Title: Condition monitoring of cage rotor induction motor using electrical exogenous variables

Authors: Md. Sharif Iqbal; D.K. Chaturvedi

Addresses: Department of Electrical Engineering, Anand Engineering College, Keetham, Agra, UP, India ' Department of Electrical Engineering, Dayalbagh Educational Institute, Dayalbagh, Agra, UP, India

Abstract: Cage rotor induction motors are brushless singly excited very commonly used most reliable and low cost motor. It is extremely rugged in construction and most reliable and low cost motor. These motors are very faithful, but normally exposed to hostile environment while working. This is responsible for early deterioration and hence the cause for motor failure. So, proper condition monitoring and early prevention of the motor is very essential. Health monitoring using the electrical parameters is very effective and offers higher accuracy. This method is less expensive and moreover provides less complication due to the use of less number of sensors. Here online electrical parameters can perform the health monitoring online and the same data can be stored easily for off line health monitoring of motor. Electrical health monitoring never creates any trash and it is completely pollution free and environment friendly. Data can be used online for the implementation of soft computing techniques for the health monitoring of motors. Here different electrical exogenous parameters are used for health monitoring of induction motor and their results are analysed by various soft computing techniques like quantum-genetic algorithm-generalised neural network (Q-GA-GNN) and artificial neural network (ANN).

Keywords: induction motor; health monitoring; quantum-genetic algorithm-generalised neural network; Q-GA-GNN; artificial neural network; ANN.

DOI: 10.1504/IJSTDS.2021.118783

International Journal of Spatio-Temporal Data Science, 2021 Vol.1 No.3, pp.284 - 298

Received: 29 Jan 2020
Accepted: 26 Nov 2020
Published online: 06 Nov 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article