Research On The Energy Management Strategy Of PHEV Based On PSO And Neural Network

Compared with Hybrid Electric Vehicles (HEV), Plug-in Hybrid Electric Vehicles (PHEV) has larger battery capacity. They can store electrical energy from a domestic power supply and can drive the vehicle alone in Electric Vehicle (EV) mode. PHEVs are new generation HEV, which are developed for the lag in battery technology and shortage of research fund.By making maximum use of cheaper electrical energy from a domestic supply, they can significantly reduce the conventional fuel consumption. This may also help in improving the environment as PHEVs emit less harmful gases. As a new type of vehicle with multi-energy source, PHEVs should control the torque distribution between engine and electric motor to obtain high fuel economy. Therefore, aiming at solving problems existing in PHEV's EMS(energy management system), this dissertation explores how to optimize and improve the EMS using intelligent theories, uch as PSO(Particle Swarm Optimization)technique, neural network theory,and multi-objective optimization. The research aims at obtaining high fuel economy, low emission and good driving performance. And the main steps are as follows:First, under the environment of Matlab/Simulink, system simulation models of PHEV are built based on ADVISOR, and then a simple rule based EMS are designed to improve the fuel economy for parametric study.Second, an off-line global optimization strategy of PSO energy management under the environment of Matlab/Simulink on PSAT is developed. Here, Particle Swarm Optimization (PSO) technique is used to obtain the optimum parameter values. This EMS has provided optimum parameters which results in optimum blended mode operation of the vehicle. To reduce the on/off times of engine, improve the performance of the vehicle further more, obtain optimum charge depletion and charge sustaining mode operation of the vehicle, an advanced PSO EMS is designed which provides optimal results for the vehicle to operate in charge depletion and charge sustaining modes. This EMS shows an overall improvement on the performance of vehicle and fuel economy. As an optimized EMS in theory, it can not only guide the development of the on-line EMS, but also be taken as a criterion for developing other EMSs. Therefore, it has guiding significance for the designing of the optimized EMSs.Furthermore, to implement the developed advanced PSO EMS in real-time, a possible real time implementation technique is designed using neural networks. This neural network implementation provides similar results as compared to advanced PSO EMS results, which shows that both PSO and neural network have the value of being used on real vehicles.