A sensorless three-phase induction motor drive using indirect field oriented control and artificial neural network

Abstract

Sensorless induction drive systems are more popular due to their reliability and low cost. Therefore, it is very beneficial to use sensorless drive systems where the rotor speed can be estimated by means of an intelligent control algorithm instead of the use of directly measuring methods. This paper presents a method of the online speed estimation for a three-phase induction motor in Indirect Field Oriented Control (IFOC) scheme accompanying an Artificial Neural Network (ANN). The error-back propagation algorithm is used for training the neural network. The error between rotor flux linkages in the adaptive model and the reference model is back propagated to adjust weights of the neural network model to estimate the motor speed. The simulation results obtained using MATLAB/Simulink show that the estimated motor speed always tracks the actual motor speed with very small error as long as the sampling time is small enough and the learning rate can be chosen appropriately.