Search

For hydrogen fuel cell vehicles, energy management strategies (EMS) are vital for balancing fuel cell and battery power, limiting fuel cell power, maintaining state of charge (SOC) fluctuation range and mitigating degradation. Reinforcement learning-based EMS, especially using deep Q-network (DQN) and deep deterministic policy gradient (DDPG), have demonstrated potential for enhancing the fuel economy of hybrid electric vehicles (HEV) and fuel cell electric vehicles (FCEV). This research proposes mutation protection DQN (MPD)-based EMS to improve hydrogen fuel economy and reduce fuel cell degradation under driving cycles with plenty of mutations. By quantifying mutation, exploring its relationship with driving conditions and integrating a mutation protection module with DQN, MPD-based EMS achieves approximately 11% and 6% better fuel economy compared to the other two learning-based EMS. Additionally, it also reduces fuel cell degradation by approximately 21% and 13%. • Quantifying the mutation of driving conditions through variance. • Utilizing information entropy to process mutations. • Introducing a dynamic mutation threshold value. • Designing mutation protection module and integrating it into the DQN. [ABSTRACT FROM AUTHOR]

Energy management is a fundamental task of a hybrid electric vehicle. However, dealing with multiple hybrid electric vehicles would be very time consuming, and developing a separate management strategy for each model is a huge workload to. Based on the above problems, this paper investigates the generalization capability of energy management strategies for hybrid electric vehicles. To improve the generalization of energy management strategies, a multi-agent reinforcement learning algorithm is proposed. To achieve this goal, the first analysis from the state values of reinforcement learning in the state selection, if all the typical features of the vehicle operation are added to the reinforcement learning algorithm, then it will make the model have a certain generalization ability. Then, with the help of the auxiliary agent, the reward value of reinforcement learning can be improved by using KL-divergence. The training and validation results show that the strategy can also achieve the training effect when tested on new models. In addition, a new driving cycle is selected for environmental testing, and the results show that the method also has strong generalization ability. • Diverse vehicle states are transferred into high-dimensional features. • Two DQN network are trained together with correlation function. • An Auxiliary agent is applied to guide the direction of agent training. • The proposed deep reinforcement learning framework realizes better performance and generalization. [ABSTRACT FROM AUTHOR]

To optimize the hydrogen consumption, lifespan of the fuel cell (FC), and durability of the lithium-ion battery in fuel cell electric vehicles (FCEVs), energy management strategies (EMSs) have been developed and implemented in the vehicle control units (VCUs) by engineers. Recently, with the rapid development of artificial intelligence, reinforcement learning (RL)-based EMS have shown great promise among various strategies. However, RL-based EMS tends to exhibit relatively poorer performance when faced with novel environments owing to the requirement for learning. This study proposes an enhanced EMS, Scalable Learning in Novel Environment (SLNE)-based EMS. This EMS performs well in unknown and dynamic environments by integrating a memory library (ML) composed of the Dirichlet process (DRP) clustering algorithm combined with the Chinese restaurant process (CRP) using the expectation-maximization (EM) algorithm for updates and the deep Q-network (DQN). Simulation and comparison are conducted under two novel driving cycles to evaluate the performance of the dynamic programming (DP)-based EMS, rule-based EMS, DQN-based EMS, and SLNE-based EMS. By comparing reward, power, and degradation, the results indicate that the proposed SLNE-based EMS demonstrates excellent convergence and adaptability when facing a novel and dynamic environment. Additionally, the proposed SLNE-based EMS achieves approximately 5% improvement in fuel economy, approximately 4.5% reduction in fuel cell degradation rate, and improved durability of the lithium-ion battery, compared with DQN-based EMS. [Display omitted] • The scalable learning in novel environment-based EMS is proposed for an FCEV. • The SLNE-based EMS performs well from the start when facing novel driving cycles. • The SLNE-based EMS demonstrates a higher reward ceiling and lower fluctuations. • Considering the fuel cell degradation, proposed EMS can better enhance the lifespan. • The fuel consumption of the SLNE-based EMS is 5% lower than that of the DQN-based EMS. [ABSTRACT FROM AUTHOR]

As the core technology of hybrid electric vehicles (HEVs), energy management strategy directly affects the fuel consumption of vehicles. This research proposes a novel reinforcement learning (RL)-based algorithm for energy management strategy of HEVs. Hierarchical structure is used in deep Q-learning algorithm (DQL-H) to get the optimal solution of energy management. Through this new RL method, we not only solve the problem of sparse reward in training process, but also achieve the optimal power distribution. In addition, as a kind of hierarchical algorithm, DQL-H can change the way of exploration of the vehicle environment and make it more effective. The experimental results show that the proposed DQL-H method realizes better training efficiency and lower fuel consumption, compared to other RL-based ones. • DQL-H trains each level independently and is more efficient than counterparts. • Sparse rewards can be overcome during the training process. • Substantial rewards can accelerate the speed of convergence. • DQL-H changes the way of exploring the vehicle environment. [ABSTRACT FROM AUTHOR]