A novel multi-segment feature fusion based fault classification approach for rotating machinery. (1st May 2019)

• Record Type: Journal Article
• Authors: Liang, Jiejunyi; Zhang, Ying; Zhong, Jian-Hua; Yang, Haitao
• Is Part Of: Mechanical systems and signal processing. Volume 122(2019)
• Page Start: 19
• Page End: 41
• Publication Date: 2019-05-01
• Subjects: Signal segmentation -- Empirical mode decomposition -- Mathematical morphology -- Deep belief networks -- Pairwise coupling -- Patter recognition; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2018.12.009
• Languages: English
• ISSNs: 0888-3270

Abstract

Highlights: Grassmann manifold–angular central Gaussian distribution for signal segmentation. A new wavelet transform – ensemble empirical mode decomposition is designed. An unsupervised feature fusion method is proposed to reduce the feature dimension. An effective fault classification framework is proposed and validated by experiments. Abstract: Accurate and efficient rotating machinery fault diagnosis is crucial for industries to guarantee the productivity and reduce the maintenance cost. This paper systematically proposes a new fault diagnosis approach including signal processing techniques and pattern recognition method. In order to reveal more useful details in a fault residing signal, a novel automatic signal segmentation method named Grassmann manifold – angular central Gaussian distribution is proposed to divide a raw signal into several segments, resulting in a significant improvement of diagnosis accuracy. An improved empirical mode decomposition, wavelet transform – ensemble empirical mode decomposition, is also designed which could adequately solve the problems of mode mixing and end effects. Moreover, a morphological method usually used in image processing is investigated and adopted to change the shape of the intrinsic mode functions to further reveal the faulty impulses. In order to reduce the high dimension of the extracted features and improve the computational efficiency and accuracy, a deep belief network is designed to conduct information fusion, and compared with widely adopted kernel principal component analysis. For classification, a pairwise coupling strategy is proposed and combined with sparse Bayesian extreme learning machine. The experiments conducted using the proposed approach demonstrate the effectiveness of the proposed system.