Forecasting battery capacity and power degradation with multi-task learning

Li, Weihan; Zhang, Haotian; van Vlijmen, Bruis; Dechent, Philipp; Sauer, Dirk Uwe

doi:10.1016/j.ensm.2022.09.013

Forecasting battery capacity and power degradation with multi-task learning

Journal Article · Wed Sep 14 00:00:00 EDT 2022 · Energy Storage Materials

DOI:https://doi.org/10.1016/j.ensm.2022.09.013· OSTI ID:2006551

^[1]; Zhang, Haotian ^[2]; van Vlijmen, Bruis ^[3]; Dechent, Philipp ^[4]; Sauer, Dirk Uwe ^[5]

RWTH Aachen University (Germany); Jülich Aachen Research Alliance (JARA-Energy) (Germany); SLAC
RWTH Aachen University (Germany)
SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States); Stanford University, CA (United States)
RWTH Aachen University (Germany); Jülich Aachen Research Alliance (JARA-Energy) (Germany)
RWTH Aachen University (Germany); Jülich Aachen Research Alliance (JARA-Energy) (Germany); Helmholtz Institute Münster (HI MS), Jülich (Germany)

Lithium-ion batteries degrade due to usage and exposure to environmental conditions, which affects their capability to store energy and supply power. Accurately predicting the capacity and power fade of lithium-ion battery cells is challenging due to intrinsic manufacturing variances and coupled nonlinear ageing mechanisms. In this paper, we propose a data-driven prognostics framework to predict both capacity and power fade simultaneously with multi-task learning. The model is able to predict the degradation trajectory of both capacity and internal resistance together with knee-points and end-of-life points accurately at early-life stage. The validation shows an average percentage error of 2.37% and 1.24% for the prediction of capacity fade and resistance rise, respectively. The model's ability to accurately predict the degradation, facing capacity and resistance estimation errors, further demonstrates the model's robustness and generalizability. Compared with single-task learning models for forecasting capacity and power degradation, the model shows a significant prediction accuracy improvement and computational cost reduction. This work presents the highlights of multi-task learning in the degradation prognostics for lithium-ion batteries.

View Accepted Manuscript (DOE)

Research Organization:: SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)

Sponsoring Organization:: USDOE Office of Science (SC)

Grant/Contract Number:: AC02-76SF00515

OSTI ID:: 2006551

Journal Information:: Energy Storage Materials, Journal Name: Energy Storage Materials Vol. 53; ISSN 2405-8297

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (40)

