NEURO-CONTROLLER SYNTHESIS TO FORM A FLAT SPEED-TORQUE CHARACTERISTICS OF SWITCHED RELUCTANCE MOTORS

Abstract

To create a sensorless control system of switched reluctance motors (SRM) that provides a flat speed-torque characteristics, a feedforward artificial neural network (ANN), that uses currents as the input signals, was synthesized. By computer modeling the work of the sensorless control system using created ANN was researched.