유전 알고리즘 기반 특징 분석 기법을 이용한 고 신뢰성 유도 전동기 결함 분류

Fault diagnosis is a vital task in the maintenance of industry machines. Induction motors play an increasing importance in industrial manufacturing. This paper proposes a reliable fault diagnosis methodology for early identifying various induction motor failures by exploiting a genetic algorithm (GA)-based feature analysis technique which selects the most discriminative fault signatures by taking a transformation matrix. Experimental results show that the features selected by the GA outperforms original and randomly selected features using the same k-nearest neighbor (k-NN) classifier in terms of convergence rate, the number of features, and classification accuracy. The GA-based feature selection method improves the classification accuracy from 3% to 100% and from 30% to 100% over the original and randomly selected features, respectively.