A New Signal Classification Method Based on EEMD and FCM and its Application in Bearing Fault Diagnosis

Abstract:

In order to diagnose nonlinear and non-stationary fault signals in bearings, a new method is presented based on the ensemble empirical decomposition (EEMD) and the fuzzy c-means (FCM) clustering algorithm. At first, the bearing fault signals were decomposed using EEMD and the intrinsic mode functions (IMF) were produced. Second the energy ratios of these IMFs were computed and taken as the characteristic parameters for the FCM clustering algorithm. Then the FCM clustering method was conducted to classify the bearing fault signals into different classes. Finally, on the basis of the preceding classification results, we diagnosed a bearing fault through taking its distances between different cluster centers as the criteria. Experiments showed that the bearing fault signal classification results conformed to actualities well. The new signal classification method can be effectively utilized in bearing fault diagnosis.

• Periodical: Applied Mechanics and Materials (Volumes 602-605)
• Pages: 1803-1806
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.602-605.1803
• Online since: August 2014
• Authors: Chao Jie Wang, Hong Yi Li, Wei Xiang, Di Zhao*
• Keywords: Bearing Fault Diagnosis, EEMD, Energy Ratio, FCM, Signal Classification

References

[1] Z.H. Wu, N.E. Huang, Ensemble empirical mode decomposition: a noise assisted data analysis method, Adv. Adapt. Data Anal., vol. 1, no. 1, pp.1-41, Jan. (2009).

DOI: 10.1142/s1793536909000047

[2] J.C. Bezdek, Pattern Recognition with Fuzzy Objective Function Algorithm. New York, CA: Plenum Press, (1981).

[3] Information on http: /csegroups. case. edu/bearingdatacenter/pages/welcome-case-western-reserve-university-bearing- data-center-website.