A Novel Learning-Based Model Predictive Control Strategy for Plug-In Hybrid Electric Vehicle

The multisource electromechanical coupling renders the energy management of plug-in hybrid electric vehicles (PHEVs) highly nonlinear and complex. Furthermore, complicated process depends on knowledge driving conditions hinders control strategies efficiently applied instantaneously, leading to massive challenges in energy-saving improvement PHEVs. To address these issues, a novel learning-based model predictive (LMPC) strategy is developed for serial–parallel PHEV with reinforced optimal effect real-time applications. Rather than employing velocity-prediction-based MPC methods favored literature, an original reference-tracking-based solution proposed strong instant application capacity. guarantee effect, online learning implemented via Gaussian (GP) uncertainties during state estimation. tracking reference LMPC-based problem achieved by microscopic traffic flow analysis (MTFA) method. simulation results validate that method can optimally manage within vehicle power sources real time, highlighting its anticipated preferable performance.