Search

• TIP-EMS enhances EV energy efficiency by integrated prediction and energy management. • Significant driving economy boost; 1.6%-4.2% better than state-of-the-art PEMS. • TIP-EMS shows robust performance with varying prediction weight adjustments. To enhance the energy efficiency of electrified vehicles (EVs), developing effective energy management strategies (EMS) for hybrid storage systems is essential. Predictive EMS (PEMS) that foresee future vehicle speeds have demonstrated substantial potential in boosting EMS performance. However, traditional PEMS models, employing a sequential approach of speed prediction followed by energy allocation, are hampered by cumulative errors. These errors from the initial speed predss this issue, this paper introduces a novel solution: the trainable integrated preiction negatively impact the efficiency of subsequent energy management. To addrediction and energy management strategy (TIP-EMS). Contrasting with conventional sequential PEMS, TIP-EMS features a dual-branch, integrated neural network, which is fully trainable. This network processes driving status inputs via attention layers, with one branch dedicated to energy management objectives using a reinforcement learning (RL) algorithm, and the other to vehicle speed prediction. Both branches are trained simultaneously, but post-training, only the RL branch is activated for energy management. Implemented with a soft actor-critic RL algorithm, TIP-EMS is applied to a fuel cell EV for optimized energy management. The validation involved training TIP-EMS using 27 driving profiles, which developed its prediction and energy management capabilities, followed by tests in untrained scenarios. The results show that TIP-EMS surpasses conventional sequential PEMS by up to 4.2% in scenarios where prediction accuracies are comparable, highlighting the efficacy of the trainable integrated mechanism. In addition, TIP-EMS exhibits superior energy conservation compared to non-predictive RL strategies. Lastly, TIP-EMS exhibits robustness to adjustments in the weight given to the prediction objective, further confirming its practical applicability. [ABSTRACT FROM AUTHOR]

• A hierarchical convex optimization framework for HEV-PCC is proposed. • A TSI-MPC approach is designed to address the speed planning problem. • An energy management strategy that combines regression model with PMP is designed. Predictive Cruise Control (PCC) achieves automated driving with improved vehicle economy by incorporating road gradient information from high-precision maps. However, existing research on PCC has primarily centered around conventional gasoline vehicles. Hybrid Electric Vehicle (HEV) offer superior fuel efficiency compared to their traditional counterparts. To further enhance vehicle economy by integrating the PCC system with HEVs, this paper proposes a hierarchical control architecture for HEV-PCC based on convex optimization. Firstly, considering spatial slope information from the road ahead, this paper introduces a Time-Space Integration Model Predictive Control (TSI-MPC) based on the principles of kinetic energy. Secondly, the paper combines a current regression model with the Pontryagin Minimum Principle (PMP) to present a Regression Analysis - Pontryagin Minimum Principle (RA-PMP) approach for the direct analytical solution of the energy management problem. Finally, the strategy is validated through simulation analysis and Hardware-in-Loop (HIL) testing on various real road scenarios. The result indicate that, in comparison to the Equivalent Consumption Minimization Strategy (ECMS) with constant speed cruising (CC), this method achieves an average fuel economy improvement of 9.45%. [ABSTRACT FROM AUTHOR]

• Deep stochastic reinforcement learning based approach to address this issue of epistemic uncertainty in a midsize fuel cell hybrid electric vehicle. • The performance of the proposed approach is benchmarked against Double Deep Q-Network (DDQN), Power Follower Controller (PFC) and Fuzzy Logic Controller (FLC). • Using New York City cycle as a validation drive cycle, the approach improves fuel economy by 7.68%, 13.53%, and 10% compared to DDQN, PFC, and FLC, respectively. • The deep REINFORCE approach improves fuel economy by 5.31 %,9.78 %, and 9.93 % compared to DDQN, PFC, and FLC, respectively under another validation cycle, Amman cycle. • The proposed method has 38% less training time when compared to the DDQN approach. Fuel cell hybrid electric vehicles offer a promising solution for sustainable and environment friendly transportation, but they necessitate efficient energy management strategies (EMSs) to optimize their fuel economy. However, designing an optimal leaning-based EMS becomes challenging in the presence of limited training data. This paper presents a deep stochastic reinforcement learning based approach to address this issue of epistemic uncertainty in a midsize fuel cell hybrid electric vehicle. The approach introduces a deep REINFORCE framework with a deep neural network baseline and entropy regularization to develop a stochastic policy for EMS. The performance of the proposed approach is benchmarked against three EMSs: i) a state-of- art deep deterministic reinforcement learning technique called Double Deep Q-Network (DDQN), Power Follower Controller (PFC) and Fuzzy Logic Controller (FLC). Using New York City cycle as a validation drive cycle, the deep REINFORCE approach improves fuel economy by 7.68%, 13.53%, and 10% compared to DDQN, PFC, and FLC, respectively. The deep REINFORCE approach improves fuel economy by 5.31 %,9.78 %, and 9.93 % compared to DDQN, PFC, and FLC, respectively under another validation cycle, Amman cycle. Moreover, the training results show that the proposed algorithm reduces training time by 38% compared to the DDQN approach. The proposed deep REINFORCE-based EMS shows superiority not only in terms of fuel economy, but also in terms of dealing with epistemic uncertainty. [ABSTRACT FROM AUTHOR]

