Data driven discovery of an analytic formula for the life prediction of Lithium-ion batteries

作     者：Jie Xiong Tong-Xing Lei Da-Meng Fu Jun-Wei Wu Tong-Yi Zhang Jie Xiong;Tong-Xing Lei;Da-Meng Fu;Jun-Wei Wu;Tong-Yi Zhang

作者机构：School of Materials Science and Engineering Harbin Institute of Technology Hong Kong University of Science and Technology (Guangzhou) 

出 版 物：《Progress in Natural Science:Materials International》 (自然科学进展·国际材料(英文))

年 卷 期：2022年第32卷第6期

页      面：793-799页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 

基　　金：supported by the Stable Supporting Fund of Shenzhen (GXWD20201230155427003-20200728114835006) the National Natural Science Foundation of China (Grant Nos. 91860115) 

主　　题：Symbolic regression Machine learning Cycle life prediction Lithium-ion batteries 

摘      要：Predicting the cycle life of Lithium-Ion Batteries（LIBs） remains a great challenge due to their complicated degradation *** present work employs an interpretative machine learning of symbolic regression（SR） to discover an analytic formula for LIB life prediction with newly defined *** novel features are based on the discharging energies under the constant-current（CC） and constant-voltage（CV） modes at every five cycles *** cycle life is affected by the CC-discharging energy at the 15th cycle(E15-CCD) and the difference between the CC-discharging energies at the 45th cycle and 95th cycle(Δ45-95).The cycle life highly correlates with a simple indicator(E15-CCD-3)/Δ45-95with a Pearson correlation coefficient of *** machine learning tools provide a rapid and accurate prediction of cycle life at the early stage.