Applied Mathematics and Mechanics

, Volume 12, Issue 8, pp 745–749 | Cite as

The application of pattern recognition techniques in fault diagnosis of machinery equipment

  • Yan Yu-ling
  • Xu Yin-ge


In this paper, the characteristics of vibration signal of machinery in different running conditions are statistically analysed, and some moments of statistical distribution of signals are selected as the eigenvector to condense the state information. Here, we divide the states of machinery into two: ‘good’ and ‘faulty’, and the pattern recognition techniques are used to classify the running conditions of machinery. At the end of this paper, the authors present some test data, and from the results obtained, it's verified that the eigenvector selected is reliable and sensible to faults. And the results also show the effectiveness of classification rule.

Key words

pattern recognition condense state information divergence index inter-object distance intra-object distance 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Julius, T. Tou,Pattern Recognition Principles, Addison-Wesley Pub. Comp. Inc., Massachusetts (1974).Google Scholar
  2. [2]
    Wang Fei-long,Foundation of Pattern Recognition, Hubei Science and Tech. Pub. (1986). (in Chinese)Google Scholar
  3. [3]
    Kashyap, R. L., Optimal feature selection and decision rules in classification problems with time series,IEEE Trans. Inform. Theory,IT-24, 3 (1978), 281–288.MathSciNetCrossRefGoogle Scholar
  4. [4]
    Mathematics and Mechanics Department, Zhongshan University,Probability and Statistics (1), People's Education Pub., (1980). (in Chinese)Google Scholar

Copyright information

© SUT 1991

Authors and Affiliations

  • Yan Yu-ling
    • 1
  • Xu Yin-ge
    • 2
  1. 1.Nanjing Aeronautical InstituteNanjing
  2. 2.Peking Jiaotong Manager CollegeBeijing

Personalised recommendations