Title :
A Diagnosis Method Based on Wavelet Coefficient Scale Relativity Correlation Dimension for Fault
Author :
Gu, Jun-jie ; Tian, Jin ; Peng, Xue-zhi ; Qin, Zhi-ming
Author_Institution :
North China Electr. Power Univ., Baoding
Abstract :
This paper introduces correlation dimension as a tool to describing machinery condition. A threshold filtering algorithm based on the region relativity of the wavelet coefficients for reducing noise is introduced. Utilizing the above method, the vibration signals of the fan under different working conditions are analyzed. The result shows that the characteristics of the signal could be preserved completely. The correlation dimension is able to identify the conditions of the fan with faults compared with the normal condition, thereby providing an effective technology for condition monitoring and fault diagnosis of mechanical equipment.
Keywords :
condition monitoring; fans; fault diagnosis; mechanical engineering computing; vibrations; wavelet transforms; condition monitoring; fault diagnosis method; machinery condition; mechanical equipment; threshold filtering algorithm; vibration signals; wavelet coefficient scale relativity correlation dimension; Condition monitoring; Cybernetics; Fault diagnosis; Frequency estimation; Machine learning; Noise reduction; Signal analysis; Vibrations; Wavelet coefficients; White noise; Correlation dimension; Fan; Fault diagnosis; Scale relativity; Wavelet Coefficient;
Conference_Titel :
Machine Learning and Cybernetics, 2007 International Conference on
Print_ISBN :
978-1-4244-0973-0
Electronic_ISBN :
978-1-4244-0973-0
DOI :
10.1109/ICMLC.2007.4370303
