An Online Predictive Energy Management Strategy for Multi-Mode Plug-in Hybrid Electric Vehicle With Mode Transition Schedule Optimization
Feng Wang, Jiaqi Xia, Xiaoyuan Zhu, Xing Xu, Yi‐Qing Ni
Abstract
Multimode configurations are extensively adopted to improve the energy efficiency of plug-in hybrid electric vehicles, which can significantly improve vehicle fuel economy by using operation mode switching. However, frequent mode transitions may deteriorate the vehicle drivability and driving comforts. Thus, this article presents a real-time predictive energy management strategy (EMS) with mode transition frequency constraints. First, two penalty functions are adopted to achieve a better balance between the fuel economy and frequency number of mode transition. Then, with the predicted vehicle speed from long-short term memory neural network and the penalty coefficients obtained from driving pattern recognition, a rapid near-optimal energy management algorithm is developed to achieve torque allocation optimization, which can ensure low mode transition frequency and high calculation efficiency for online application. Finally, the effectiveness as well as performance of proposed EMS is verified by using comparative hardware-in-the-loop tests.