An Artificial Neural Network Based Rotor Position Estimation for Sensorless Permanent Magnet Brushless DC Motor Drive

This paper presents a sensorless scheme for rotor position estimation of permanent magnet brushless dc motor using artificial neural networks with the formulation and comprehensive analysis of vector control PMBLDC drive. The PMBLDC motors are widely used as they possess high power density and are simple to control. However the operation of PMBLDC motor, demands the knowledge of rotor position as a prerequisite. In most of the drive systems, the rotor position sensors produce undesirable effects such as mechanical losses and also have other disadvantages. In order to overcome the disadvantages introduced by position sensors, there arises a need for sensorless scheme of the drive. In this paper, an artificial neural network based sensorless control is described. The performance of the drive with sensorless scheme is also analyzed