Plug-in hybrid electric vehicles (PHEVs) show great promise in reducing transportation-related fossil fuel consumption and greenhouse gas emissions. A critical research topic for PHEVs is designing an efficient energy management system (EMS), in particular, determining how the energy flows in a hybrid powertrain should be managed in response to a variety of system parameters. Most of the existing systems either rely on a priori knowledge of future driving conditions to achieve the optimal but not real-time solution (e.g. Dynamic Programming strategy), or only upon the current driving situation to achieve a real-time but not optimal solution (e.g. rule-based strategy). Towards this end, we propose a Q-Learning based blended real-time EMS for PHEVs to address the trade-off between real-time performance and optimality. The proposed EMS can optimize the fuel consumption while learning the system's characteristics in real time. Numerical analysis shows that the proposed EMS can achieve a near optimal solution with 11.93% fuel savings compared to a binary mode control strategy, but a 2.86% fuel consumption increase compared to an off-line Dynamic Programming strategy.
展开▼
