A data driven model for accurate SOC estimation in EVs

Abstract

Accurate state of charge (SOC) is critical for battery energy management system in electric vehicle (EV) application. Overcharge and over discharge will shorten battery's lifespan and induce potential safety problem, which may even permanently damage the lithium-ion battery. Thus, a data driven model is proposed for improving the accuracy of SOC estimation in this paper. A preliminary mathematic model under constant current is established, which can match the primary high SOC stage. Since the battery model is nonlinear, model free adaptive control (MFAC) is used to get the dynamic linearization model and accomplish SOC estimation process on the basis of the mathematic model. With the small sample scale of new data updated, a data driven model based on partial least squares (PLS) is obtained online. The accuracy of the mathematic model also decreases during the operating process. Finally, the calculated values from the two different models are mixed for an accurate SOC. Experimental results on lithium polymer battery prove the effectiveness of the proposed method.