Real-Time Verification of AI Based Rotor Position Estimation Techniques for a 6/4 Pole Switched Reluctance Motor Drive

Abstract

This paper presents real-time verification of an artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) based rotor position estimation techniques for a 6/4 pole switched reluctance motor (SRM) drive system. The techniques estimate rotor position by measuring the three-phase voltages and currents and using magnetic characteristics of the SRM, with the aid of an ANN and ANFIS, in real-time environments. The rotor position estimating techniques are used in a high-performance sensorless variable speed SRM drive. A digital signal processor, TMS320F2812, executes the rotor position estimation. To verify the performance of the ANN and ANFIS based rotor position estimation techniques, a rotor position sensor is mounted with the drive system. The experimental results show that the ANN and ANFIS based rotor position estimation techniques provide good performance at different operating conditions.