State of Charge Estimation Using Data-Driven Techniques for Storage Devices in Electric Vehicles

Abstract

This paper develops a state of charge (SOC) estimation mechanism for electric vehicle batteries using machine learning technique. Conventionally, the battery SOC is estimated using a model-based approach which requires extensive modeling, experimentation, and validation before accurate SOC estimation. The technique proposed in this research is unique and does not require the battery temperature or capacity as inputs which are essential for model-based estimation. Initially, the battery data is simulated, and a machine learning model is developed using support vector data descriptor and validated using the simulated battery data. The developed classification algorithm can estimate the state of charge of the battery and is suitable for online and real-time applications.