The Research On Permanent Magnet Synchronous Motor Based On Recurrent Fuzzy Neural Network Control

Permanent magnet synchronous motor has been widely used in many fields due to its simple structure,small size,light weight and high power factor.However,the permanent magnet synchronous motor is a controlled system with strong coupling and nonlinearity.The motor's own parameters such as rotor resistance and moment of inertia will change with the environment,which will affect the overall performance of the motor system.The traditional PID control is a kind of linear control,now PI control is adopted mostly,but this kind of control is difficult to achieve satisfactory result when controlling the nonlinear permanent magnet synchronous motor.In order to enhance the robustness of the system and improve the limitation of the conventional PI-controlled permanent magnet synchronous motor system,this thesis adopts the control method combining fuzzy control and neural network control to give full play to the advantages of the two control methods,in order to improve the anti-disturbance and robustness of the system.Firstly,this thesis reviews the intelligent control strategy of permanent magnet synchronous motor and its development status at domestic and foreign.On the basis of introducing the structure and working principle of permanent magnet synchronous motor,the mathematical model is established,and the working principle of vector control system of permanent magnet synchronous motor and the space voltage vector pulse width modulation technology used in vector control are introduced.Secondly,the traditional PI control can not meet the high control performance requirements of the motor system when controlling the permanent magnet synchronous motor system,and the traditional fuzzy control has poor learning ability and relies on experts' experience too much.Therefore,the neural network control is introduced,and the fuzzy rules are learned by neural network.The fuzzy neural network PI controller is designed as the speed regulator of the permanent magnet synchronous motor system.The fuzzy neural network PI controller model is built by using MATLAB/Simulink,and the fuzzy neural network PI controller is compared with the traditional fuzzy PI controller.Finally,in order to further improve the robustness of the system,based on the comprehensive analysis of the intelligent control method of permanent magnet synchronousmotor,a recurrent fuzzy neural network controller is designed by using the control method combining fuzzy control and recurrent neural network control,and the dynamic performance of the system is improved by the self-feedback characteristics of the recurrent neural network.In order to further improve the precision and stability of the control system,the backstepping control is introduced to recurrent fuzzy neural network,and a backstepping recurrent fuzzy neural network controller is designed.The two controllers designed are verified by MATLAB/Simulink.