AUTHOR=Chen Yuan , Duan Wenxian , Ding Zhenhuan , Li Yingli 

TITLE=Battery Life Prediction Based on a Hybrid Support Vector Regression Model

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.899804

DOI=10.3389/fenrg.2022.899804

ISSN=2296-598X

ABSTRACT=Accurate state of health and remaining useful life prediction is important to provide effective judgment for the lithium-ion battery and reduce the probability of failure. This paper proposes a hybrid model for the prediction combining an improved decomposition algorithm, improved parameterization algorithm and the least squares support vector regression algorithm. The capacity signal is decomposed by the improved complete ensemble empirical mode decomposition with adaptive noise algorithm to solve the backward problem. Then the least squares support vector regression algorithm is used to predict each component of the decomposition separately. To obtain better parameters of the model, good point set principle and inertia weight are introduced to optimize the sparrow search algorithm. Experimental results confirm that the hybrid prediction model has high accuracy, good stability and strong robustness, which achieves minimum 0.3% mean absolute error of B0005 battery. The impact of prediction steps on accuracy is also discussed in this paper, the available capacity of the battery predicted by 8 steps is still accurate.