A position sensorless control system of SRM over wide speed range

This paper presents a position sensorless control system of SRM over wide speed range. The rotor position estimation of the SRM is somewhat difficult because of its highly nonlinear characteristics. In this paper, the magnetizing curve of prototype 1-hp SRM is obtained from locked rotor test and complicated data patters are trained using neural network. To estimate more accurate rotor position, current-flux-rotor position lookup table over wide operating rage is generated using trained neural network. Experimental result for a 1-hp SRM over 16:1 speed control range is presented for the verification of the proposed sensorless control algorithm.