Separation of saliency information for speed sensorless detection of induction machines flux and rotor position

Purpose – The purpose of this paper is to describe an effective method to eliminate or substantially reduce the modulation harmonics due to saturation and inter-modulation for sensorless speed control induction motor drives at low and zero speed with high loads using artificial neural networks (ANN). Design/methodology/approach – In this paper, the separation of the saturation signal, the slotting signal, and the inter-modulation signal components in squirrel cage induction machines operating at low and zero frequency using ANN has been experimentally implemented and measurement results are given. Findings – The measurement results show the advantages of the application of the proposed technique at low and zero speed sensorless control even at high load levels. Originality/value – The paper describes an effective method of eliminating or reducing modulation harmonics in induction motor drives.