Lithium-ion battery health prognosis via electrochemical impedance spectroscopy using CNN-BiLSTM model

Abstract

Lithium-ion battery (LIB) health prognosis is essential for ensuring the safety of electric vehicles while they are in use. However, conventional approaches for accurate health state forecasting face challenges due to the complex interplay of battery degradation mechanisms and the significant variability in operating conditions during cycling. In this study, we propose a data-driven method composed of convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM) to accurately predict the state of health and remaining useful life of LIBs. The model is trained using a well-established open-source electrochemical impedance spectroscopy (EIS) database. This database includes over 20,000 EIS spectra from commercial LIBs, collected under various states of health, states of charge and temperatures. The CNN-BiLSTM model surpasses the previous state-of-the-art Gaussian process method in current capacity estimation and remaining useful life prediction. Furthermore, we showcase the model’s capability to forecast the capacity degradation trajectory of a cell using its early-cycle EIS data. Our research demonstrates the versatility of the battery forecasting method by integrating EIS with machine learning, and emphasizes the value of implementing the EIS-based artificial approach in a battery management system.

Keywords

Lithium-ion battery health prediction / convolutional neural networks / bidirectional long short-term memory / electrochemical impedance spectroscopy / battery degradation

References

[1] Harper G,Kendrick E.Recycling lithium-ion batteries from electric vehicles.Nature2019;575:75-86

[2] Zubi G,Carvalho M.The lithium-ion battery: state of the art and future perspectives.Renew Sust Energ Rev2018;89:292-308

[3] Lu L,Li J,Ouyang M.A review on the key issues for lithium-ion battery management in electric vehicles.J Power Sources2013;226:272-88

[4] Yang S,Jiang J,Zhang L.Review on state-of-health of lithium-ion batteries: characterizations, estimations and applications.J Clean Prod2021;314:128015

[5] Liu W,Chau K.Overview of batteries and battery management for electric vehicles.Energy Rep2022;8:4058-84

[6] Chen Y,Zhao Y.A review of lithium-ion battery safety concerns: the issues, strategies, and testing standards.J Energy Chem2021;59:83-99

[7] Xu B,Ulbig A,Kirschen DS.Modeling of lithium-ion battery degradation for cell life assessment.IEEE Trans Smart Grid2018;9:1131-40

[8] Li J,Lotfi N,Park J.A single particle model with chemical/mechanical degradation physics for lithium ion battery state of health (SOH) estimation.Appl Energy2018;212:1178-90

[9] Neupert S.Model-based state-of-charge and state-of-health estimation algorithms utilizing a new free lithium-ion battery cell dataset for benchmarking purposes.Batteries2023;9:364

[10] Li J,Park J.A comprehensive single-particle-degradation model for battery state-of-health prediction.J Power Sources2020;456:227950

[11] Maheshwari A,Santarelli M.Optimizing the operation of energy storage using a non-linear lithium-ion battery degradation model.Appl Energy2020;261:114360

[12] Pender JP,Youn DH.Electrode degradation in lithium-ion batteries.ACS Nano2020;14:1243-95

[13] Birkl CR,Mcturk E,Howey DA.Degradation diagnostics for lithium ion cells.J Power Sources2017;341:373-86

[14] Zhang M,Du J.A review of SOH prediction of Li-ion batteries based on data-driven algorithms.Energies2023;16:3167

[15] Lombardo T,El-Bouysidy H.Artificial intelligence applied to battery research: hype or reality?.Chem Rev2022;122:10899-969 PMCID:PMC9227745

[16] Deng Z,Cai J.Battery health estimation with degradation pattern recognition and transfer learning.J Power Sources2022;525:231027

[17] Khaleghi S,Beheshti SH.Online health diagnosis of lithium-ion batteries based on nonlinear autoregressive neural network.Appl Energy2021;282:116159

