Due to the ignorance of dynamic characteristics of powertrains, existing frameworks for co-optimizing component sizing and energy management of hybrid powertrains may lead to unsatisfactory performance. To design an alternative framework and provide a promising solution, this paper proposes a novel co-optimization methodology that incorporates the high-fidelity model (HFM) of plug-in hybrid electric vehicles (PHEVs). The present methodology employs the maps of engines and electric motors during the optimization process. In addition, based on the Pareto optimization method, an adaptive non-dominated sorting genetic algorithm-III (NSGA-III) with chaos sequence (NSGA-CS) is proposed. By setting an objective function that concerns the fuel consumption, battery state of health (SOH), and manufacturing cost, the co-optimization effect of NSGA-CS with HFM (NSGA-CS & HFM) is compared with that of NSGA-III with Willans model (NSGA-CS & WM) using the real-time control strategy. Under the NEDC-WLTC driving cycle, compared with the original vehicle, the NSGA-CS & HFM approach can reduce fuel consumption, battery SOH loss, and system costs by 7.4%, 8.0%, and 6.3%, respectively. The effectiveness of the optimized parameters is verified in the hardware-in-loop (HIL) experiment. These results suggest that the novel co-optimization methodology proposed in this paper is effective in optimizing the powertrain parameters and control strategies and can further promote the energy-saving potential of HEV/PHEVs.

The climate-adaptive energy management system holds promising potential for harnessing the concealed energy-saving capabilities of connected plug-in hybrid electric vehicles. This research focuses on exploring the synergistic effects of artificial intelligence control and traffic preview to enhance the performance of the energy management system (EMS). A high-fidelity model of a multi-mode connected PHEV is calibrated using experimental data as a foundation. Subsequently, a model-free multistate deep reinforcement learning (DRL) algorithm is proposed to develop the integrated thermal and energy management (ITEM) system, incorporating features of engine smart warm-up and engine-assisted heating for cold climate conditions. The optimality and adaptability of the proposed system is evaluated through both offline tests and online hardware-in-the-loop tests, encompassing a homologation driving cycle and a real-world driving cycle in China with real-time traffic data. The results demonstrate that ITEM achieves a close to dynamic programming fuel economy performance with a margin of 93.7%, while reducing fuel consumption ranging from 2.2% to 9.6% as ambient temperature decreases from 15°C to -15°C in comparison to state-of-the-art DRL-based EMS solutions.

Combining the physical significance of theoretical models with the high fitting accuracy of data-driven models is crucial for precise characterization of fuel cell electric truck (FCET) energy consumption. This paper proposes a theory-constrained neural network (TCNN), integrating physical significance without compromising accuracy. A theory-guided filter is applied to ensure the interpretability of each sub-module. Fuel cell temperature and voltage are modeled separately, each serving as an important input for the other. Sub-networks are trained individually under the constraints of the theory-guided filter to minimize the error between the final output and the data. Additionally, a neural network based on the CNN-BiLSTM-MHSA architecture ensures model accuracy. Results show that the proposed neural network significantly improves fitting accuracy for both fuel cell temperature and voltage. The proposed TCNN successfully integrates the theoretical model, improving accuracy by 33.7% compared to the theoretical model and maintaining accuracy comparable to the purely data-driven model. Hydrogen consumption calculated based on this model shows accuracy improvements of 63.7% and 49.4% compared to traditional methods using efficiency curves and hydrogen consumption curves, respectively. The proposed voltage model and temperature model using TCNN enable accurate hydrogen consumption calculations, which can be broadly applied to energy management, component sizing, and other related areas.

Automotive energy management systems (EMSs) are evolving to achieve intelligence across their entire lifecycle, from initial product development to real-world customer usage. This paper proposes a bi-level transfer approach with model-agnostic meta-learning (MAML) to realize cross-platform transferable and online-adaptive EMS. In the development phase, MAML calibrates the heuristic control maps of an instantaneous optimization-based EMS, with a per-unit state-action space design ensuring seamless knowledge transfer between vehicle platforms. During the usage phase, real driving data are adopted to refine onboard control parameters. The framework is validated through real vehicle experiments. Firstly, the entire MAML-assisted V-cycle development is implemented to validate the optimality and knowledge transfer of the EMS, resulting in zero-shot transfer for EMS calibration on new vehicle products. Additionally, real vehicle experimental tests show that a correction of 8.0%~9.5% fuel economy is improved against the convention reinforcement learning-based EMS during usage via online-adaptation, effectively bridging the gap between pre-trained policies and real-world optimal energy management.

The synergy of reinforcement learning (RL)-based energy management and vehicle-to-everything communication has been proved effective in boosting the fuel economy of connected plug-in hybrid electric vehicles (PHEVs). However, the intricate coupling of mechanical, electrical, thermal states and driving cycle results in a high-dimensional complex energy control problem for PHEVs, which is challenging to optimally solve within the same time scale. To this end, this study designs a multi-horizon reinforcement learning (MHRL)-based energy management of PHEVs, aware of the traffic preview from intelligent transportation systems to optimize the energy flow and thermal states as well as the transient dynamics of the powertrain. The proposed strategy features a novel state space representation, and solves the coordinated training among multiple sub-networks belonging to different control tasks in various time scales. Simulation and hardware-in-the-loop experiments are carried out based on a standard driving cycle and a real-world driving cycle with real-time traffic data demonstrate that the MHRL strategy improves fuel economy by 3.0%~7.9% compared to conventional RL-based energy management under various coolant temperature conditions and dynamic driving scenarios.