Untrained artificial neuron based speed control of interior permanent magnet motor drives over full operating speed range

Abstract

This paper presents an intelligent speed controller for the interior permanent magnet synchronous motor (IPMSM), based on a single artificial neuron (SAN). Traditional artificial neural network-based motor controllers require extensive offline training, which is both time consuming and requires extensive knowledge of motor behaviour for the specific drive system. In addition, drive behaviour is unpredictable when parameters outside the training set are encountered. The proposed drive system overcomes these limitations by requiring no offline training, is robust under varying operating parameters and is easily adaptable to various drive systems. Drive efficacy is verified in simulation as well as experimentally.