State of Charge Estimation for Lithium-Ion Batteries Using Machine Learning Algorithms

Abstract

An effective Battery Management System (BMS) is compulsory for the safe and reliable operation of lithium-ion batteries, which are increasingly being used in Electric Vehicles (EVs). Accurate State of Charge estimation (SoC) is a cumbersome task, since lithium-ion batteries are highly influenced by such random factors including driving loads, operational conditions, and aging. This work presents a comparison study of various machine learning algorithms for SoC estimation. To do this, a 3Ah LGHG2 battery cell was put through a series of temperature and driving cycle tests. The proposed models are evaluated in terms of accuracy and robustness. The simulation results have shown that the Gaussian Process Regression (GPR) model outperforms the other algorithms achieving R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> and RMSE values of (97 %, 1.3 %) and (95 %, 1.6 %) in normal conditions and in a noisy environment, respectively.