SENSORLESS CONTROL SYSTEM OF SWITCHED RELUCTANCE MOTORS USING KOHONEN NEURAL NETWORK

To create a sensorless control system of switched reluctance motors with a more simple structure of the neural network than existing ones and to minimize the quantity of calculations, Kohonen artificial neural network was synthesized. The input values of network are only phase currents and voltage, and the output values ? control signals of the switches. By computer simulation the work of the sensorless control system using created artificial neural network was researched.