Simulation Of Switched Reluctance Motor Modeling And Control With Neural Network

The switched reluctance motor (SRM) possesses many specific advantages such as simple structure, high efficiency, good reliability, and low cost. The switched reluctance motor drive (SRD), which is constructed by the SRM, has attracted extensive attention in the world due to its wide range and superior performances of speed tuning. The Switched Reluctance Motor (SRM) has strong nonlinear feature due to its structure and operation mode, and the performances and control methods of this new kind of motors are significantly different from those traditional ones. As a result, the accurate modeling and high performance control of the SRM proves to be very important and has gained widely research.Firstly, this paper establishes the dynamic simulation models of the 4-phase (8/6 poles) SRM and its drive system based on MATLAT/Simulink, and then the research on voltage PWM speed control strategies is processed on it. The position feedback signals are obtained via the Hall means. Then the input and output relationship of the SRM is researched by the fuzzy neural network method. The nonlinear model of SRM is obtained. It has low error and can be performed easily. With the BP neural network and the traditional PID controller combined, a new control method based on adaptive BP neural network PID controller and on-line identification is presented. This method uses BP neural network, which has powerful nonlinear mapping and self-adaptation capabilities, to observe the output of the system real time, and adjust the parameters of PID controller on line. Simulation results show that the proposed control approach can successfully maintain system stability with good dynamic response and adaptability.