Stator resistance tuning based on a neural network in an indirect rotor field oriented control system of an induction motor

Abstract

This paper presents an ANN-based (artificial neural network-based)method of stator resistance tuning in an IRFO (indirect rotor field oriented) control system of an induction motor. This method is based on the conventional two-layer ANN in which the rotor time constant is not a constant parameter and is identified using a model reference adaptive system (MRAS)- based procedure. During the training, rotor speed estimation of the induction motor is enabled. The difference between the actual and the estimated rotor speed is used as a signal for manual stator resistance tuning. Computer simulations and experimental results show the effectiveness of the described approach in a low rotor speed region.

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.

Mateo Bašić

Full Professor | Department of Power Electronics and Control

Full professor at the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture in Split, with recent research interests related to the fields of power electronics and renewable energy sources, with a special focus on energy-efficient control of inverters, battery systems, wind turbines, photovoltaic sources and self-excited induction generators in microgrids - both in island operation and in grid-tie operation.