The Effects of Driver Speed Prediction-Based Battery Management System on Li-ion Battery Performance for Electric Vehicles

Abstract

The electric vehicle (EV) technologies have received great attention due to the potential contributions to reducing emissions and energy consumption. The relatively short travel distance and battery lifetime of EV are major concerns for consumers. It is suggested that driver behavior plays important role in determining EV battery's electric current and heat generation, which have effects on travel distance of EV and its battery lifetime. To address this problem, the current work proposes a Driver Speed Prediction-Based Battery Management System (P-BMS). P-BMS is able to innovatively predict both electric current and temperature of EV battery based on driver behavior, proactively manage and control both electric current and temperature level of the EV battery in order to minimize energy consumption and maximize both travel distance of EV and EV battery lifetime. Results suggest that P-BMS can significantly reduce energy, extend travel distance in one charge and prolong EV battery lifetime.

Vehicle Deceleration Prediction Model to Reflect Individual Driver Characteristics by Online Parameter Learning for Autonomous Regenerative Braking of Electric Vehicles

“…The prediction of vehicle states based on Intelligent Transportation System (ITS) information can be widely used to improve energy efficiency and driver convenience [1,2,3,4]. For electric vehicles, a smart regenerative control algorithm is an advanced driver assistance system which uses the prediction information of a vehicle decelerating from ITS information.…”

“…Thus, an appropriate prediction algorithm for vehicle states is required to generate the deceleration trajectory as the set point of this autonomous braking control on diverse deceleration conditions. Also, this algorithm should consider individual driver characteristics to apply this automatic braking system more practically [4,9,10,11,12,13,14].…”