Optimal Energy Management for a Hybrid Vehicle Using Neuro-Dynamic Programming to Consider Transient Engine Operation

This paper proposes a self-learning approach to develop optimal power management with multiple objectives, e.g. to minimize fuel consumption and transient engine-out NOx and particulate matter emission for a series hydraulic hybrid vehicle. Addressing multiple objectives is particularly relevant in the case of a diesel powered hydraulic hybrid since it has been shown that managing engine transients can significantly reduce real-world emissions. The problem is formulated as an infinite time horizon stochastic sequential decision making/markovian problem. The problem is computationally intractable by conventional Dynamic programming due to large number of states and complex modeling issues. Therefore, the paper proposes an online self-learning neural controller based on the fundamental principles of Neuro-Dynamic Programming (NDP) and reinforcement learning. The controller learns from its interactions with the environment and improves its performance over time. The controller tries to minimize multiple objectives and continues to evolve until a global solution is achieved. The control law is a stationary full state feedback based on 5 states and can be directly implemented. The controller performance is then evaluated in the Engine-in-the-Loop (EIL) facility.