Multilayer Neural Network Verification of Mutual Inductance Choice in Sensorless Induction Motor Vector Control System

Abstract

Squirrel-cage induction motor (IM) is the most frequently used electric machine in modern controlled electromotor drives. In this paper is analyzed IM sensorless vector control system based on MRAS (Model Reference Adaptive System) theory. It is especially important get knowledge of the IM rotor time constant incorporated into observer (Fig. 1.). In this constant is incorporated IM mutual inductance Lm. The characteristic of the observed IM is varying of mutual inductance Lm at lower frequency of supply voltage due to saturation effect in iron. In this paper accuracy of the mutual inductance Lm in the observer of induction motor vector control is verified by using feedforward static four layer artificial neural network (ANN).

Dinko Vukadinović

Full Professor | Department of Power Electronics and Control

Full professor at the Faculty of Electrical Engineering, Mechanical Engineering, and Naval Architecture in Split, specialized in modern control systems for power electronic converters, electric motors, and generators. At the Power Electronics Research Laboratory, he leads experimental projects and develops advanced methods for regulating electrical machines and converters, while supervising doctoral research in these areas.