Advanced State of Health Estimation for Lithium-Ion Batteries Using Deep Learning and Feature Engineering

Document Type : Research Article

Authors

1 Department of Electrical Engineering, K. N. Toosi University of Technology, Tehran, Iran

2 Department of Mechanical Engineering, K. N. Toosi University of Technology, Tehran, Iran

Abstract

Obtaining an accurate estimate of the state of health of a lithium-ion battery is important for its efficiency and stability, but it's hard because the aging processes are so complicated and non-linear. Deep neural networks and long short-term memory networks are powerful tools, but their potential is often not realized if the raw operating features fail to capture synergistic aging mechanisms. This article proposes a novel two-stage hybrid feature engineering methodology to address this constraint. In the first stage, the method uses a binary particle swarm optimization algorithm to look for a small set of important predictive features. In the second stage, the parsimonious subset is enhanced with a physics-constrained Electro-Thermal Interaction Feature that incorporates terminal voltage and temperature interaction stresses. The resulting feature set was subsequently utilized for the training and evaluation of both deep neural networks and long short-term memory networks models. Adding the electro-thermal interaction feature significantly improves the predictability of both models on the primary B05 cell, raising the R² value from about 0.93 to over 0.99. To assess generalizability, the framework was rigorously validated using a cross-battery approach on two additional cells (B07 and B055), where the models maintained high performance with an average R² > 0.97. The findings indicate that domain-knowledge-intensive feature engineering significantly influences performance more than the architectural decision between deep neural networks and long short-term memory networks, facilitating highly accurate and robust state of health predictions, which are crucial in advanced battery management systems.

