A Novel Real-Time Battery State Estimation Using Data-Driven Prognostics and Health Management
Source abstract
Abstract
This paper presents a novel data-driven framework for real-time State of Charge (SOC) estimation in lithium-ion battery systems using a data-driven Prognostics and Health Management (PHM) approach. The method leverages an optimized bidirectional Long Short-Term Memory (Bi-LSTM) network, trained with enhanced datasets filtered via exponentially weighted moving averages (EWMAs) and refined through SHAP-based feature attribution. Compared against a Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) across ten diverse drive cycles, the proposed model consistently achieved superior performance, with mean absolute errors (MAEs) as low as 0.40%, outperforming EKF (0.66%) and UKF (1.36%). The Bi-LSTM model also demonstrated higher R2 values (up to 0.9999) and narrower 95% confidence intervals, confirming its precision and robustness. Real-time implementation on embedded platforms yielded inference times of 1.3–2.2 s, validating its deployability for edge applications. The framework’s model-free nature makes it adaptable to other nonlinear, time-dependent systems beyond battery SOC estimation.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · Fault Detection and Control Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Science and Engineering, University of Derby, Markeaton St., Derby DE22 3AW, UK
References (51)
Show source-provided references
1. Battery prognostics and health management from a machine learning perspective10.1016/j.jpowsour.2023.233474 ↗
2. Hannan, M.A., How, D.N.T., Lipu, M.S.H., Mansor, M., Ker, P.J., Dong, Z.Y., Sahari, K.S.M., Tiong, S.K., Muttaqi, K.M., and Mahlia, T.M.I. (2021). Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model. Sci. Rep., 11.10.1038/s41598-021-98915-8 ↗
3. State of Charge Estimation for Lithium-Ion Batteries Using Model-Based and Data-Driven Methods: A Review10.1109/ACCESS.2019.2942213 ↗
4. Liu, X., Fan, X., Wang, L., and Wu, J. (2023). State of Charge Estimation for Power Battery Base on Improved Particle Filter. World Electr. Veh. J., 14.10.3390/wevj14010008 ↗
5. Zhang, S., Wan, Y., Ding, J., and Da, Y. (2021). State of Charge (SOC) Estimation Based on Extended Exponential Weighted Moving Average H-infinite Filtering. Energies, 14.10.3390/en14061655 ↗
6. Simply designed and universal sliding mode observer for the SOC estimation of lithium-ion batteries10.1049/iet-pel.2016.0095 ↗
7. Dini, P., Colicelli, A., and Saponara, S. (2024). Review on Modeling and SOC/SOH Estimation of Batteries for Automotive Applications. Batteries, 10.10.3390/batteries10010034 ↗
8. Campestrini, C. (2018). Practical Feasibility of Kalman Filters for the State Estimation of Lithium-Ion Batteries. [Ph.D. Thesis, Technische Universität München].
9. State of Charge Estimation of Lithium-Ion Batteries Over Wide Temperature Range Using Unscented Kalman Filter10.1109/ACCESS.2018.2860050 ↗
10. State-of-Charge Estimation of Lithium-Ion Batteries via Long Short-Term Memory Network10.1109/ACCESS.2019.2912803 ↗
11. Long Short-Term Memory Networks for Accurate State-of-Charge Estimation of Li-ion Batteries10.1109/TIE.2017.2787586 ↗
12. Kirchgässner, W., Wallscheid, O., and Böcker, J. (2019, January 12–14). Empirical Evaluation of Exponentially Weighted Moving Averages for Simple Linear Thermal Modeling of Permanent Magnet Synchronous Machines. Proceedings of the 2019 IEEE 28th International Symposium on Industrial Electronics (ISIE), Vancouver, BC, Canada.10.1109/ISIE.2019.8781195 ↗
13. Rozemberczki, B., Watson, L., Bayer, P., Yang, H.T., Kiss, O., Nilsson, S., and Sarkar, R. (2022, January 23–29). The Shapley Value in Machine Learning. Proceedings of the 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence, Vienna, Austria.10.24963/ijcai.2022/778 ↗
14. Pimentel, J., McEwan, A.A., and Yu, H.Q. (2023, January 6–8). A Novel Real-Time Framework for Embedded Systems Health Monitoring. Proceedings of the 2023 26th Euromicro Conference on Digital System Design (DSD), Durres, Albania.10.1109/DSD60849.2023.00051 ↗
15. A survey of cross-validation procedures for model selection10.1214/09-SS054 ↗
16. Chen, Y., Huang, D., Zhu, Q., Liu, W., Liu, C., and Xiong, N. (2017). A New State of Charge Estimation Algorithm for Lithium-Ion Batteries Based on the Fractional Unscented Kalman Filter. Energies, 10.10.3390/en10091313 ↗
17. Comparison of one and two time constant models for lithium ion battery
18. Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs: Part 1. Background10.1016/j.jpowsour.2004.02.031 ↗
19. Nonlinear Structural Model of the Battery10.1016/S1452-3981(23)10890-X ↗
20. Sigma-point Kalman filtering for battery management systems of LiPB-based HEV battery packs: Part 1: Introduction and state estimation10.1016/j.jpowsour.2006.06.003 ↗
21. Wan, E., and Van Der Merwe, R. (2000, January 4). The unscented Kalman filter for nonlinear estimation. Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No.00EX373), Lake Louise, AB, Canada.
