Battery cycle life study through relaxation and forecasting the lifetime via machine learning

被引:43
作者
Hosen, Md Sazzad [1 ]
Youssef, Rekabra [1 ]
Kalogiannis, Theodoros [1 ]
Van Mierlo, Joeri [1 ]
Berecibar, Maitane [1 ]
机构
[1] Vrije Univ Brussel, MOBI Res Grp, Battery Innovat Ctr, Pl Laan 2, B-1050 Brussels, Belgium
关键词
Relaxation study; Battery lifetime; Aging modeling; Machine learning; Gaussian process; Real-life validation; LITHIUM-ION BATTERIES; HEALTH ESTIMATION; CAPACITY RECOVERY; AGING MECHANISMS; MODEL; STATE; PROGNOSTICS; REGRESSION; CALENDAR; CELLS;
D O I
10.1016/j.est.2021.102726
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Battery lifetime modeling and prediction of precise capacity degradation for real-life applications are critical to understanding the complex and non-linear battery behavior. However, the application of accurate and robust aging models on dynamic on-road scenarios is still a challenge. In this work, a comprehensive aging dataset of 40 Nickel Manganese Cobalt (NMC) cells is generated for two years considering distinct relaxation phases in the function of the state of charge (SoC), temperature, and time. A qualitative analysis of the diversified aging parameters along with the sensitivity analysis of the rest criteria is conducted. Taking the discharge capacity as the pivotal predictor, a robust training dataset is built and preliminary fed to common data-driven models. Among them, the Gaussian process regression (GPR) is identified to be the best suit with which a 0.02% root-meansquared error (RMSE) can be achieved for battery life prediction when tested with a static profile choosing an exponential kernel. Further, to demonstrate a real-life scenario, a worldwide harmonized light-duty test cycle (WLTC) is performed, and the capacity fade percentile can be predicted accurately with a 0.05% RMSE. This research shows that data-driven algorithms like GPR can be a promising online tool that can forecast the entire lifetime with high precision for dynamic profiles.
引用
收藏
页数:11
相关论文
共 48 条
[1]   Advanced mathematical methods of SOC and SOH estimation for lithium-ion batteries [J].
Andre, Dave ;
Appel, Christian ;
Soczka-Guth, Thomas ;
Sauer, Dirk Uwe .
JOURNAL OF POWER SOURCES, 2013, 224 :20-27
[2]   A review on lithium-ion battery ageing mechanisms and estimations for automotive applications [J].
Barre, Anthony ;
Deguilhem, Benjamin ;
Grolleau, Sebastien ;
Gerard, Mathias ;
Suard, Frederic ;
Riu, Delphine .
JOURNAL OF POWER SOURCES, 2013, 241 :680-689
[3]   Critical review of state of health estimation methods of Li-ion batteries for real applications [J].
Berecibar, M. ;
Gandiaga, I. ;
Villarreal, I. ;
Omar, N. ;
Van Mierlo, J. ;
Van den Bossche, P. .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2016, 56 :572-587
[4]   Degradation diagnostics for lithium ion cells [J].
Birkl, Christoph R. ;
Roberts, Matthew R. ;
McTurk, Euan ;
Bruce, Peter G. ;
Howey, David A. .
JOURNAL OF POWER SOURCES, 2017, 341 :373-386
[5]   Stress evolution and capacity fade in constrained lithium-ion pouch cells [J].
Cannarella, John ;
Arnold, Craig B. .
JOURNAL OF POWER SOURCES, 2014, 245 :745-751
[6]   Cyclable lithium and capacity loss in Li-ion cells [J].
Christensen, J ;
Newman, J .
JOURNAL OF THE ELECTROCHEMICAL SOCIETY, 2005, 152 (04) :A818-A829
[7]  
Christensen J., 2014, MATH MODEL LITHIUM I, P1, DOI [10.1149/1.1804812, DOI 10.1149/1.1804812]
[8]   A combined thermo-electric resistance degradation model for nickel manganese cobalt oxide based lithium-ion cells [J].
de Hoog, Joris ;
Jaguemont, Joris ;
Nikolian, Alexandros ;
Van Mierlo, Joeri ;
Van Den Bossche, Peter ;
Omar, Noshin .
APPLIED THERMAL ENGINEERING, 2018, 135 :54-65
[9]   Combined cycling and calendar capacity fade modeling of a Nickel-Manganese-Cobalt Oxide Cell with real-life profile validation [J].
de Hoog, Joris ;
Timmermans, Jean-Marc ;
Ioan-Stroe, Daniel ;
Swierczynski, Maciej ;
Jaguemont, Joris ;
Goutam, Shovon ;
Omar, Noshin ;
Van Mierlo, Joeri ;
Van den Bossche, Peter .
APPLIED ENERGY, 2017, 200 :47-61
[10]  
Dubarry M., 2020, BENCHMARK SYNTHETIC, P1, DOI 10.20944/