A Method for Quality Inspection of Motors by Detecting Abnormal Sound

Recently, a quality of motors is inspected by human ears. In this paper, I propose two systems using a method of speech recognition for automation of the inspection. The first system is based on a method of linear processing which uses K-means and Nearest Neighbor method, and the second is based on a method of non-linear processing which uses neural networks. I used motor sounds in these systems, and I successfully recognize 86.67% of motor sounds in the linear processing system and 97.78% in the non-linear processing system.

Authors:

• Tadatsugu Kitamoto

Keywords:

• Acoustical diagnosis
• Neural networks
• K-means
• Short-time Fourier transformation

References:

[1] H. Sugimoto and K. Fukuda, "Abnormal noise detector for gear units", J.
Acoust. Soc. Am., vol.82, pp.1856, 1987.
[2] Z.Zhang and H.Kawabata, "Study of Detection Method of Abnormal
Sound Using Cellular Neural Network", Trans. J. Soc. of Mechanical
Engineers. C, vol. 69, no. 668, pp. 3207-3214, 2003.
[3] Munehiro Namba "On the quality inspection of motors by detecting
abnormal noise".
[4] S. Miyamoto, introduction to cluster analysis (Book style). Tokyo, CA:
Morikita, 1999, pp. 13-24.
[5] G. F. Page, J. B. Gomm and D. Williams, Application of neural networks
to modeling and control (Book style). London, CA: CHAPMAN &
HALL, 1993, pp.9-23.
[6] Simon Haykin, Neural networks (Book style). New Jersey, CA: Prentice
Hall, 1999, pp. 159-173.