Online battery health diagnosis for electric vehicles based on DTW-XGBoost
Na Yan, Yan-Bing Yao, Zeng-Dong Jia, Lei Liu, Cui-Ting Dai, Zhigao Li, Zong-Hui Zhang, Wei Li, Lei Wang, Pengfei Wang
Abstract
With the rapid development of electric vehicles, electric vehicle battery health diagnosis has become a hot issue. In order to realize online battery health diagnosis, an online battery health diagnosis platform based on DTW-XGBoost was proposed. The feature extraction method of multi-source data fusion based on clustering was adopted. DTW clustering was used to perform data aggregation and feature extraction for real-time battery data during charging process, and XGBoost algorithm was used to establish SOH prediction model. Build an online battery health diagnosis platform including acquisition and control module, modeling and analysis module and application service module by using cloud platform to improve charging operation and maintenance management level.