The development of energy management strategy (EMS), which considers how power is distributed between the battery and ultracapacitor, can reduce the electric vehicle’s power consumption and slow down battery degradation. Therefore, the purpose of this paper is to develop an EMS for hybrid energy storage electric vehicles based on Pontryagin’s minimums principle (PMP) considering battery degradation. To verify the EMS, the hybrid energy storage electric vehicle model is first established. In the meantime, the battery cycle life trials are finished in order to develop a battery degradation model. Following that, a rule-based control approach and the PMP optimization algorithm are used to allocate power in a hybrid energy storage system (HESS) in a reasonable manner. Finally, a simulation experiment under urban dynamometer driving schedule (UDDS) settings verifies the established EMS, and the findings reveal that the suggested EMS has a lower energy consumption rate and battery deterioration rate than the rule-based method.

Deep reinforcement learning has been widely applied in energy management strategies (EMS) for fuel cell vehicles because of its excellent performance in the face of complex environments. However, when driving conditions change, deep reinforcement learning-based EMS needs to be retrained to adapt to the new data distribution, which is a time-consuming process. To address this limitation and enhance the generalization ability of EMS, this paper proposes a deep transfer reinforcement learning framework. First, we designed a DDPG algorithm combined with prioritized experience replay (PER) as the research algorithm and trained a PER–DDPG-based EMS (defined as the source domain) using multiple driving cycles. Then, transfer learning was used when training the EMS (defined as the target domain) using a new driving cycle, i.e., the neural network parameters in the source domain model were reused to help initialize the target domain model. The simulation results show that the energy management strategy combined with transfer learning not only converges faster (improved by 59.09%), but also shows stronger adaptability when faced with new and more complex driving cycles, compared with not using transfer learning and having the model retrained.

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.

The seal and weight of the Type IV hydrogen storage vessel are the key problems restricting the safety and driving range of fuel cell vehicles. The boss, as a metal medium connecting the inner liner of the Type IV hydrogen storage vessel with the external pipeline, affects the sealing performance of the Type IV hydrogen storage vessel, and there is no academic research on the weight of the boss. Therefore, according to the force characteristics of the boss, this paper divides the upper and lower areas (valve column and plate). The valve column with seal optimization and light weight is manufactured with a 3D printing additive, while the plate bearing and transferring the internal pressure load is manufactured by forging. Firstly, a two-dimensional axisymmetric simulation model of the sealing ring was established, and the effects of different compression rates on its seal performance were analyzed. Then, the size and position of the sealing groove were sampled, simulated, and optimized based on the Latin Hypercube method, and the reliability of the optimal seal structure was verified by experiments. Finally, the Solid Isotropic Material with Penalization (SIMP) topology method was used to optimize the weight of the boss with optimal sealing structure, and the reconstructed model was checked and analyzed. The results show that the weight of the optimized boss is reduced by 9.6%.

In extremely cold environments, the fuel cell vehicle (FCV) waste heat utilization subsystem can only exchange a small amount of proton exchange membrane fuel cell (PEMFC) waste heat into the warm air circuit for cab heating, which has poor adaptability to extremely cold environments. The first step in this study was to build a test bench for the waste heat utilization subsystem of fuel cell vehicles. Secondly, the PEMFC heating capacity and liquid–liquid exchanger heat transfer capacity were analyzed using experimental data to assess the ability of FCV waste heat utilization subsystems with different rated powers to adapt to extremely cold environments. Then, the optimization mathematical model of the liquid–liquid exchanger was established, and the heat transfer performance of the liquid–liquid exchanger was orthogonally optimized based on the Taguchi method. Finally, the optimized liquid–liquid exchanger was installed in the waste heat utilization subsystem for experimental tests. The results show that when the ambient temperature is −20 °C, −25 °C or −30 °C, in the optimized waste heat utilization subsystem, the inlet and outlet temperatures of the PEMFC are reduced, and the power consumption of the positive temperature coefficient (PTC) is reduced by 57.6% and 48% and 34.3%, respectively, improving the utilization rate of PEMFC waste heat, and thereby improving the adaptability of FCV in extremely cold environments.

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.