A two-stage deep learning framework for early-stage lifetime prediction for lithium-ion batteries with consideration of features from multiple cycles

Frontiers in Energy Research - Tập 10
Jiwei Yao1, Kody M. Powell1,2, Tao Gao1
1Department of Chemical Engineering, United States
2Department of Mechanical Engineering, United States

Tóm tắt

Lithium-ion batteries are a crucial element in the electrification and adoption of renewable energy. Accurately predicting the lifetime of batteries with early-stage data is critical to facilitating battery research, production, and deployment. But this problem remains challenging because batteries are complex, nonlinear systems, and data acquired at the early-stage exhibit a weak correlation with battery lifetime. In this paper, instead of building features from specific cycles, we extract features from multiple cycles to form a time series dataset. Then the time series data is compressed with a GRU-based autoencoder to reduce feature dimensionality and eliminate the time domain. Further, different regression models are trained and tested with a feature selection method. The elastic model provides a test RMSE of 187.99 cycles and a test MAPE of 10.14%. Compared with the state-of-art early-stage lifetime prediction model, the proposed framework can lower the test RMSE by 10.22% and reduce the test MAPE by 28.44%.

Từ khóa


Tài liệu tham khảo

Arachchige, 2017, Enhanced prognostic model for lithium ion batteries based on particle filter state transition model modification, Appl. Sci. (Basel)., 7, 1172, 10.3390/APP7111172

Attia, 2021, Statistical learning for accurate and interpretable battery lifetime prediction, J. Electrochem. Soc., 168, 090547, 10.1149/1945-7111/AC2704

Brunton, 2020, Machine learning for fluid mechanics, Annu. Rev. Fluid Mech., 52, 477, 10.1146/annurev-fluid-010719-060214

Chen, , Battery electrode mass loading prognostics and analysis for lithium-ion battery--based energy storage systems, Front. Energy Res., 9, 754317, 10.3389/fenrg.2021.754317

Chen, , A machine learning framework for early detection of lithium plating combining multiple physics-based electrochemical signatures, Cell Rep. Phys. Sci., 2, 100352, 10.1016/j.xcrp.2021.100352

Cho, 2014, On the properties of neural machine translation: Encoder-decoder approaches, 10.48550/arXiv.1409.1259

Fei, 2022, Early-stage lifetime prediction for lithium-ion batteries: A deep learning framework jointly considering machine-learned and handcrafted data features, J. Energy Storage, 52, 104936, 10.1016/J.EST.2022.104936

Gao, 2022, Co-estimation of state-of-charge and state-of- health for lithium-ion batteries using an enhanced electrochemical model, IEEE Trans. Ind. Electron., 69, 2684, 10.1109/TIE.2021.3066946

Greenbank, 2022, Automated feature extraction and selection for data-driven models of rapid battery capacity fade and end of life, IEEE Trans. Ind. Inf., 18, 2965, 10.1109/TII.2021.3106593

Guo, 2022, Understanding the mechanism of capacity increase during early cycling of commercial NMC/graphite lithium-ion batteries, J. Energy Chem., 74, 34, 10.1016/J.JECHEM.2022.07.005

Gupta, 2021, Transfer learning LSTM model for battery useful capacity fade prediction, 10.1109/ICMT53429.2021.9687230

He, 2011, Prognostics of lithium-ion batteries based on Dempster–Shafer theory and the Bayesian Monte Carlo method, J. Power Sources, 196, 10314, 10.1016/J.JPOWSOUR.2011.08.040

Hegde, 2020, Applications of machine learning methods for engineering risk assessment – a review, Saf. Sci., 122, 104492, 10.1016/J.SSCI.2019.09.015

Hsu, 2022, Deep neural network battery life and voltage prediction by using data of one cycle only, Appl. Energy, 306, 118134, 10.1016/j.apenergy.2021.118134

Hu, 2022, Lithium-ion battery calendar health prognostics based on knowledge-data-driven attention, IEEE Trans. Ind. Electron., 70, 407, 10.1109/TIE.2022.3148743

Hu, 2020, Battery lifetime prognostics, Joule, 4, 310, 10.1016/J.JOULE.2019.11.018

Hu, 2021, A particle filter and long short-term memory fusion technique for lithium-ion battery remaining useful life prediction, J. Dyn. Syst. Meas. Control, 143, 4049234, 10.1115/1.4049234

Jeon, 2019, Wettability in electrodes and its impact on the performance of lithium-ion batteries, Energy Storage Mat., 18, 139, 10.1016/J.ENSM.2019.01.002

Li, 2021, Online capacity estimation of lithium-ion batteries with deep long short-term memory networks, J. Power Sources, 482, 228863, 10.1016/J.JPOWSOUR.2020.228863

