Intelligent Power Sharing by Battery and Ultracapacitor in Regular Routes of EV

Nowadays, hybrid energy storage system (HESS) is widely used in high-performance vehicles to fulfill the instant power requirement. Such kind of energy storage system (ESS) can become extremely useful for electric vehicles (EVs) driving in hilly regions. However, maintaining the state-of-charge (SoC) of the ultracapacitor (UC) during aggressive driving conditions is still a challenge and requires a reliable mechanism. In this context, this paper employs artificial intelligence (AI) and its capability to predict the present and future requirements of the UC current. In the proposed method, the ANN model is trained using regular route driving data to generate a reference of transient current during EV traction. Further, the model charges the UC during the deceleration of the EV as per the predicted future current requirement. It has been modeled and simulated in MATLAB/Simulink considering the actual data of the vehicle. The hardware prototype consists of a 51.2 V, 86 Ah Li-ion battery and 19.3 F, 51 V UC integrated with 48 V, 48 A, 3 kW IPMSM setup. In the developed driving cycle, velocity, and road slope vary along the direction of traction and braking. The experimental results show that the battery energy utilization is 13.13% less in the ANN-based method as compared to the rule-based method. Additionally, the peak battery current is reduced by 26.6% and the battery power has a minimum standard deviation in the ANN-based method as compared to the battery-only method. As a result, the battery state-of-health (SoH) improves by 21.43% which leads to 2.71 years of battery lifetime enhancement in regular routes of driving.