22. Santos, R.M.S., Alves, C.L.G.d.S., Macedo, E.C.T., Villanueva, J.M.M., and Hartmann, L.V. (September, January 28). Estimation of lithium-ion battery model parameters using experimental data. Proceedings of the 2017 2nd International Symposium on Instrumentation Systems, Circuits and Transducers (INSCIT), Fortaleza, Brazil.10.1109/INSCIT.2017.8103527 ↗
23. Jin, D., and Lin, S. (2012). Brief Introduction of Back Propagation (BP) Neural Network Algorithm and Its Improvement. Advances in Computer Science and Information Engineering, Springer.
24. Pimentel, J., McEwan, A.A., and Yu, H.Q. (September, January 31). Towards a Real-Time Smart Prognostics and Health Management (PHM) of Safety Critical Embedded Systems. Proceedings of the 2022 25th Euromicro Conference on Digital System Design (DSD), Maspalomas, Spain.10.1109/DSD57027.2022.00098 ↗
25. Estimating Electric Motor Temperatures With Deep Residual Machine Learning10.1109/TPEL.2020.3045596 ↗
26. Daniel, K., Jessica, H., and Enrico, B. (2021). A Survey of Domain Knowledge Elicitation in Applied Machine Learning. Multimodal Technol. Interact., 5.10.3390/mti5120073 ↗
27. Feature Engineering Techniques and Spatio-Temporal Data Processing10.1007/s13222-021-00391-x ↗
28. Nor, A.K.B.M., Pedapait, S.R., and Muhammad, M. (2021). Explainable AI (XAI) for PHM of Industrial Asset: A State-of-the-Art, PRISMA-Compliant Systematic Review. arXiv.
29. Hyperparameter optimization for machine learning models based on Bayesian optimization
30. Yu, T., and Zhu, H. (2020). Hyper-parameter optimization: A review of algorithms and applications. arXiv.
31. Random search for hyper-parameter optimization
32. Impact of the Choice of Cross-Validation Techniques on the Results of Machine Learning-Based Diagnostic Applications10.4258/hir.2021.27.3.189 ↗
33. Staudemeyer, R.C., and Morris, E.R. (2019). Understanding LSTM—A tutorial into Long Short-Term Memory Recurrent Neural Networks. arXiv.
34. Non-linear system modeling using LSTM neural networks10.1016/j.ifacol.2018.07.326 ↗
35. López, E., Valle, C., Allende, H., Gil, E., and Madsen, H. (2018). Wind Power Forecasting Based on Echo State Networks and Long Short-Term Memory. Energies, 11.10.3390/en11030526 ↗
36. Pimentel, J., McEwan, A.A., and Yu, H.Q. (2024, January 2–4). Multi-Step Ahead Battery SOC Estimation Using Data-Driven Prognostics and Health Management. Proceedings of the 2024 13th International Conference on Software and Information Engineering, Derby, UK. ICSIE ’24.10.1145/3708635.3708642 ↗
37. Cui, Z., Ke, R., Pu, Z., and Wang, Y. (2019). Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction. arXiv.10.1016/j.trc.2020.102674 ↗
38. Hong, C.W., Lee, C., Lee, K., Ko, M.S., Kim, D.E., and Hur, K. (2020). Remaining Useful Life Prognosis for Turbofan Engine Using Explainable Deep Neural Networks with Dimensionality Reduction. Sensors, 20.10.3390/s20226626 ↗
39. Graves, A., Jaitly, N., and Mohamed, A.r. (2013, January 8–12). Hybrid speech recognition with Deep Bidirectional LSTM. Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic.10.1109/ASRU.2013.6707742 ↗
40. Lithium-ion battery data and where to find it10.1016/j.egyai.2021.100081 ↗
41. Kollmeyer, P. (2018). Panasonic 18650PF Li-Ion Battery Data, McMaster University.
42. Li, C., Xiao, F., and Fan, Y. (2019). An Approach to State of Charge Estimation of Lithium-Ion Batteries Based on Recurrent Neural Networks with Gated Recurrent Unit. Energies, 12.10.3390/en12091592 ↗
43. Wong, K.L., Bosello, M., Tse, R., Falcomer, C., Rossi, C., and Pau, G. (2021, January 26–28). Li-Ion Batteries State-of-Charge Estimation Using Deep LSTM at Various Battery Specifications and Discharge Cycles. Proceedings of the Conference on Information Technology for Social Good, New York, NY, USA. GoodIT ’21.10.1145/3462203.3475878 ↗
44. An overview of vehicular emission standards10.1007/s12647-022-00555-4 ↗
45. Monsalve, G., Cardenas, A., and Martinez, W. (2022, January 1–3). Analysis of two Equivalent Circuit Models for State of Charge Estimation using Kalman Filters. Proceedings of the 2022 IEEE 31st International Symposium on Industrial Electronics (ISIE), Anchorage, AK, USA.10.1109/ISIE51582.2022.9831758 ↗
46. The MathWorks Inc. (2023). Optimization Toolbox Version: R2023b, The MathWorks Inc.
47. Chollet, F. (2024, May 15). Keras. Available online: https://github.com/fchollet/keras.
48. Pimentel, J., and Vladimirova, T. (2019, January 22–24). Towards MPSoC Enabled Subsea Embedded Systems for Fault Tolerant Applications. Proceedings of the 2019 NASA/ESA Conference on Adaptive Hardware and Systems (AHS), Colchester, UK.10.1109/AHS.2019.000-7 ↗
49. Stacked bidirectional and unidirectional LSTM recurrent neural network for forecasting network-wide traffic state with missing values10.1016/j.trc.2020.102674 ↗
50. Remaining useful life estimation in prognostics using deep convolution neural networks10.1016/j.ress.2017.11.021 ↗
51. Niu, K., Zhou, M., Abdallah, C.T., and Hayajneh, M. (2022). Deep transfer learning for system identification using long short-term memory neural networks. arXiv.