Parameter Matching And System Modeling Of AMT Plug-in Electric Vehicle

In the nearly 100 years,human is the main means of transport by common carriage change to high-speed car.But attendant environmental pollution,energy crisis has affected the human development,people began to want the car not only powerful but also save energy and reduce emission.In order to achieve this requirement,the new energy vehicles began to appear on the stage of history.The new energy vehicles are varied,but due to the restriction of various technical factors are often used for new energy vehicles for hybrid electric vehicle,and the city’s new energy bus is widely used in parallel hybrid electric vehicle.The characteristics of the parallel hybrid electric vehicle transmission parts and the parameters matching pair of vehicle fuel economy have an important influence.At home and abroad has been a lot of research on hybrid electric vehicle;parameter matching,these studies emphasis on research and analysis of the theory of.Therefore,this paper on its research foundation,by comparing the actual sample data,validate the parameters matching optimization algorithm has practical reference value.The parallel plug-in hybrid electric vehicle as the research object,mainly the following two aspects: 1 according to the principle of vehicle dynamics and control strategy,the initial completion of the parallel plug-in hybrid system parameter matching;using Simscape to establish the physical model,and with the help of a semi physical simulation model to verify the correctness of.2.the parameter matching optimization using genetic algorithm BP neural network,using BP neural network training object,training of various experimental data,the results will be trained as the fitness of genetic algorithm,genetic algorithm through selection,crossover and mutation operation to complete the optimization objective,implementation,optimization of the parameters,the optimized results are verified by simulation model,and comparing the simulation results with actual sample data,results show that the 100 km fuel consumption decreased by 3L/100 KM.proved that the combination algorithm of optimization The results have practical reference value.