A lithium-ion battery state-of-health prediction model based on physical information constraints and multimodal feature fusion

Abstract

Accurate estimation of lithium battery state-of-health (SOH) is essential for ensuring safe operation and efficient utilization. To address the challenges of complex degradation factors and unreliable feature extraction, we develop a novel SOH prediction model integrating physical information constraints and multimodal feature fusion. Our approach employs a multi-channel encoder to process heterogeneous data modalities, including health indicators, raw charge/discharge sequences, and incremental capacity data, and uses multi-channel encoders to achieve structured input. A physics-informed loss function, derived from an empirical capacity decay equation, is incorporated to enforce interpretability, while a cross-layer attention mechanism dynamically weights features to handle missing modalities and random noise. Experimental validation on multiple battery types demonstrates that our model reduces mean absolute error (MAE) by at least 51.09% compared to unimodal baselines, maintains robustness under adverse conditions such as partial data loss, and achieves an average MAE of 0.0201 in real-world battery pack applications. This model significantly enhances the accuracy and universality of prediction, enabling accurate prediction of battery SOH under actual engineering conditions.

Keywords

lithium-ion batteries / state-of-health prediction / multimodal feature fusion / physics-informed neural networks / attention mechanism

References

[1] Fu S-y, Tao S-y, Fan H-t, et al.. Data-driven capacity estimation for lithium-ion batteries with feature matching based transfer learning method [J]. Applied Energy, 2024, 353: 121991

[2] Liu Y-s, Wang L-c, Li D-z, et al.. State-of-health estimation of lithium-ion batteries based on electrochemical impedance spectroscopy: A review [J]. Protection and Control of Modern Power Systems, 2023, 8(3): 1-17

[3] Tran M K, Cunanan C, Panchal S, et al.. Investigation of individual cells replacement concept in lithium-ion battery packs with analysis on economic feasibility and pack design requirements [J]. Processes, 2021, 9(122263

[4] Deng Z-w, Xu L, Liu H-a, et al.. Rapid health estimation of in-service battery packs based on limited labels and domain adaptation [J]. Journal of Energy Chemistry, 2024, 89: 345-354

[5] Zhao J-h, Zhu Y, Zhang B, et al.. Review of state estimation and remaining useful life prediction methods for lithium-ion batteries [J]. Sustainability, 2023, 15(65014

[6] Sun X-w, Zhang Y, Zhang Y-c, et al.. Summary of health-state estimation of lithium-ion batteries based on electrochemical impedance spectroscopy [J]. Energies, 2023, 16(155682

[7] Wen J-p, Chen X, Li X-h, et al.. SOH prediction of lithium battery based on IC curve feature and BP neural network [J]. Energy, 2022, 261: 125234

[8] Zhang B-d, Liu W, Cai Y-x, et al.. State of health prediction of lithium-ion batteries using particle swarm optimization with Levy flight and generalized opposition-based learning [J]. Journal of Energy Storage, 2024, 84: 110816

[9] Ardakani A H, Ali Abdollahian S, Abdollahi F. NARX transformer: A dynamic model for leveraging multicycle data in long-term battery state of health estimation [J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 2530908

[10] Li Z, Dong H, Hou S-d, et al.. Coordinated control scheme of a hybrid renewable power system based on hydrogen energy storage [J]. Energy Reports, 2021, 7: 5597-5611

[11] Xiong R, Li L-l, Tian J-P. Towards a smarter battery management system: A critical review on battery state of health monitoring methods [J]. Journal of Power Sources, 2018, 405: 18-29

[12] Shi M-j, Xu J, Lin C-p, et al.. A fast state-of-health estimation method using single linear feature for lithium-ion batteries [J]. Energy, 2022, 256: 124652

[13] Merrouche W, Trari M, Djellal L, et al.. Improved model and simulation tool for dynamic SOH estimation and life prediction of batteries used in PV systems [J]. Simulation Modelling Practice and Theory, 2022, 119: 102590

[14] Tian H-x, Qin P-l, Li K, et al.. A review of the state of health for lithium-ion batteries: Research status and suggestions [J]. Journal of Cleaner Production, 2020, 261: 120813

[15] Dai H-f, Wei X-z, Sun Z-C. A new SOH prediction concept for the power lithium-ion battery used on HEVs [C]. 2009 IEEE Vehicle Power and Propulsion Conference, 20091649-1653

[16] Javaid M U, Seo J, Suh Y K, et al.. Battery state of health estimation from discharge voltage segments using an artificial neural network [J]. International Journal of Precision Engineering and Manufacturing–Green Technology, 2024, 11(3863-876

[17] Hou Z-y, Xu W-q, Jia G-w, et al.. Estimation of SOH of lithium-ion batteries based on PSO-Bi GRU-attention network [J]. Journal of the Electrochemical Society, 2024, 171(2): 020550

[18] Zhou J-n, Wang S-l, Cao W, et al.. State of health prediction of lithium-ion batteries based on SSA optimized hybrid neural network model [J]. Electrochimica Acta, 2024, 487: 144146

[19] Feng J-q, Cai F, Zhao Y, et al.. A novel feature optimization and ensemble learning method for state-of-health prediction of mining lithium-ion batteries [J]. Energy, 2024, 299: 131474

[20] Galeotti M, Cinà L, Giammanco C, et al.. Performance analysis and SOH (state of health) evaluation of lithium polymer batteries through electrochemical impedance spectroscopy [J]. Energy, 2015, 89: 678-686

[21] Liao L-x, Köttig F. Review of hybrid prognostics approaches for remaining useful life prediction of engineered systems, and an application to battery life prediction [J]. IEEE Transactions on Reliability, 2014, 63(1191-207