Keywords

Main Subjects

References

[1] F. Xin, M.S. Whittingham, Lithium-ion batteries, in:  Microscopy and Microanalysis for Lithium-Ion Batteries, CRC Press, 2023, pp. 1-28.
[2] T. Kim, W. Song, D.-Y. Son, L.K. Ono, Y. Qi, Lithium-ion batteries: outlook on present, future, and hybridized technologies, Journal of Materials Chemistry A, 7(7) (2019) 2942-2964.
[3] F.N.U. Khan, M.G. Rasul, A. Sayem, N.K. Mandal, Design and optimization of lithium-ion battery as an efficient energy storage device for electric vehicles: A comprehensive review, Journal of Energy Storage, 71 (2023) 108033.
[4] M. You, Y. Liu, Z. Chen, X. Zhou, Capacity Estimation of lithium battery based on charging data and Long Short-term Memory Recurrent Neural Network, in:  2022 IEEE Intelligent Vehicles Symposium (IV), IEEE, 2022, pp. 230-234.
[5] G. Kim, S. Sin, J. Park, I. Baek, J. Baek, J. Kim, Capacity prediction of lithium-ion battery using UKF based on different C-rate, in:  2021 24th International Conference on Electrical Machines and Systems (ICEMS), IEEE, 2021, pp. 2303-2306.
[6] L. Krčmář, P. Rydlo, A. Richter, J. Eichler, P. Jandura, State of Health and Aging Estimation Using Kalman Filter in Combination with ARX Model for Prediction of Lifetime Period of Li-Ion, in:  2021 International Conference on Electrical Drives & Power Electronics (EDPE), IEEE, 2021, pp. 234-237.
[7] J. Seok, W. Lee, H. Lee, S. Park, C. Chung, S. Hwang, W.-S. Yoon, Aging mechanisms of Lithium-ion batteries, Journal of Electrochemical Science and Technology, 15(1) (2024) 51-66.
[8] H. Teel, T.R. Garrick, J.S. Lopata, F. Wang, Y. Zeng, S. Shimpalee, Prediction of Lithium-Ion Battery Aging Due to SEI Growth and Lithium Plating Using 3D Microstructure-Based Modeling Method, in:  Electrochemical Society Meeting Abstracts prime2024, The Electrochemical Society, Inc., 2024, pp. 2075-2075.
[9] A.Y. Kharal, M. Khalid, W.M. Hamanah, I.H. Naqvi, N. Arshad, Degradation Mode Quantification and Analysis of Lithium-ion Battery Cell Over Dynamic Load Profile and Different State of Charge Conditions, in:  2024 IEEE 34th Australasian Universities Power Engineering Conference (AUPEC), IEEE, 2024, pp. 1-6.
[10] V. Lopez-Richard, S. Pradhan, L.K. Castelano, R.S. Wengenroth Silva, O. Lipan, S. Höfling, F. Hartmann, Accuracy bottlenecks in impedance spectroscopy due to transient effects, Journal of Applied Physics, 136(16) (2024).
[11] J. Guo, Y. Xu, P. Li, K. Pedersen, M. Gaberšček, D.I. Stroe, Can electrochemical impedance spectroscopy be replaced by direct current techniques in battery diagnosis?, ChemPhysChem, 25(21) (2024) e202400528.
[12] E. Vanem, M. Bruch, Q. Liang, K. Thorbjørnsen, L.O. Valøen, Ø.Å. Alnes, Data‐driven snapshot methods leveraging data fusion to estimate state of health for maritime battery systems, Energy Storage, 5(8) (2023) e476.
[13] C. Gervillié-Mouravieff, W. Bao, D.A. Steingart, Y.S. Meng, Non-destructive characterization techniques for battery performance and life-cycle assessment, Nature Reviews Electrical Engineering, 1(8) (2024) 547-558.
[14] Z. Yi, Y. Song, D. Liu, Indirect Measurement Method of Energy Storage Lithium-Ion Battery Electro-Chemical Parameters, in:  2023 IEEE 16th International Conference on Electronic Measurement & Instruments (ICEMI), IEEE, 2023, pp. 244-249.
[15] C. LI, C. WANG, G. WANG, Z. LU, C. MA, Review on implementation method analysis and performance comparison of lithium battery state of charge estimation, Energy storage science and technology, 11(10) (2022) 3328.
[16] B. Zraibi, M. Mansouri, M.M. El Aoud, Advancing Lithium-ion Battery Prognostics: A Novel Deep Learning Framework for Enhanced SOH and RUL Prediction Accuracy, in:  2024 International Conference on Ubiquitous Networking (UNet), IEEE, 2024, pp. 1-8.
[17] A. Rastegarpanah, M.E. Asif, R. Stolkin, Hybrid neural networks for enhanced predictions of remaining useful life in lithium-ion batteries, Batteries, 10(3) (2024) 106.
[18] I. Marri, E. Petkovski, L. Cristaldi, M. Faifer, Battery remaining useful life prediction supported by long short-term memory neural network, in:  2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), IEEE, 2023, pp. 1-6.
[19] M. Abbas, I. Cho, J. Kim, Mathematical characterization of experimental aging data for designing battery degradation model, Journal of Electrical Engineering & Technology, 18(1) (2023) 393-406.
