Modelling and control of bearingless switched reluctance motor based on artificial neural network

Bearingless switched reluctance motors have combined advantages of switched reluctance motors (SRM) and magnetic bearings. An accurate model of radial force and torque is the basis of precise and fast rotor position control in bearingless SRM. This paper presents a new non-linear modeling method of bearingless SRM using finite element method (FEM) and artificial neural network (ANN). The new method is superior to the previous ones because of its consideration of the non-linearity of magnetic field in bearingless SRM. Furthermore, a novel instantaneous radial force control scheme direct radial force control (DRFC), is proposed in this paper. The new model and DRFC are proved to be more effective than the original control scheme by the simulation results.