Artificial neural network based voltage controller for energy efficient induction motor drive

A loaded induction motor is generally obtained using a search technique which involves more time and the machine is subjected to many step changes of voltage which is undesirable. This paper presents two novel techniques for energy efficient operation of a voltage controlled induction motor drive using artificial neural networks (ANN). In the proposed methods, the time required to converge to the best efficiency point of the drive is minimum and the machine is subjected to a maximum of two step changes of voltage, irrespective of load. The backpropagation neural network is trained off-line to identify the optimal efficiency point of the motor in the entire operating range with a no priori knowledge of the machine parameters.