A method based on improved ant lion optimization and support vector regression for remaining useful life estimation of lithium‐ion batteries

Abstract

Abstract Remaining useful life (RUL) prediction of lithium‐ion batteries (LIBs) plays a very important role in the prognostics and health management (PHM). Accurately predicting RUL of batteries can maintain and replace the batteries in advance to guarantee the safety and stability of the energy storage system (ESS). A method based on improved ant lion optimization and support vector regression (IALO‐SVR) is proposed to accurately predict RUL of LIBs. The ALO algorithm easily falls into the local optimal solution, the levy flight algorithm is utilized to improve the shortcoming of the ALO algorithm. With the mathematical comparison of particle swarm optimization (PSO), differential evolution (DE), and ALO algorithms, the results indicate that the IALO algorithm has higher convergence accuracy. Experimental data simulations were performed using the battery datasets of NASA Prognostics Center of Excellence (PCoE) and the Center for Advanced Life Cycle Engineering (CALCE) to verify the proposed method. Through comparison with SVR, PSO‐LSSVM, and ALO‐SVR methods, the results indicate that the RUL prediction is more accurate based upon the IALO‐SVR method. Therefore, the proposed method can provide high prediction accuracy in battery health prognosis.

Keywords

• improved ant lion optimization
• lithium‐ion battery
• remaining useful life
• support vector regression