Fuel-Efficient Control via Accelerator Mitigation in Series HEVs Using Nonlinear MPC

The energy management of hybrid electric vehicles (HEVs) is significantly influenced by driver behavior, often leading to reduced fuel efficiency. This study proposes a model predictive control (MPC)-based system to improve fuel efficiency by modifying the driver’s accelerator input. A neural network state-space model is employed to capture the complex dynamics of HEVs. Simulations using an HEV simulator validate the effectiveness of the proposed method in enhancing fuel efficiency. These results demonstrate the potential of combining MPC with neural network modeling to overcome the challenges posed by driver behavior in HEV energy management.