Study of energy management optimization for hybrid electric scooter using dynamic programming

This paper presents parameters optimization of energy management system for hybrid electric scooters (HES) by applying dynamic programming (DP). For hybrid electric scooters, an energy management system (EMS) is required to manage the power split among engine, motor and generator, with the constraint of the sum of the total output torque of the three power sources equal to the demand torque during drive. In order to determine an optimal energy management strategy for the EMS, a dynamic programming based algorithm application for hybrid electric scooters is proposed in this paper, because it has been proven to be capable of dealing with the global optimal energy management problem for hybrid vehicles. The dynamic simulation model of hybrid electric scooter is composed by a velocity predication module which is constructed by a feedforward neural network (FNN) and parameters optimization module by dynamic programming. The dynamic programming and velocity predication is successfully applied to the parameters optimization of EMS for HES.