Abstract
Efficient battery health indicator (HI) extraction and accurate estimation method are two important issues in the study of battery state of health (SOH) estimation. Although machine learning-based methods have been widely applied to the battery SOH estimation in recent years, the battery HI extraction in most studies is too tedious, the estimation method lacks pertinence, and the aging pattern of the battery aging dataset is simple. To solve the above problems, this paper proposes a novel battery HI based on the charging duration of the equal voltage intervals in the constant current charging process, which can effectively characterize the battery aging characteristics by only 10 continuous charging duration counts directly from the battery management system. Considering the difficulty of collecting battery aging data and the high dimensionality of the extracted HI, the least squares support vector regression (LSSVR), which is suitable for small samples and high dimensional data, is used to build the SOH mapping model and the optimal hyperparameters are found with the help of particle swarm optimization (PSO). The satisfactory SOH estimation accuracy of the proposed method is validated on a public LiFePO4 battery aging dataset containing different temperatures, discharge rates, discharge depths and cycle intervals.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