A naive Bayes model for robust remaining useful life prediction of lithium-ion battery Ng, Selina S. Y.; Xing, Yinjiao; Tsui, Kwok L. Applied Energy, Vol. 118 https://doi.org/10.1016/j.apenergy.2013.12.020	journal	April 2014
A novel multistage Support Vector Machine based approach for Li ion battery remaining useful life estimation Patil, Meru A.; Tagade, Piyush; Hariharan, Krishnan S. Applied Energy, Vol. 159 https://doi.org/10.1016/j.apenergy.2015.08.119	journal	December 2015
An online method for lithium-ion battery remaining useful life estimation using importance sampling and neural networks Wu, Ji; Zhang, Chenbin; Chen, Zonghai Applied Energy, Vol. 173 https://doi.org/10.1016/j.apenergy.2016.04.057	journal	July 2016
Satellite lithium-ion battery remaining useful life estimation with an iterative updated RVM fused with the KF algorithm Song, Yuchen; Liu, Datong; Hou, Yandong Chinese Journal of Aeronautics, Vol. 31, Issue 1 https://doi.org/10.1016/j.cja.2017.11.010	journal	January 2018
Influence analysis of static and dynamic fast-charging current profiles on ageing performance of commercial lithium-ion batteries Abdel-Monem, Mohamed; Trad, Khiem; Omar, Noshin Energy, Vol. 120 https://doi.org/10.1016/j.energy.2016.12.110	journal	February 2017
Data-driven systematic parameter identification of an electrochemical model for lithium-ion batteries with artificial intelligence Li, Weihan; Demir, Iskender; Cao, Decheng Energy Storage Materials, Vol. 44 https://doi.org/10.1016/j.ensm.2021.10.023	journal	January 2022
Nonlinear aging characteristics of lithium-ion cells under different operational conditions Schuster, Simon F.; Bach, Tobias; Fleder, Elena Journal of Energy Storage, Vol. 1 https://doi.org/10.1016/j.est.2015.05.003	journal	June 2015
Nonlinear health evaluation for lithium-ion battery within full-lifespan You, Heze; Zhu, Jiangong; Wang, Xueyuan Journal of Energy Chemistry, Vol. 72 https://doi.org/10.1016/j.jechem.2022.04.013	journal	September 2022
Predicting the impact of formation protocols on battery lifetime immediately after manufacturing Weng, Andrew; Mohtat, Peyman; Attia, Peter M. Joule, Vol. 5, Issue 11 https://doi.org/10.1016/j.joule.2021.09.015	journal	November 2021
Cycling degradation of an automotive LiFePO₄ lithium-ion battery Zhang, Yancheng; Wang, Chao-Yang; Tang, Xidong Journal of Power Sources, Vol. 196, Issue 3, p. 1513-1520 https://doi.org/10.1016/j.jpowsour.2010.08.070	journal	February 2011
Genetic identification and fisher identifiability analysis of the Doyle–Fuller–Newman model from experimental cycling of a LiFePO4 cell Forman, Joel C.; Moura, Scott J.; Stein, Jeffrey L. Journal of Power Sources, Vol. 210 https://doi.org/10.1016/j.jpowsour.2012.03.009	journal	July 2012
Health diagnosis and remaining useful life prognostics of lithium-ion batteries using data-driven methods Nuhic, Adnan; Terzimehic, Tarik; Soczka-Guth, Thomas Journal of Power Sources, Vol. 239 https://doi.org/10.1016/j.jpowsour.2012.11.146	journal	October 2013
Design and parametrization analysis of a reduced-order electrochemical model of graphite/LiFePO4 cells for SOC/SOH estimation Marcicki, James; Canova, Marcello; Conlisk, A. Terrence Journal of Power Sources, Vol. 237 https://doi.org/10.1016/j.jpowsour.2012.12.120	journal	September 2013
Prognostics of lithium-ion batteries based on relevance vectors and a conditional three-parameter capacity degradation model Wang, Dong; Miao, Qiang; Pecht, Michael Journal of Power Sources, Vol. 239 https://doi.org/10.1016/j.jpowsour.2013.03.129	journal	October 2013
Production caused variation in capacity aging trend and correlation to initial cell performance Baumhöfer, Thorsten; Brühl, Manuel; Rothgang, Susanne Journal of Power Sources, Vol. 247 https://doi.org/10.1016/j.jpowsour.2013.08.108	journal	February 2014
Review and recent advances in battery health monitoring and prognostics technologies for electric vehicle (EV) safety and mobility Rezvanizaniani, Seyed Mohammad; Liu, Zongchang; Chen, Yan Journal of Power Sources, Vol. 256 https://doi.org/10.1016/j.jpowsour.2014.01.085	journal	June 2014
A holistic aging model for Li(NiMnCo)O2 based 18650 lithium-ion batteries Schmalstieg, Johannes; Käbitz, Stefan; Ecker, Madeleine Journal of Power Sources, Vol. 257 https://doi.org/10.1016/j.jpowsour.2014.02.012	journal	July 2014
Lithium plating in a commercial lithium-ion battery – A low-temperature aging study Petzl, Mathias; Kasper, Michael; Danzer, Michael A. Journal of Power Sources, Vol. 275 https://doi.org/10.1016/j.jpowsour.2014.11.065	journal	February 2015
Capacity and power fade cycle-life model for plug-in hybrid electric vehicle lithium-ion battery cells containing blended spinel and layered-oxide positive electrodes Cordoba-Arenas, Andrea; Onori, Simona; Guezennec, Yann Journal of Power Sources, Vol. 278 https://doi.org/10.1016/j.jpowsour.2014.12.047	journal	March 2015
Correlation between capacity and impedance of lithium-ion cells during calendar and cycle life Schuster, Simon F.; Brand, Martin J.; Campestrini, Christian Journal of Power Sources, Vol. 305 https://doi.org/10.1016/j.jpowsour.2015.11.096	journal	February 2016
Failure statistics for commercial lithium ion batteries: A study of 24 pouch cells Harris, Stephen J.; Harris, David J.; Li, Chen Journal of Power Sources, Vol. 342 https://doi.org/10.1016/j.jpowsour.2016.12.083	journal	February 2017