[20] K. Benlamine, T. Mesbahi, Machine Learning Applied to Battery Prognostics based on Advanced State of Health Estimation, in:  2022 IEEE Vehicle Power and Propulsion Conference (VPPC), IEEE, 2022, pp. 1-6.
[21] J. Lin, Y. Zhang, E. Khoo, Hybrid physics-based and data-driven modeling with calibrated uncertainty for lithium-ion battery degradation diagnosis and prognosis, arXiv preprint arXiv:2110.13661,  (2021).
[22] S. Shen, B. Liu, K. Zhang, S. Ci, Toward fast and accurate SOH prediction for lithium-ion batteries, IEEE Transactions on Energy Conversion, 36(3) (2021) 2036-2046.
[23] J. Zhao, Y. Zhu, B. Zhang, M. Liu, J. Wang, C. Liu, Y. Zhang, Method of Predicting SOH and RUL of Lithium-Ion Battery Based on the Combination of LSTM and GPR, Sustainability, 14(19) (2022) 11865.
[24] J. Wen, X. Chen, X. Li, Y. Li, SOH prediction of lithium battery based on IC curve feature and BP neural network, Energy, 261 (2022) 125234.
[25] J. Jia, J. Liang, Y. Shi, J. Wen, X. Pang, J. Zeng, SOH and RUL prediction of lithium-ion batteries based on Gaussian process regression with indirect health indicators, Energies, 13(2) (2020) 375.
[26] Z. Yu, N. Liu, Y. Zhang, L. Qi, R. Li, Battery SOH prediction based on multi-dimensional health indicators, Batteries, 9(2) (2023) 80.
[27] S. Peng, J. Zhu, T. Wu, A. Tang, J. Kan, M. Pecht, SOH early prediction of Lithium-ion batteries based on voltage interval selection and features fusion, Energy, 308 (2024) 132993.
[28] C. Qian, B. Xu, Q. Xia, Y. Ren, B. Sun, Z. Wang, SOH prediction for Lithium-Ion batteries by using historical state and future load information with an AM-seq2seq model, Applied Energy, 336 (2023) 120793.
[29] X. Shu, S. Shen, J. Shen, Y. Zhang, G. Li, Z. Chen, Y. Liu, State of health prediction of lithium-ion batteries based on machine learning: Advances and perspectives, Iscience, 24(11) (2021).
[30] R. Tang, P. Zhang, S. Ning, Y. Zhang, Prediction of battery SOH and RUL based on cooperative characteristics in voltage-temperature-time dimensions, Journal of The Electrochemical Society, 170(6) (2023) 060535.
[31] S. Pepe, F. Ciucci, Long-range battery state-of-health and end-of-life prediction with neural networks and feature engineering, Applied Energy, 350 (2023) 121761.
[32] J. Wang, C. Zhang, L. Zhang, X. Su, W. Zhang, X. Li, J. Du, A novel aging characteristics-based feature engineering for battery state of health estimation, Energy, 273 (2023) 127169.
[33] B. Zhao, W. Zhang, Y. Zhang, C. Zhang, C. Zhang, J. Zhang, Research on the remaining useful life prediction method for lithium-ion batteries by fusion of feature engineering and deep learning, Applied Energy, 358 (2024) 122325.
[34] M. Zhang, J. Yin, W. Chen, SOH estimation and RUL prediction of lithium batteries based on multidomain feature fusion and CatBoost model, Energy Science & Engineering, 11(9) (2023) 3082-3101.
[35] J. Bian, G. Liu, J. Chen, Y. Cao, R. Chen, Y. Qian, PSO-MLSt-LSTM: Multi-layer stacked ensemble model for lithium-ion battery SOH prediction via multi-feature fusion, Journal of Energy Storage, 125 (2025) 116825.
[36] X. Shu, G. Li, J. Shen, Z. Lei, Z. Chen, Y. Liu, A uniform estimation framework for state of health of lithium-ion batteries considering feature extraction and parameters optimization, Energy, 204 (2020) 117957.
[37] I. Jorge, T. Mesbahi, A. Samet, R. Boné, Time series feature extraction for lithium-ion batteries state-of-health prediction, Journal of Energy Storage, 59 (2023) 106436.
[38] Y. Jiang, Y. Chen, F. Yang, W. Peng, State of health estimation of lithium-ion battery with automatic feature extraction and self-attention learning mechanism, Journal of Power Sources, 556 (2023) 232466.
[39] B. Saha, K. Goebel, Battery data set, NASA AMES prognostics data repository,  (2007).
[40] T. Waldmann, M. Wilka, M. Kasper, M. Fleischhammer, M. Wohlfahrt-Mehrens, Temperature dependent ageing mechanisms in Lithium-ion batteries–A Post-Mortem study, Journal of power sources, 262 (2014) 129-135.
[41] P. Ramadass, B. Haran, R. White, B.N. Popov, Mathematical modeling of the capacity fade of Li-ion cells, Journal of power sources, 123(2) (2003) 230-240.
AUT Journal of Electrical Engineering
Volume 58, Issue 1
2026
Pages 101-120

Files

Share

How to cite

Statistics