Hierarchical Control Strategy for the Hybrid Electric Propulsion System of a Flying Car with Engine Start-Stop System and Dynamic Coordination

The fact that flying cars can run on the ground and in the air presents difficulties when designing their power supply system and control system. To tackle these issues, in this paper, the dynamic characteristics of a flying car with two generation units (GUs) are studied and a hierarchical control strategy is developed to enhance its economic efficiency. First, the models of the hybrid electric propulsion system (HEPS) and vehicular dynamics are built based on mechanism and experimental data. Then, a hierarchical control strategy that includes an upper-level energy management strategy (EMS) and a lower-level coordination control is designed for this system. A Deep reinforcement learning (DRL) algorithm is applied for EMS, considering the engine start-stop system and power distribution simultaneously. A distributed model predictive control (DMPC) algorithm is built for coordinated control of each power component, taking into account the influence of other power components when tracking the control targets to improve whole system performance. The simulation results demonstrate that the proposed hierarchical method can efficiently improve fuel economy by 11.8% compared to rule-based strategies, and the computational burden of DMPC is reduced by 87.1% compared to that of centralized model predictive control through distributed computing.