HYBRID METHOD OF OBTAINING DEGREES OF FREEDOM FOR RADIAL AIRGAP LENGTH IN SRM UNDER NORMAL AND FAULTY CONDITIONS BASED ON MAGNETIOSTATIC MODEL

In this paper, a new hybrid method of obtaining the degrees of freedom for redial airgap length in Switched Reluctance Motor operation under normal and faulty conditions based on magnetostatic analysis is presented. At the beginning, this method goes through the magnetic design of the motor utilizing three dimensional (3-D) Finite Element Method (FEM) in order to consider the end effects as well as axial fringing field effects. The motor parameters, such as torque, flux linkage, flux density versus rotor position are precisely obtained. Then, a Multi Layered Perception Neural Network is designed by considering the nonlinear behavior of the motor parameters obtained under different modes of operation. Using this network and the obtained parameters from FEM, an Objective Function (OF) for torque ripple with the aim of having a minimum mean square error is estimated. In addition, an improved Genetic Algorithm (GA) for the minimization the OF is also presented to determine the motor's operational regions. Finally, the legal intervals for different modes of motor operation are addressed.