Abstract
A rolling element bearing fault recognition approach is proposed in this paper. This method combines the basic Higher-order spectrum (HOS) theory and fuzzy clustering method in data mining area. In the first step, all the bispectrum estimation results of the training samples and test samples are turned into binary feature images. Secondly, the binary feature images of the training samples are used to construct object templates including kernel images and domain images. Every fault category has one object templates. At last, by calculating the distances between test samples' binary feature images and the different object templates, the object classification and pattern recognition can be effectively accomplished. Bearing is the most important and much easier to be damaged component in rotating machinery. Furthermore, there exist large amounts of noise jamming and nonlinear coupling components in bearing vibration signals. The Higher Order Cumulants (HOC), which can quantitatively describe the nonlinear characteristic signals with close relationship between the mechanical faults, is introduced in this paper to de-noise the raw bearing vibration signals and obtain the bispectrum estimation pictures. In the experimental part, the rolling bearing fault diagnosis experiment results proved that the classification was completely correct.
Highlights
Some rotating machinery failure features which are inconspicuous in stable conditions can reflect many special features [1,2,3]
Han / Rolling element bearing fault recognition approach based on fuzzy clustering bispectrum estimation methods which had anti-noise ability, and successfully introduced Higher Order Cumulants (HOC) into the nonlinear non-Gaussian signals processing [10,11,12,13]
Han / Rolling element bearing fault recognition approach based on fuzzy clustering bispectrum estimation 215 is called cumulant production function of x
Summary
Some rotating machinery failure features which are inconspicuous in stable conditions can reflect many special features [1,2,3]. In bad working environment, various faults may occur, such as crack, vortex move, friction and oil film vortex move etc These faults’ occurrence or development often leads to the dynamic signals having nonlinear characteristics, which can characterize the existence of some certain faults [7,8]. 214 W.Y. Liu and J.G. Han / Rolling element bearing fault recognition approach based on fuzzy clustering bispectrum estimation methods which had anti-noise ability, and successfully introduced Higher Order Cumulants (HOC) into the nonlinear non-Gaussian signals processing [10,11,12,13]. The HOS can make up the limitations in Fourier analysis, which makes it be a new fault diagnosis method and an effective tool to analyze the nonlinear signals. Based on the above analysis and aimed at the non-Gaussianity of the rotating machinery bearing vibration signals, a fuzzy clustering bispectrum estimation approach is proposed in this paper.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have