[18] Hossain Lipu M,Miah MS.Deep learning enabled state of charge, state of health and remaining useful life estimation for smart battery management system: methods, implementations, issues and prospects.J Energy Storage2022;55:105752

[19] Jones PK,Lee AA.Impedance-based forecasting of lithium-ion battery performance amid uneven usage.Nat Commun2022;13:4806 PMCID:PMC9381522

[20] Severson KA,Jin N.Data-driven prediction of battery cycle life before capacity degradation.Nat Energy2019;4:383-91

[21] Che Y,Lin X,Teodorescu R.Health prognostics for lithium-ion batteries: mechanisms, methods, and prospects.Energy Environ Sci2023;16:338-71

[22] Li C,Fan Y.An approach to state of charge estimation of lithium-ion batteries based on recurrent neural networks with gated recurrent unit.Energies2019;12:1592

[23] Xu Z,Fan Q,Hong J.Improving the state of charge estimation of reused lithium-ion batteries by abating hysteresis using machine learning technique.J Energy Storage2020;32:101678

[24] Peng K,Bao Z.Data-driven battery capacity estimation based on partial discharging capacity curve for lithium-ion batteries.J Energy Storage2023;67:107549

[25] Zheng L,Lu DD,He T.Incremental capacity analysis and differential voltage analysis based state of charge and capacity estimation for lithium-ion batteries.Energy2018;150:759-69

[26] Fei Z,Tsui K,Zhang Z.Early prediction of battery lifetime via a machine learning based framework.Energy2021;225:120205

[27] Shu X,Shen J.State of health prediction of lithium-ion batteries based on machine learning: advances and perspectives.iScience2021;24:103265 PMCID:PMC8567399

[28] Choi W,Kim JM,Yoon W.Modeling and applications of electrochemical impedance spectroscopy (EIS) for lithium-ion batteries.J Electrochem Sci Technol2020;11:1-13

[29] Meddings N,Overney F.Application of electrochemical impedance spectroscopy to commercial Li-ion cells: a review.J Power Sources2020;480:228742

[30] Middlemiss LA,Sayers R.Characterisation of batteries by electrochemical impedance spectroscopy.Energy Rep2020;6:232-41

[31] Juarez-robles D,Barsukov Y.Mukherjee P. Impedance evolution characteristics in lithium-ion batteries.J Electrochem Soc2017;164:A837-47

[32] Gaberšček M.Understanding Li-based battery materials via electrochemical impedance spectroscopy.Nat Commun2021;12:6513 PMCID:PMC8586247

[33] Moradighadi N,Tribollet B.Identifying the dominant electrochemical reaction in electrochemical impedance spectroscopy.Electrochim Acta2021;400:139460

[34] Li D,Li L,Wang K.Electrochemical impedance spectroscopy based on the state of health estimation for lithium-ion batteries.Energies2022;15:6665

[35] Jiang B,Wang X,Shang W.A comparative study of different features extracted from electrochemical impedance spectroscopy in state of health estimation for lithium-ion batteries.Appl Energy2022;322:119502

[36] Zhang Y,Zhang Y,Stimming U.Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning.Nat Commun2020;11:1706 PMCID:PMC7136228

[37] Lecun Y,Bengio Y.Gradient-based learning applied to document recognition.Proc IEEE1998;86:2278-324

[38] Rumelhart DE,Williams RJ.Learning representations by back-propagating errors.Nature1986;323:533-6

[39] Hochreiter S.Long short-term memory.Neural Comput1997;9:1735-80

[40] Graves A.Framewise phoneme classification with bidirectional LSTM and other neural network architectures.Neural Netw2005;18:602-10

[41] Koroma MS,Philippot M.Life cycle assessment of battery electric vehicles: implications of future electricity mix and different battery end-of-life management.Sci Total Environ2022;831:154859 PMCID:PMC9171403

[42] Zhang Y, Tang Q, Zhang Y, et al. Dataset accompanying the paper: Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning. Zenodo 2020.