Energy management strategy (EMS) is critical for improving the economy of hybrid powertrains and the durability of energy sources. In this paper, a novel EMS based on a twin delayed deep deterministic policy gradient algorithm (TD3) is proposed for a fuel cell hybrid electric bus (FCHEB) to optimize the driving cost of the vehicle. First, a TD3-based energy management strategy is established to embed the limits of battery aging and fuel cell power variation into the strategic framework to fully exploit the economic potential of FCHEB. Second, the TD3-based EMS is compared and analyzed with the deep deterministic policy gradient algorithm (DDPG)-based EMS using real-world collected driving conditions as training data. The results show that the TD3-based EMS has 54.69% higher training efficiency, 36.82% higher learning ability, and 2.45% lower overall vehicle operating cost compared to the DDPG-based EMS, validating the effectiveness of the proposed strategy.

As an auxiliary component with the largest energy consumption in the fuel cell power system, the electric air compressor is of great significance to improve the overall efficiency of the system by reducing its power consumption under the premise of meeting the cathode intake demand. In this paper, the flow state of the gas in the flow field of the fuel cell TSEAC (two-stage electric air compressor) is analyzed by simulation, and the accuracy of the simulation results is verified by experiments. Through the research on the gas compression work of the fuel cell TSEAC, it is found that the higher temperature rise of the gas during the compression process will increase the compression work, thereby reducing the efficiency of the fuel cell TSEAC. Therefore, based on the field synergy theory, this paper designs the heat dissipation structure of the TSEAC elbow. In the common working conditions of fuel cell TSEAC, micro-fin tube is an effective energy-saving structure that takes into account heat dissipation enhancement and flow resistance, and its ratio of micro-fin height to laminar bottom layer thickness ε/δ = 1.6 has the best energy-saving effect. Finally, the energy-saving effect of the micro-fin tube is verified by simulation. The load torque of the optimized fuel cell TSEAC is reduced from 1.540 N·m to 1.509 N·m, and the shaft power is reduced from 14.51 kW to 14.22 kW. Its efficiency increased by 1.9%.

In the context of intelligent and connected transportation, obtaining the real-time vehicle status and comprehensive traffic data is crucial for addressing challenges related to speed optimization and energy regulation in intricate transportation situations. This paper introduces a control method for the speed optimization and energy management of a fuel cell hybrid bus (FCHB) based on the Deep Deterministic Policy Gradient (DDPG) algorithm. The strategy framework is built on a dual-objective optimization deep reinforcement learning (D-DRL) architecture, which integrates traffic signal information into the energy management framework, in addition to conventional state spaces to guide control decisions. The aim is to achieve “green wave” traffic while minimizing hydrogen consumption. To validate the effectiveness of the proposed strategy, simulation tests were conducted using the SUMO platform. The results show that in terms of speed planning, the difference between the maximum and minimum speeds of the FCHB was reduced by 21.66% compared with the traditional Intelligent Driver Model (IDM), while the acceleration and its variation were reduced by 8.89% and 13.21%, respectively. In terms of the hydrogen fuel efficiency, the proposed strategy achieved 95.71% of the performance level of the dynamic programming (DP) algorithm. The solution proposed in this paper is of great significance for improving passenger comfort and FCHB economy.

Recent breakthroughs in artificial intelligence are accelerating the intelligent transformation of vehicles. Vehicle electronic and electrical architectures are converging toward centralized domain controllers. Deep learning, reinforcement learning, and deep reinforcement learning now form the core technologies of domain control. This review surveys advances in deep reinforcement learning in four vehicle domains: intelligent driving, powertrain, chassis, and cockpit. It identifies the main tasks and active research fronts in each domain. In intelligent driving, deep reinforcement learning handles object detection, object tracking, vehicle localization, trajectory prediction, and decision making. In the powertrain domain, it improves power regulation, energy management, and thermal management. In the chassis domain, it enables precise steering, braking, and suspension control. In the cockpit domain, it supports occupant monitoring, comfort regulation, and human–machine interaction. The review then synthesizes research on cross-domain fusion. It identifies transfer learning as a crucial method to address scarce training data and poor generalization. These limits still hinder large-scale deployment of deep reinforcement learning in intelligent electric vehicle domain control. The review closes with future directions: rigorous safety assurance, real-time implementation, and scalable on-board learning. It offers a roadmap for the continued evolution of deep-reinforcement-learning-based vehicle domain control technology.