Environmental issues have become a global concern recently. Countries worldwide are making efforts for carbon neutrality. In the automotive industry, focus has shifted from internal combustion engine vehicle to eco-friendly vehicles such as Electric Vehicles (EVs), Hybrid Electric Vehicles (HEVs), and Fuel Cell Electric Vehicles (FCEVs). For driving strategy, research on vehicle driving method that can reduce vehicle energy consumption, called eco-driving, has been actively conducted recently. Conventional cruise mode driving control is not considered an optimal driving strategy for various driving environments. To maximize energy efficiency, this paper conducted research on eco-driving strategy for EVs-based on reinforcement learning. A longitudinal dynamics-based electric vehicle simulator was constructed using MATLAB Simulink with a road slope. Reinforcement learning algorithms, specifically Deep Deterministic Policy Gradient (DDPG) and Deep QNetwork (DQN), were applied to minimize energy consumption of EVs with a road slope. The simulator was trained to maximize rewards and derive an optimal speed profile. In this study, we compared learning results of DDPG and DQN algorithms and confirmed tendencies by parameters in each algorithm. The simulation showed that energy efficiency of EVs was improved compared to that of cruise mode driving.

This study is to investigate the cooling performance of the secondary battery in electric vehicles according to three different gaps between battery cells. To accomplish the convective cooling performance of the battery surface with three different gaps, selected local positions (X, Y, Z) for various temperature distributions were marked on the gap surface contacting the cell surface. The cooling performance of the gap of 0.5 mm was compared with the gaps of 5 mm, and 1 mm. Normalized local Nusselt number of the cooling area at the normalized width position indicated that the gap of 0.5 mm was on average 26.99% lower than that of 5 mm and 0.49% lower than that of 1 mm. At the normalized height, the gap of 0.5 mm was on average 12.12% higher than that of 1 mm. Because of the vortex at the outlet area, cooling performance at the gap of 0.5 mm was on average 13.19% higher than that of 5 mm and 0.79% higher than that of 1 mm at normalized thickness. Ultimately, the best cooling performance existed at the gap of 5 mm, but the gap of 0.5 mm was best for improving space efficiency, energy storage capacity, and vehicle-driving durability.

This study is to investigate convection cooling performance of the Secondary Battery of Electric Vehicle without heat sink. Research is focused on the comparative study on cooling between forced convection and natural convection cooling. Selected local locations for various temperature distributions had shown in the flow domain. Final temperature on the cell surface has been compared by forced convection with natural convection. According to the results of velocity and temperature distributions in the fluid domain, Buoyancy appear by density difference in the natural convection. Apparent vortex was detected in the fluid domain for forced convection. According to calculations of convective heat transfer coefficient between cell and atmosphere in the battery pack, average value of more 70-78% heat transfer coefficient increased by forced convection than natural convection. Average temperature value of the cell surface decreased up to 46.50% by forced convection. Due to vortex by air, cooling performance of forced convection is excellent. In addition, cooling on edge of the battery is better than heat source location.