Abstract：The remaining useful life (RUL) of lithium-ion battery is difficult to predict accurately, and the capacity data cannot be measured online in real time. Based on indirect health factors, a method for predicting the remaining useful life of lithium-ion battery is proposed in this paper. Firstly, the discharge voltage rate is extracted as an indirect health parameter index, and the discharge voltage rate data is decomposed by local mean decomposition (LMD). Then the grey correlation degree is used to verify the high correlation degree between the decoupled discharge voltage rate data and the battery capacity, and the extreme learning machine (ELM) training model is used to predict the remaining useful life of lithium-ion battery. Finally, the indirect health factors are input into the LMD-ELM model to obtain the accurate prediction value of battery capacity. The NASA data set is used to verify that the mean square error of the remaining useful life of lithium-ion battery predicted by the method proposed in this paper is less than 0.22%, and the average absolute percentage error is less than 3.12%.
于沛, 王常乐. 基于局部均值分解和极限学习机的锂电池剩余寿命预测[J]. 电气技术, 2023, 24(1): 23-28.
YU Pei, WANG Changle. Remaining life prediction of lithium-ion battery based on local mean decomposition and extreme learning machine. Electrical Engineering, 2023, 24(1): 23-28.
2023, Vol. 24 