Li, 2019, Data-driven health estimation and lifetime prediction of lithium-ion batteries: A review, Renew. Sustain. energy Rev., 113, 109254, 10.1016/j.rser.2019.109254

Liakos, 2018, Machine learning in agriculture: A review, Sensors, 18, 2674, 10.3390/S18082674

Liu, 2019, Modified Gaussian process regression models for cyclic capacity prediction of lithium-ion batteries, IEEE Trans. Transp. Electrific., 5, 1225, 10.1109/TTE.2019.2944802

Liu, 2021, A data-driven approach with uncertainty quantification for predicting future capacities and remaining useful life of lithium-ion battery, IEEE Trans. Ind. Electron., 68, 3170, 10.1109/TIE.2020.2973876

Liu, 2022, Future ageing trajectory prediction for lithium-ion battery considering the knee point effect, IEEE Trans. Energy Convers., 37, 1282, 10.1109/TEC.2021.3130600

Mendez, 2022, Linear and nonlinear dimensionality reduction from fluid mechanics to machine learning, 10.48550/arxiv.2208.07746

Paulson, 2022, Feature engineering for machine learning enabled early prediction of battery lifetime, J. Power Sources, 527, 231127, 10.1016/j.jpowsour.2022.231127

Pudil, 1994, Floating search methods in feature selection, Pattern Recognit. Lett., 15, 1119, 10.1016/0167-8655(94)90127-9

Reich, 1997, Machine learning techniques for civil engineering problems, Comp-aided. Civ. Eng., 12, 295, 10.1111/0885-9507.00065

Richardson, , Gaussian process regression for <italic&gt;in situ&lt;/italic&gt; capacity estimation of lithium-ion batteries, IEEE Trans. Ind. Inf., 15, 127, 10.1109/TII.2018.2794997

Richardson, , Battery health prediction under generalized conditions using a Gaussian process transition model, J. Energy Storage, 23, 320, 10.1016/J.EST.2019.03.022

Richardson, 2017, Gaussian process regression for forecasting battery state of health, J. Power Sources, 357, 209, 10.1016/J.JPOWSOUR.2017.05.004

Saha, 2009, Prognostics methods for battery health monitoring using a Bayesian framework, IEEE Trans. Instrum. Meas., 58, 291, 10.1109/TIM.2008.2005965

Sanchez-Lengeling, 2018, Inverse molecular design using machine learning:Generative models for matter engineering, Science, 361, 360, 10.1126/science.aat2663

Saxena, 2022, A convolutional neural network model for battery capacity fade curve prediction using early life data, J. Power Sources, 542, 231736, 10.1016/J.JPOWSOUR.2022.231736

Schmalstieg, 2014, A holistic aging model for Li(NiMnCo)O2 based 18650 lithium-ion batteries, J. Power Sources, 257, 325, 10.1016/J.JPOWSOUR.2014.02.012

Severson, 2019, Data-driven prediction of battery cycle life before capacity degradation, Nature Energy, 4, 383, 10.1038/s41560-019-0356-8

Tang, 2019, Real-time aging trajectory prediction using a base model-oriented gradient-correction particle filter for Lithium-ion batteries, J. Power Sources, 440, 227118, 10.1016/J.JPOWSOUR.2019.227118

Uddin, 2022, State of health estimation of lithium-ion batteries in vehicle-to-grid applications using recurrent neural networks for learning the impact of degradation stress factors, 10.48550/arxiv.2205.07561

Wassiliadis, 2018, Revisiting the dual extended kalman filter for battery state-of-charge and state-of-health estimation: A use-case life cycle analysis, J. Energy Storage, 19, 73, 10.1016/J.EST.2018.07.006

Xing, 2013, An ensemble model for predicting the remaining useful performance of lithium-ion batteries, Microelectron. Reliab., 53, 811, 10.1016/J.MICROREL.2012.12.003

Xu, 2021, Life prediction of lithium-ion batteries based on stacked denoising autoencoders, Reliab. Eng. Syst. Saf., 208, 107396, 10.1016/J.RESS.2020.107396

Yang, 2019, A coulombic efficiency-based model for prognostics and health estimation of lithium-ion batteries, Energy, 171, 1173, 10.1016/J.ENERGY.2019.01.083

Yang, 2022, Robust State of Health estimation of lithium-ion batteries using convolutional neural network and random forest, J. Energy Storage, 48, 103857, 10.1016/J.EST.2021.103857

Zhang, 2018, Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries, IEEE Trans. Veh. Technol., 67, 5695, 10.1109/TVT.2018.2805189

Feature engineering for machine learning: Principles and techniques for data scientists ZhengA. CasariA. 2018

Thông tin
Thông tin xuất bản

Frontiers in Energy Research

Tập 10

Thông tin tác giả