[Display omitted] • Explores RL-based EMS development in multi-power source vehicles. • Highlights general RL advantages over specific hybrid designs in EMS. • Discusses RL-EMS performance factors using PHEV and FCEV models. Reinforcement learning-based (RL-based) energy management strategy (EMS) is considered a promising solution for the energy management of electric vehicles with multiple power sources. Research and applications of reinforcement learning and deep reinforcement learning in energy management issues are emerging. However, previous studies have not systematically examined the essential elements of RL-based EMS. This paper presents a performance analysis of RL-based EMS in a Plug-in Hybrid Electric Vehicle (PHEV) and Fuel Cell Electric Vehicle (FCEV). The performance analysis is developed in four aspects: algorithm, perception and decision granularity, hyperparameters, and reward function. The results show that the Off-policy algorithm effectively develops a more fuel-efficient solution within the complete driving cycle compared with other algorithms. Improving the perception and decision granularity reduces the frequency of tabular-based policy updates but better balances battery power and fuel consumption. Setting a high initial SOC in training will effectively improve the performance of RL-based EMS. The construction of an equivalent energy loss reward function for RL-based EMS based on instantaneous State of Charge (SOC) variation should be approached with caution. This approach is highly sensitive to parameters and is more likely to lead to violations of SOC constraints. In contrast, an equivalent energy reward function based on overall SOC variation is a safer alternative. [ABSTRACT FROM AUTHOR]

• A hierarchical predictive energy management is designed for fuel cell trucks under vehicle-following scenarios. • The speed planning considering future changes of leading vehicle is designed to ensure safe inter-vehicle distance and minimize power demand. • A driving-habit-conscious fuzzy C-means clustering enhanced Markov Chain speed prediction method is proposed to forecast future speed of leading vehicle. • The proposed hierarchical predictive energy management for host vehicle can reduce fuel cell degradation cost by 1.31–3.48% and total operation cost by 0.75–1.94%. Fuel cell hybrid electric heavy-duty vehicles play a key role to realize green and low-carbon travel. To cope with actual traffic environment, an advanced energy management strategy (EMS) is crucial to ensure vehicle's efficiency and economy. In this paper, a predictive co-optimization control method is designed to achieve speed planning and energy management for the host vehicle with a fuel cell/Li-ion battery hybrid energy storage system under vehicle-following scenarios. Firstly, the host vehicle obtains the real-time speed of leading vehicle by communication technology, and speed prediction for the leading vehicle is implemented by fuzzy C-means clustering enhanced Markov Chain (FCM-MC) considering driving habits. Secondly, based on speed prediction results, the speed planning which aims to ensure safe inter-vehicle distance and minimize the demanded vehicular power is implemented to derive the speed curve of host vehicle. Finally, according to speed planning results, predictive energy management is applied to achieve power allocation between fuel cell (FC) and battery. The simulation results denote that the proposed speed prediction method can decrease forecast error effectively. The speed planning ensures the safe inter-vehicle distance. With speed prediction accuracy improved, the proposed hierarchical energy management strategy can reduce fuel cell degradation cost by 1.31%-3.48% and total operation cost by 0.75%-1.94%. [ABSTRACT FROM AUTHOR]

[Display omitted] • Novel predictive ECMS algorithm for hybrid trucks based on projected power demand. • Algorithm operation validated on commercial plug-in hybrid electric truck. • Up to 5.9% energy efficiency gains over a municipal operation profile. • Power-predictive ECMS for energy management brings real CO 2 benefits. This paper examines potential fuel consumption savings through the implementation of a predictive equivalent consumption minimisation strategy, as a control algorithm in the energy management system of hybrid heavy-duty vehicles. A plug-in hybrid electric truck simulation model was developed as a demonstrator and was validated with experimental data. The baseline vehicle model was based on the same algorithm as VECTO, which is further extended in the current study by novel factors that contain the average predicted power demand. The potential benefits of the proposed algorithm are examined for different heavy-duty categories over regulatory mission profiles in both charge-sustain and charge-depletion modes. The results show that the fuel consumption can be reduced by up to 5.9 % and 4.4% in charge sustaining and charge depleting modes, respectively, depending on the mission profile. If such an algorithm is adopted by commercial vehicles, this could lead to substantial CO 2 and fuel consumption savings on the road. [ABSTRACT FROM AUTHOR]