Research On Energy Management Strategy Of Fuzzy Control Of Parallel HEV With Recognizable Working Conditions

With the increasingly severe energy crisis and environmental protection situation,it is an urgent task to find new energy vehicles with renewable energy.Various energy sources of hybrid electric vehicles have different characteristics,so energy management has become the core issue of hybrid electric vehicles.Hybrid Electric Vehicle(HEV)integrates electrical and mechanical systems,including chemical changes and thermodynamic processes.It is difficult to accurately describe HEV using mathematical models.Aiming at the problems of parallel hybrid electric vehicle energy management strategy,this paper makes a thorough study on this problem by combining fuzzy control algorithm,particle swarm optimization algorithm,simulated annealing algorithm and neural network algorithm,and carries out relevant simulation experiments.The main work is as follows:Firstly,the simulation model of parallel hybrid electric vehicle is built,the modeling methods of engine,motor and battery are analyzed,and the energy management strategy based on fuzzy control is realized.Secondly,the hybrid algorithm of PSO and SA is used to optimize the fuzzy rules.The hybrid algorithm not only has the characteristics of fast convergence of PSO,but also can search the global optimal value as SA.For the PSO algorithm,chaos strategy is used to give PSO particles a random disturbance,which can increase the diversity of the population and improve the search ability.A condition recognizer is designed by using RBF neural network.The recognizer can monitor the working condition online and identify the type of working condition,and select the appropriate optimized fuzzy rules to assign to the fuzzy controller to use,so as to improve the fuel economy according to the actual working condition.Finally,a parallel hybrid electric vehicle model is built in Advisor,and the optimized fuzzy control energy management strategy is used to test under random conditions.The simulation results show that the energy management strategy improves fuel economy compared with the energy management strategy before optimization.