Gaussian process regression for forecasting battery state of health Richardson, Robert R.; Osborne, Michael A.; Howey, David A. Journal of Power Sources, Vol. 357 https://doi.org/10.1016/j.jpowsour.2017.05.004	journal	July 2017
A review on battery thermal management in electric vehicle application Xia, Guodong; Cao, Lei; Bi, Guanglong Journal of Power Sources, Vol. 367 https://doi.org/10.1016/j.jpowsour.2017.09.046	journal	November 2017
Theory of battery ageing in a lithium-ion battery: Capacity fade, nonlinear ageing and lifetime prediction Atalay, Selcuk; Sheikh, Muhammad; Mariani, Alessandro Journal of Power Sources, Vol. 478 https://doi.org/10.1016/j.jpowsour.2020.229026	journal	December 2020
One-shot battery degradation trajectory prediction with deep learning Li, Weihan; Sengupta, Neil; Dechent, Philipp Journal of Power Sources, Vol. 506 https://doi.org/10.1016/j.jpowsour.2021.230024	journal	September 2021
A new prognostics method for state of health estimation of lithium-ion batteries based on a mixture of Gaussian process models and particle filter Li, Fan; Xu, Jiuping Microelectronics Reliability, Vol. 55, Issue 7 https://doi.org/10.1016/j.microrel.2015.02.025	journal	June 2015
Multitask Learning Caruana, Rich Machine Learning, Vol. 28, Issue 1, p. 41-75 https://doi.org/10.1023/A:1007379606734	journal	January 1997
Data-driven capacity estimation of commercial lithium-ion batteries from voltage relaxation Zhu, Jiangong; Wang, Yixiu; Huang, Yuan Nature Communications, Vol. 13, Issue 1 https://doi.org/10.1038/s41467-022-29837-w	journal	April 2022
Data-driven prediction of battery cycle life before capacity degradation Severson, Kristen A.; Attia, Peter M.; Jin, Norman Nature Energy, Vol. 4, Issue 5 https://doi.org/10.1038/s41560-019-0356-8	journal	March 2019
Estimation of Potentials in Lithium-Ion Batteries Using Machine Learning Models Li, Weihan; Limoge, Damas W.; Zhang, Jiawei IEEE Transactions on Control Systems Technology, Vol. 30, Issue 2 https://doi.org/10.1109/TCST.2021.3071643	journal	March 2022
System Identification and Estimation Framework for Pivotal Automotive Battery Management System Characteristics Pattipati, Bharath; Sankavaram, Chaitanya; Pattipati, Krishna IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), Vol. 41, Issue 6 https://doi.org/10.1109/TSMCC.2010.2089979	journal	November 2011
L 1-Regularization Path Algorithm for Generalized Linear Models Park, Mee Young; Hastie, Trevor Journal of the Royal Statistical Society Series B: Statistical Methodology, Vol. 69, Issue 4 https://doi.org/10.1111/j.1467-9868.2007.00607.x	journal	August 2007
Electrochemical Modeling of Linear and Nonlinear Aging of Lithium-Ion Cells Keil, Jonas; Jossen, Andreas Journal of The Electrochemical Society, Vol. 167, Issue 11 https://doi.org/10.1149/1945-7111/aba44f	journal	January 2020
Theory of SEI Formation in Rechargeable Batteries: Capacity Fade, Accelerated Aging and Lifetime Prediction Pinson, Matthew B.; Bazant, Martin Z. Journal of The Electrochemical Society, Vol. 160, Issue 2 https://doi.org/10.1149/2.044302jes	journal	December 2012
Application of Time-Resolved Multi-Sine Impedance Spectroscopy for Lithium-Ion Battery Characterization Zappen, Hendrik; Ringbeck, Florian; Sauer, Dirk Batteries, Vol. 4, Issue 4 https://doi.org/10.3390/batteries4040064	journal	December 2018
Model-Based Investigation of Porosity Profiles in Graphite Anodes Regarding Sudden-Death and Second-Life of Lithium Ion Cells Müller, Daniel; Dufaux, Thomas; Birke, Kai Peter Batteries, Vol. 5, Issue 2 https://doi.org/10.3390/batteries5020049	journal	June 2019
In-Operando Impedance Spectroscopy and Ultrasonic Measurements during High-Temperature Abuse Experiments on Lithium-Ion Batteries Zappen, Hendrik; Fuchs, Georg; Gitis, Alexander Batteries, Vol. 6, Issue 2 https://doi.org/10.3390/batteries6020025	journal	April 2020
Algorithm to Determine the Knee Point on Capacity Fade Curves of Lithium-Ion Cells Diao, Weiping; Saxena, Saurabh; Han, Bongtae Energies, Vol. 12, Issue 15 https://doi.org/10.3390/en12152910	journal	July 2019
Elbows of Internal Resistance Rise Curves in Li-Ion Cells Strange, Calum; Li, Shawn; Gilchrist, Richard Energies, Vol. 14, Issue 4 https://doi.org/10.3390/en14041206	journal	February 2021
Post-Mortem Analysis of Inhomogeneous Induced Pressure on Commercial Lithium-Ion Pouch Cells and Their Effects Fuchs, Georg; Willenberg, Lisa; Ringbeck, Florian Sustainability, Vol. 11, Issue 23 https://doi.org/10.3390/su11236738	journal	November 2019

Similar Records

Life Prediction Model for Grid-Connected Li-ion Battery Energy Storage System: Preprint

Conference · Fri Aug 25 00:00:00 EDT 2017 · OSTI ID:1378083

Life Prediction Model for Grid-Connected Li-ion Battery Energy Storage System

Conference · Wed Sep 06 00:00:00 EDT 2017 · OSTI ID:1390498

A Convolutional Neural Network Model for Battery Capacity Fade Curve Prediction using Early Life Data

Journal Article · Wed Jun 29 00:00:00 EDT 2022 · Journal of Power Sources · OSTI ID:1910034

Related Subjects

25 ENERGY STORAGE
Capacity
Degradation
Lithium-ion battery
Multi-task learning
Power

Forecasting battery capacity and power degradation with multi-task learning

Citation Formats

References (40)

Similar Records

Related Subjects