[22] Hu X-s, Li S-b, Peng. A comparative study of equivalent circuit models for Li-ion batteries [J]. Journal of Power Sources, 2012, 198: 359-367

[23] Kumar R R, Bharatiraja C, Udhayakumar K, et al.. Advances in batteries, battery modeling, battery management system, battery thermal management, SOC, SOH, and charge/discharge characteristics in EV applications [J]. IEEE Access, 2023, 11: 105761-105809

[24] Li J, Adewuyi K, Lotfi N, et al.. A single particle model with chemical/mechanical degradation physics for lithium ion battery state of health (SOH) estimation [J]. Applied Energy, 2018, 212: 1178-1190

[25] Lin C, Tang A-h, Xing J-L. Evaluation of electrochemical models based battery state-of-charge estimation approaches for electric vehicles [J]. Applied Energy, 2017, 207: 394-404

[26] Ozkurt C, Camci F, Atamuradov V, et al.. Integration of sampling based battery state of health estimation method in electric vehicles [J]. Applied Energy, 2016, 175: 356-367

[27] Singh P, Chen C, Tan C M, et al.. Semi-empirical capacity fading model for SOH estimation of Li-ion batteries [J]. Applied Sciences, 2019, 9(15): 3012

[28] Zhang C-p, Jiang J-c, Zhang L-j, et al.. A generalized SOC-OCV model for lithium-ion batteries and the SOC estimation for LNMCO battery [J]. Energies, 2016, 9(11900

[29] Liu F, Shao C, Su W-x, et al.. Online joint estimator of key states for battery based on a new equivalent circuit model [J]. Journal of Energy Storage, 2022, 52: 104780

[30] Hu X-s, Yuan H, Zou C-f, et al.. Co-estimation of state of charge and state of health for lithiumion batteries based on fractional-order calculus [J]. IEEE Transactions on Vehicular Technology, 2018, 67(1110319-10329

[31] Jiang B, Zhu Y-l, Zhu J-g, et al.. An adaptive capacity estimation approach for lithium-ion battery using 10-Min relaxation voltage within high state of charge range [J]. Energy, 2023, 263: 125802

[32] Jia J-f, Liang J-y, Shi Y-h, et al.. SOH and RUL prediction of lithium-ion batteries based on Gaussian process regression with indirect health indicators [J]. Energies, 2020, 13(2375

[33] Guo P-y, Cheng Z, Yang L. A data-driven remaining capacity estimation approach for lithium-ion batteries based on charging health feature extraction [J]. Journal of Power Sources, 2019, 412: 442-450

[34] Li Y, Zou C-f, Berecibar M, et al.. Random forest regression for online capacity estimation of lithium-ion batteries [J]. Applied Energy, 2018, 232: 197-210

[35] Kheirkhah-Rad E, Parvareh A, Moeini-Aghtaie M, et al.. A data-driven state-of-health estimation model for lithium-ion batteries using referenced-based charging time [J]. IEEE Transactions on Power Delivery, 2023, 38(53406-3416

[36] Khan N, Ullah F U M, Afnan, et al.. Batteries state of health estimation via efficient neural networks with multiple channel charging profiles [J]. IEEE Access, 2020, 9: 7797-7813

[37] Fu Y-m, Xu J, Shi M-j, et al.. A fast impedance calculation-based battery state-of-health estimation method [J]. IEEE Transactions on Industrial Electronics, 2022, 69(7): 7019-7028

[38] Qian C, Xu B-h, Chang L, et al.. Convolutional neural network based capacity estimation using random segments of the charging curves for lithiumion batteries [J]. Energy, 2021, 227: 120333

[39] Li W-h, Sengupta N, Dechent P, et al.. Online capacity estimation of lithium-ion batteries with deep long short-term memory networks [J]. Journal of Power Sources, 2021, 482: 228863

[40] Shen S, Sadoughi M, Li M, et al.. Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries [J]. Applied Energy, 2020, 260: 114296

[41] Xia F, Wang K-g, Chen J-J. State of health and remaining useful life prediction of lithium-ion batteries based on a disturbance-free incremental capacity and differential voltage analysis method [J]. Journal of Energy Storage, 2023, 64: 107161

[42] Xia F, Wang K-g, Chen J-J. State - of - health prediction for lithium-ion batteries based on complete ensemble empirical mode decomposition with adaptive noise-gate recurrent unit fusion model [J]. Energy Technology, 2022, 10(42100767

[43] Liu H-a, Li C, Hu X-s, et al.. Multi-modal framework for battery state of health evaluation using open-source electric vehicle data [J]. Nature Communications, 2025, 16(11137

[44] Lin M-q, You Y-q, Meng J-h, et al.. Lithium-ion batteries SOH estimation with multimodal multilinear feature fusion [J]. IEEE Transactions on Energy Conversion, 2023, 38(42959-2968

[45] Wang F-j, Zhai Z, Zhao Z-b, et al.. Physics-informed neural network for lithium-ion battery degradation stable modeling and prognosis [J]. Nature Communications, 2024, 15(14332

[46] Xia F, Yu Y, Chen J-J. SOH and RUL prediction of lithium batteries based on fusions of RLOESS filtered electrochemical and thermal features by bidirectional gated recurrent unit network [J]. Journal of Energy Storage, 2024, 102: 114134

[47] Xia F, Tang C, Chen J-J. Online two-dimensional filter for anti-interference aging features extraction to accurately predict the battery health [J]. Measurement, 2024, 234: 114758

RIGHTS & PERMISSIONS

Central South University