Neural Network and Fuzzy Logic Based Control of Induction Machines

Abstract

Induction motors have been used as the workhorse in industry for a long time due to their being easy to build, highly robust, and having generally satisfactory efficiency. In addition, induction generators play an important role in renewable energy systems such as energy systems with variable-speed wind turbines. The induction machine is a nonlinear multivariable dynamic system with parameters that vary with temperature, frequency and magnetic saturation. Considering that neural networks are capable of handling time varying nonlinearities due to their own nonlinear nature, they are suitable for application in induction machine systems. This lecture presents a brief review of applications of artificial neural networks and fuzzy logic for induction machines. Most applications of neuro and/or fuzzy theory in induction machine control systems focus on advanced controllers for speed, position or voltage, where the conventional PI controller is replaced by a neuro and/or fuzzy controller. Few other applications will also be shown in this lecture, such as: neural network-based speed estimator, neural network-based inverter control, applications of neural networks in waveform processing and delayless filtering, identification of machine parameters based on fuzzy/neural concepts and approaches for the efficiency improvement in induction machine systems. Some of the presented simulation and experimental results are obtained at the Research laboratory for Power Electronics of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture in Split, Croatia.

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.