Search

Electric vehicles (EVs) have received extensive attention as an environmentally friendly and sustainable mode of transportation. To address "range anxiety" issues, extended-range electric vehicles (EREVs) have gradually gained popularity as a solution. However, current research on energy management strategies (EMS) for EVs often overlooks the energy consumption of the air conditioning (AC) system, resulting in suboptimal energy allocation. Therefore, this study focuses on the extended-range electric bus (EREbus), an extended-range electric bus, and incorporates the AC system into its EMS, enabling coordinated optimization with the powertrain system. First, the study embeds a control-oriented cabin thermal management model based on the powertrain model. Next, representations transfer-based reinforcement learning (RTRL) transfers the learned policy representations from the AC-off state to the EMS in the AC-on state. Furthermore, the study analyzes the impact of different representation transfers on powertrain performance and thermal comfort. The results demonstrate that the proposed EMS can improve the convergence rate and stability of training. Compared to direct learning methods, RTRL exhibits clear advantages in reducing operating costs and improving cabin thermal comfort, achieving reductions of 8.3%–12.6 % and 5.2%–27.0 % in operating costs for driving modes with different battery levels. Moreover, setting the transfer layer appropriately promotes the utilization of the global optimal potential of RTRL. This research provides support for energy management and holds the potential for promoting the development of EVs. • A novel vehicle thermal management model achieving cabin comfort regulation by controlling the evaporator and the blower. • A transfer-based reinforcement learning method enables the new comfort-aware energy management. • A collaborative strategy was tested in an extended-range electric bus model under various of driving conditions. [ABSTRACT FROM AUTHOR]

This paper proposes an offline sizing method and an online energy management strategy for the electric vehicle with semi-active hybrid battery system (HBS). The semi-active HBS is composed by Nickel Cobalt Rechargeable (NCR) and lithium titanate (LTO) batteries with a bi-directional DC/DC converter. First, the vehicle dynamics and the HBS are modelled. Second, a hierarchical optimal sizing method is proposed to minimize the distance-based cost (DBC) of electric taxi in a variety of driving cycles. The lower layer optimizes the energy management strategy (EMS) with dynamic programming (DP), while the upper layer optimizes the sizes of HBS for minimum DBC. Based on the sizing results, the DBC decreases firstly and then increases with the increasing LTO size. In addition, the results of DP indicate the SOC of the LTO batteries works between 50% and 80% for optimal NCR lifespan. Third, by using the rule extracted from DP, a learning-based EMS, i.e., deep deterministic policy gradient (DDPG), is proposed with excellent real-time control potential. Finally, the simulation results show that the proposed DDPG EMS achieves the improved performance than fuzzy logic control EMS and closed result with what can be achieved through DP, yet the computation time is much less. • NCR/LTO hybrid battery system is proposed. • A hierarchical framework is proposed to optimize the size of HBS. • Rule-based strategy is extracted from the optimal EMS. • DDPG is proposed to achieve the near-optimal real-time control. [ABSTRACT FROM AUTHOR]