Improved Battery Cycle Life Prediction Using a Hybrid Data-Driven Model Incorporating Linear Support Vector Regression and Gaussian
2022 (English)In: ChemPhysChem, ISSN 1439-4235, E-ISSN 1439-7641, Vol. 23, no 7, article id e202100829Article in journal (Refereed) Published
Abstract [en]
The ability to accurately predict lithium-ion battery life-time already at an early stage of battery usage is critical for ensuring safe operation, accelerating technology development, and enabling battery second-life applications. Many models are unable to effectively predict battery life-time at early cycles due to the complex and nonlinear degrading behavior of lithium-ion batteries. In this study, two hybrid data-driven models, incorporating a traditional linear support vector regression (LSVR) and a Gaussian process regression (GPR), were developed to estimate battery life-time at an early stage, before more severe capacity fading, utilizing a data set of 124 battery cells with lifetimes ranging from 150 to 2300 cycles. Two type of hybrid models, here denoted as A and B, were proposed. For each of the models, we achieved 1.1 % (A) and 1.4 % (B) training error, and similarly, 8.3 % (A) and 8.2 % (B) test error. The two key advantages are that the error percentage is kept below 10 % and that very low error values for the training and test sets were observed when utilizing data from only the first 100 cycles.The proposed method thus appears highly promising for predicting battery life during early cycles.
Place, publisher, year, edition, pages
Wiley , 2022. Vol. 23, no 7, article id e202100829
Keywords [en]
battery cycle life, cycle life prediction, data-driven modeling, Gaussian process regression, linear support vector regression, Errors, Forecasting, Gaussian distribution, Gaussian noise (electronic), Life cycle, Regression analysis, Battery life time, Cycle life predictions, Data-driven model, Gaussians, Hybrid datum, Safe operation, Support vector regressions, Lithium-ion batteries
National Category
Probability Theory and Statistics Energy Engineering
Identifiers
URN: urn:nbn:se:kth:diva-321185DOI: 10.1002/cphc.202100829ISI: 000762567400001PubMedID: 35075749Scopus ID: 2-s2.0-85125384789OAI: oai:DiVA.org:kth-321185DiVA, id: diva2:1709542
Note
QC 20221109
2022-11-092022-11-092023-07-17Bibliographically approved