Hybrid heavy-duty trucks have attracted wide attention due to their excellent fuel economy and high mileage. For power-split hybrid heavy-duty trucks, the optimization of powertrain parameters is closely related to the control strategies of hybrid vehicles. In particular, the parameters of the powertrain system will directly affect the control of the vehicles’ power performance and economy. However, currently, research on hybrid heavy-duty trucks employing power-split configurations is lacking. Furthermore, few studies consider both the optimization of powertrain parameters and the control strategy at the same time to carry out comprehensive optimization research. In order to address these issues, this paper focuses on the fuel economy of hybrid heavy-duty trucks with power-split configurations. Improved particle swarm optimization (IPSO) and dynamic programming (DP) algorithms are introduced to optimize powertrain parameters. With these methods being applied, hybrid heavy-duty trucks show a 2.15% improvement in fuel consumption compared to that of the previous optimization. Moreover, based on the optimal powertrain parameters, a DP-based rule-control strategy (DP-RCS) and optimal DP-RCS scheme are presented and used in this paper to conduct our research. Simulation results show that the optimal DP-RCS reduces fuel consumption per hundred kilometers by 11.35% compared to the rule-based control strategy (RCS), demonstrating that the combination of powertrain parameter optimization and DP-RCS effectively improves the fuel economy of hybrid heavy-duty trucks.

With the rapid development of machine learning, deep reinforcement learning (DRL) algorithms have recently been widely used for energy management in hybrid electric urban buses (HEUBs). However, the current DRL-based strategies suffer from insufficient constraint capability, slow learning speed, and unstable convergence. In this study, a state-of-the-art continuous control DRL algorithm, softmax deep double deterministic policy gradients (SD3), is used to develop the energy management system of a power-split HEUB. In particular, an action masking (AM) technique that does not alter the SD3′s underlying principles is proposed to prevent the SD3-based strategy from outputting invalid actions that violate the system’s physical constraints. Additionally, the transfer learning (TL) method of the SD3-based strategy is explored to avoid repetitive training of neural networks in different driving cycles. The results demonstrate that the learning performance and learning stability of SD3 are unaffected by AM and that SD3 with AM achieves control performance that is highly comparable to dynamic planning for both the CHTC-B and WVUCITY driving cycles. Aside from that, TL contributes to the rapid development of SD3. TL can speed up SD3’s convergence by at least 67.61% without significantly affecting fuel economy.

The hybrid electric dump truck is equipped with multiple power sources, and each powertrain component is controlled by an energy management strategy (EMS) to split the demanded power. This study proposes an EMS based on deep reinforcement learning (DRL) algorithm to extend the battery life and reduced total usage cost for the vehicle, namely the twin delayed deep deterministic policy gradient (TD3) based EMS. Firstly, the vehicle model is constructed and the optimization objective function, including battery aging cost and fuel consumption cost, is designed. Secondly, the TD3-based EMS is used for continuous action control of ICE power based on vehicle state, and the action mask is applied to filter out invalid actions. Thirdly, the simulations of the EMSs are trained under the CHTC-D driving cycle and C-WTVC driving cycle. The results show that the action mask improves the convergence efficiency of the strategies, and the proposed TD3-based EMS outperforms the deep deterministic policy gradient (DDPG) based EMS. Meanwhile, the battery life is extended by 36.17% under CHTC-D and 35.49% under C-WTVC, and the total usage cost is reduced by 4.30% and 2.49% when the EMS considers battery aging. In summary, the proposed TD3-based EMS can extend the battery life and reduce usage cost, and provides a method to solve the optimization problem for the EMS of hybrid power systems.

To address the prominent fatigue failure risk of planetary gears in power-split hybrid buses and the lack of quantitative damage analysis across various operating modes in existing studies, this paper focuses on the front planetary gear set of a power-split hybrid bus. Based on a full-vehicle co-simulation model, loads under full operating conditions are decomposed into 11 operating modes, mode-switching loads are analyzed and extracted, and mode-decomposed and mode-switching fatigue loading spectra are compiled. Fatigue simulation is then conducted using Miner’s linear damage accumulation rule. Results show that the sun gear directly coupled to motor is the system’s most fatigue-susceptible component, exhibiting significant asymmetric unilateral tooth flank damage. The hybrid electric vehicle (HEV) mode contributes approximately 88% of total damage to the sun gear’s right flank, dominating system fatigue damage. Transient mode-switching conditions account for approximately 60% of total damage to the sun gear’s left flank, serving as the core damage source. Compared with the traditional full-condition merging method, the proposed mode-decomposed method improves the conservatism of life prediction. This work provides methodological support for refined strength design and targeted optimization of power-split hybrid transmission systems.