Early Prediction of Battery Cycle Life Using Machine Learning
Date
2021-01-26
Authors
Liu, Wenmeng
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Lithium-ion batteries are widely used in transportation and vehicle electrification because of their low cost, high-energy density, and long lifetime. However, aging, complex nonlinear degradation, and diverse operation conditions degrade the performance of batteries. In addition, it often takes months to years to evaluate the cycle life of an Li-ion battery. Therefore, accurate prediction of the cycle life using the data from the first few cycles is imperative.
In this study, supervised Machine Learning (ML) techniques are used to develop data-driven models that can accurately predict the cycle life of lithium iron phosphate (LFP) batteries. This model is built using battery data from the first 300 cycles, at which point most batteries have yet to exhibit capacity degradation. The dataset employed consists of experimental results for 124 LFP batteries tested under 72 fast charging protocols. This dataset is one of the largest open-access datasets for Li-ion batteries. To investigate the electrochemical evolution of each battery, 14 domain-based features are considered which fall into three categories: ∆Q(V) features, discharge capacity, and physical measurements related to battery degradation (such as internal resistance). ∆Q(V) is the discharge capacity difference between the end and start cycles at a discharge voltage V. An early prediction model on cycle life can be regarded as a regression problem. A subset of these features is used as input to the ML models. The ML models used in this study are a linear model with L1 and L2 norm regularization (elastic net), a tree-based model (random forest), and a linear model with L1 norm regularization (benchmark). The benchmark model only uses the log variance of ∆Q(V) due to its high correlation with cycle life. The elastic net model provides the best overall prediction performance (7.28% test error), followed by the random forest model (7.85% test error) and the benchmark model (11.45% test error).
Description
Keywords
Machine learning, Cycle life