Multiple layer kernel extreme learning machine modeling and eugenics genetic sparrow search algorithm for the state of health estimation of lithium-ion batteries

Abstract

High precision state of health (SOH) estimation of lithium-ion batteries (LIBs) is a research hotspot in battery management system (BMS). To achieve this goal, an improved integrated algorithm based on multiple layer kernel extreme learning machine (ML-KELM) and eugenics genetic sparrow search (EGSS) algorithm is proposed to estimate the SOH of LIBs. First, a kernel version of ML-ELM model is constructed for initial SOH estimation of LIBs. The kernel function parameters are used to simulate sparrow foraging and anti-predatory behaviors, and the parameter optimization process is completed in the proposed EGSS algorithm by iteratively updating the position of sparrows to improve SOH prediction accuracy and model stability. The cycle data of different specifications of LIB units are processed to construct the high-dimensional health feature (HF) dataset and the low-dimensional fusion feature (FF) dataset, and each version of ML-ELM network is trained and tested separately. The numerical analysis of the prediction results shows that the best root mean square error (RMSE) of the comprehensive algorithm for SOH estimation is limited within 0.29%. The results of the multi-indicator comparison show that the proposed algorithm can track the true value stably and accurately with satisfactory high accuracy and strong robustness.