An Incremental Capacity Analysis-based State-of-health Estimation Model for Lithium-ion Batteries in High-power Applications

Abstract

The Incremental Capacity (IC) is a rich source of data for the state-of-health estimation of lithium-ion batteries. This data is typically collected during a low C-rate (dis)charge of the battery which is not representative of many real-world applications outside the research laboratories. Here, this limitation is showcased to be mitigated by employing a new feature-extraction technique applied to a large dataset including 105 batteries with cycle lives ranging from 158 to 1637 cycles. The state-of-health of these batteries is successfully predicted with a mean-absolute-percentage error below 0.7 % by using three regression models of support vector regressor, multi-layer perceptron, and random forest. The methodologies proposed in this work facilitate the development of accurate IC-based state-of-health predictors for lithium-ion batteries in on-board applications.