The Energy Management Research On Hybrid Electric Vehicle (HEV) Based On Fuzzy Neural Network

The research and development on Hybrid Electric Vehicle (HEV) is an important method to resolve the pollute of environment and the energy crisis. But at the present time, the research on HEV in our country is in the very beginning o The National Department of Science and Technology makes HEV a significant project of 863 Plan and this project is from the 863 Plan .Energy management of HEV is the key problem of the research and development on HEV because of its non-linear, random and ambiguous features. Combining Fuzzy inference with Neural Network, the fuzzy neural network technology has great superiority in processing non-linear, random and ambiguous problems. So we can use fuzzy neural network in the energy management of HEV. So the thesis makes a primitive study in this field.According to the real situation of Energy management of HEV, we construct a four-leveled new fuzzy neural network. It fuzzy node adopts Gauss Model Subjection Function, whose center-value and width-value exerts great influence on the network's operation transmission and performance, and needs modification by studying. Then the BP Algorithm is inferred in detail and adding momentum item is used to avoid local least and speed up the convergence of Average Error Function. To guarantee the physical meaning of the area-value and improve the significance among rules, we choose part-layer algorithm to modify the area-value between the third level and the forth one. Thus the BP algorithm only study the center-value, width-value and Wj values. The improved parameters are saved in the data file for the management system use.By taking the operation realized by the successful fuzzy neuralnetwork as its core, study the problem of energy management of HEV simulation. Successfully simulate and achieve the working procession of the energy management of HEV:A, when system get the values of the accelerator pedal angle and brake pedal angle, calculating the angle of motor and the angle of engine through the network; B, send the angles to motor and engine, then motor and engine work with the new angles.Develop software to simulate the energy management of HEV by using C. In a word, the thesis makes a primitive study of the fuzzy neural network approach on the energy management of HEV and proves its validity.