Denoising method based on hidden Markov tree model in dual tree complex wavelet domain and its application in mechanical fault diagnosis

Su Wen-sheng;Wang Feng-tao;Zhu Hong;Zhang Zhixin;Li Hongkun;Guo Zhenggang

Journal of Vibration and Shock ›› 2011, Vol. 30 ›› Issue (6) : 47-52.

PDF(1645 KB)
PDF(1645 KB)
Journal of Vibration and Shock ›› 2011, Vol. 30 ›› Issue (6) : 47-52.
论文

Denoising method based on hidden Markov tree model in dual tree complex wavelet domain and its application in mechanical fault diagnosis

  • Su Wen-sheng; Wang Feng-tao; Zhu Hong;Zhang Zhixin;Li Hongkun;Guo Zhenggang
Author information +
History +

Abstract

A denoising method based on hidden Markov tree model in dual tree complex wavelet domain is proposed, and it is successfully applied in mechanical fault diagnosis. Noise is inevitably present in mechanical vibration signal, which makes the extraction of weak fault information be the difficulty and hotspot of fault diagnosis. Since dual tree complex wavelet transform has the approximate translation invariance while hidden Markov tree model can effectively describes the dependency between wavelet coefficients and the non-Gaussian nature of these coefficients, a method combining these advantages can achieve better denoising results than that of conventional soft or hard threshold denoising and hidden Markov tree model in wavelet domain. Applications of simulation signals verify that Gaussian white noise can be effectively inhibited, as well as abnormal impact can be removed by using this method. For actual rolling bearing signal, satisfied result also can be acquired

Key words

Dual-tree complex wavelet transform / hidden Markov tree model / denoising / fault diagnosis

Cite this article

Download Citations
Su Wen-sheng;Wang Feng-tao;Zhu Hong;Zhang Zhixin;Li Hongkun;Guo Zhenggang. Denoising method based on hidden Markov tree model in dual tree complex wavelet domain and its application in mechanical fault diagnosis[J]. Journal of Vibration and Shock, 2011, 30(6): 47-52
PDF(1645 KB)

Accesses

Citation

Detail

Sections
Recommended

/