Indirect prediction of remaining useful life for lithium-ion batteries based on improved multiple kernel extreme learning machine

Abstract

Lithium-ion batteries (LIBs) will undergo aging after a certain period of operation. Predicting RUL in advance is critical to ensure a reliable energy supply from the battery system. To address the problem of poor robustness of the single-core extreme learning machine model in predicting the RUL of LIBs, a multiple kernel extreme learning machine (MKELM) integrating radial basis function (RBF) and Poly kernel function is proposed. Firstly, introduce the sparrow search algorithm improved by logistic chaotic mapping (ISSA) to optimize the parameter selection of the MKELM, which overcomes the inefficiency of parameter selection, and improves the efficiency of the global optimal parameter selection. Secondly, from the charging/discharging processes, extract the health indicators (HIs) and examine the correlation capacity via methods of Pearson, Spearman, and Kendall. Finally, validate the ISSA-MKELM with the NASA battery dataset, and the prediction results are compared with traditional methods. Results show that, with the lowest prediction error (less than 2.38 %), ISSA-MKELM has good state tracking fit and excellent computational efficiency performance but also has strong generalization and robustness.