Lithium-ion battery state of health estimation based on multi-source health indicators extraction and sparse Bayesian learning

Abstract

A concise and accurate method for estimating the state of health (SOH) of lithium-ion batteries in the on-board energy management system is critical. However, SOH cannot be directly measured by on-board equipment. To improve the accuracy of SOH estimation for Li-ion batteries, this work proposes an SOH estimation model based on multi-source health indicators (HIs) extraction and sparse Bayesian learning. First, four direct HIs are extracted from the voltage and temperature curves of the batteries during charging and discharging, and two indirect HIs are extracted from the incremental capacity curves in combination with a Gaussian filtering algorithm. Then, the datasets are divided into three different training and test sets, which are used to simulate online SOH estimation under different situations. Finally, the six extracted HIs are selected using the Pearson correlation coefficient method, and the experiment is repeated for one of the situations using the three higher correlation features, and the results before and after selection are compared. The experimental results show that the proposed model can achieve satisfactory results in various simulated online estimation situations on the NASA and Oxford datasets.