Diagnostics of Induction Motor Based on Analysis of Acoustic Signals with the Application of Eigenvector Method and K-Nearest Neighbor Classifier

Archives of Metallurgy and Materials

A. Głowacz¹ 

[1] Faculty of Electrical Engineering, Automatics, Computer Science and Electronics, Department of Automatics, Agh University of Science and Technology, 30-059 Kraków, 30 Mickiewicza Av., Poland;

关键词: Keywords: Diagnostics;    Recognition;    Acoustic signal;    Induction motor;   

DOI  :  10.2478/v10172-012-0039-y

学科分类：金属与冶金

来源: Akademia Gorniczo-Hutnicza im. Stanislawa Staszica / University of Mining and Metallurgy

【 摘 要 】

In this paper numerical experiments are proposed to investigate differences between the acoustic signals of induction motors. Four conditions of induction motor were considered. Investigations were carried out with application of eigenvector method and K-Nearest Neighbor classifier with Minkowski distance. Pattern creation process was conducted for 20 samples of sound. Identification process used 96 samples of sound. The obtained results confirm the correctness of the solutions methodology.

【 授权许可】

Unknown