Feature‐based fault diagnosis system of induction motors using vibration signal

Abstract

Purpose

The purpose of this paper is to identify the efficiency of vibration signals for fault diagnosis system of induction motors.

Design/methodology/approach

A fault diagnosis system for induction motors using vibration signals is designed based on pattern recognition. Genetic algorithm is used for feature reduction and neural network tuning.

Findings

The usage of genetic algorithm improves the system performance through selecting significant features and optimizing network structure. The efficiency of vibration signals is demonstrated.

Practical implications

Condition monitoring and fault diagnosis for induction motors is one of the main industry maintenance parts. Motors faults usually result in whole production line breakdown. In this paper, one fault diagnosis system is proposed for induction motors based on feature recognition through combination of feature extraction, genetic algorithm and neural network techniques. From the paper, one can learn practically the whole procedure of feature‐based fault diagnosis system and the efficiency of GA and vibration signals for motor fault diagnosis. One real test has been done to validate the system performance. The results indicate that this system is promising for the real application in industry.

Originality/value

The use of genetic algorithm for feature selection and neural network tuning; the choice of vibration analysis for fault diagnosis of induction motor.

Citation

Han, T., Yang, B. and Yin, Z. (2007), "Feature‐based fault diagnosis system of induction motors using vibration signal", Journal of Quality in Maintenance Engineering, Vol. 13 No. 2, pp. 163-175. https://doi.org/10.1108/13552510710753069