Energy management strategy for parallel hybrid electric vehicles based on approximate dynamic programming and velocity forecast

In parallel hybrid electric vehicles (HEVs), the power split between the engine and the electric motor as well as the gear shift in the gearbox determines the overall energy efficiency. In this paper an adaptive energy management strategy with velocity forecast is proposed to optimize the fuel consumption in parallel HEVs, which is formulated into a mixed-integer optimization problem. Approximate dynamic programming with a novel actor-gear-critic design is presented for simultaneously controlling the power split and gear shift online. The power split as a continuous variable is determined from an actor network to realize the energy distribution between two power sources. The gear shift as a discrete variable is obtained from a gear network to adjust the gear ratio in the gearbox. The concept enables an online learning of the energy management strategy for different driving behaviors without the requirement of a system model and the driving cycle. Simulation results indicate that the proposed strategy achieves close fuel economy compared with the optimal solutions resulting from dynamic programming. Furthermore, a multi-stage neural network is introduced for velocity forecast, providing a computationally efficient training framework with good prediction performance. The velocity prediction is finally combined with the energy management strategy for an effective application and fuel economy.