengfei, Xipeng Qiu, and Xuanjing Huang. "Recurrent neural network for text classification with multi-task learning." arXiv preprint arXiv:1605.05101 (2016).
Liu, Pengfei, Xipeng Qiu, and Xuanjing Huang. "Adversarial multi-task learning for text classification." arXiv preprint arXiv:1704.05742 (2017).
Lu, Jiahuan, et al. "Deep learning to estimate lithium-ion battery state of health without additional degradation experiments." Nature Communications 14.1 (2023): 2760.
Lui, Yu Hui, et al. "Physics-based prognostics of implantable-grade lithium-ion battery for remaining useful life prediction." Journal of Power Sources 485 (2021): 229327.
Preger, Yuliya, et al. "Degradation of commercial lithium-ion cells as a function of chemistry and cycling conditions." Journal of The Electrochemical Society 167.12 (2020): 120532.
Rauf, Huzaifa, Muhammad Khalid, and Naveed Arshad. "Machine learning in state of health and remaining useful life estimation: Theoretical and technological development in battery degradation modelling." Renewable and Sustainable Energy Reviews 156 (2022): 111903.
Thelen, Adam, et al. "Integrating physics-based modeling and machine learning for degradation diagnostics of lithium-ion batteries." Energy Storage Materials 50 (2022): 668-695.
Wang, Fujin, et al. "Physics-informed neural network for lithium-ion battery degradation stable modeling and prognosis." Nature Communications 15.1 (2024): 4332.
Xu, Qing, et al. "Distilling universal and joint knowledge for cross-domain model compression on time series data." arXiv preprint arXiv:2307.03347 (2023).
Zhang, Shuxin, et al. "A physics-informed hybrid multitask learning for lithium-ion battery full-life aging estimation at early lifetime." IEEE Transactions on Industrial Informatics (2024).
Zhang, Yu, and Qiang Yang. "A survey on multi-task learning." IEEE transactions on knowledge and data engineering 34.12 (2021): 5586-5609.
Zhu, Jiangong, et al. "Data-driven capacity estimation of commercial lithium-ion batteries from voltage relaxation." Nature communications 13.1 (2022): 2261.
Wen, Zhihao, et al. "Temporal and heterogeneous graph neural network for remaining useful life prediction." IEEE Transactions on Neural Networks and Learning Systems (2025).
Hou, Yubo, et al. "Source-free Calibrated Uncertainty for RUL Adaptation with incomplete degradation." Mechanical Systems and Signal Processing 233 (2025): 112718.
Wang, Yucheng, et al. "A survey on graph neural networks for remaining useful life prediction: Methodologies, evaluation and future trends." Mechanical Systems and Signal Processing 229 (2025): 112449.
Hou, Yubo, et al. "Evidential Domain Adaptation for Remaining Useful Life Prediction with Incomplete Degradation." IEEE Transactions on Instrumentation and Measurement (2025).
This work is licensed under a Creative Commons Attribution 3.0 Unported License.