International Journal of Safety

The Korean Society of Safety (한국안전학회)
권호 표지

Detection and Classification of Bearing Flaking Defects by Using Kullback Discrimination Information (KDI)

  • Kim, Tae-Gu (Department of Occupational Health & Safety Engineering, Inje University) ;
  • Takabumi Fukuda (Department of Safety Engineering, Faculty of Engineering, Yokohama National University) ;
  • Hisaji Shimizu (Department of Safety Engineering, Faculty of Engineering, Yokohama National University)
  • Published : 2002.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

Kullback Discrimination Information (KDI) is one of the pattern recognition methods. KDI defined as a measure of the mutual dissimilarity computed between two time series was studied for detection and classification of bearing flaking on outer-race and inner-races. To model the damages, the bearings in normal condition, outer-race flaking condition and inner-races flaking condition were provided. The vibration sensor was attached by the bearing housing. This produced the total 25 pieces of data each condition, and we chose the standard data and measure of distance between standard and tested data. It is difficult to detect the flaking because similar pulses come out when balls pass the defection point. The detection and classification method for inner and outer races are defected by KDI and nearest neighbor classification rule is proposed and its high performance is also shown.

Keywords

References

  1. W. Gersch, Two Applications of Parametric Time Series Modeling Methods, Mechanical Signature Analysis The-ory and Application, Academic Press, UK, pp. 288-318, 1986
  2. T. Fukuda, M. Matsuoka, X. Li, H. Shimizu, Fault Detection and its Classification of a Compressor by Kullback Dischmination Information, Proc. of 1997 JSME Annual Meeting, Vol. 1, pp. 418-419 (in Japa-nese), 1997
  3. Li, C.J. and Kim, T., Linear Model QUsed Fault Detec-tion and Isolation for a Screw Compressor, Mechanical Systems and Signal Processing, 8-3, pp. 259-273, 1993 https://doi.org/10.1006/mssp.1994.1020
  4. Tae Gu, Kim, Fukuda and Shimizu: A study on bearing fault detection and classification using KDI(In Japanese), Journal of Japan Society for Safety Engineering, Vol. 37, No. 3, pp. 172-176