A feature extraction method based on HLMD and MFE for bearing clearance fault of reciprocating compressor. (July 2016)

• Record Type: Journal Article
• Authors: Zhao, Haiyang; Wang, Jindong; Han, Hui; Gao, Yiqi
• Is Part Of: Measurement. Volume 89(2016:Jul.)
• Page Start: 34
• Page End: 43
• Publication Date: 2016-07
• Subjects: Local mean decomposition -- Multiscale fuzzy entropy -- Reciprocating compressor -- Bearing clearance -- Fault diagnosis; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2016.03.076
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: A novel construction method of local mean function and envelope function. MFE of the selected PF components were calculated to form the eigenvectors matrix. The eigenvectors with the best divisibility were selected from matrix. A higher accuracy for diagnosis of reciprocating compressor bearing clearance fault. Abstract: According to the nonlinearity, nonstationarity and multi-component coupling characteristics of reciprocating compressor vibration signal, a feature extraction method based on hermite local mean decomposition (HLMD) and multiscale fuzzy entropy (MFE) is proposed for the diagnosis of reciprocating compressor oversized bearing clearance faults. Firstly, aiming at the strong nonstationary characteristic of vibration signal, a novel HLMD algorithm was given by using the monotone piecewise cubic hermite interpolation (MPCHI) instead of cubic spline interpolation (CSI) to construct the envelopes. Secondly, HLMD was performed on the vibration signals in each state and a series of PF components are produced, and the highlighted PF components which contain the main information of fault state were chosen with the correlation coefficient. Thirdly, MFE of the selected PF components were calculated to form the eigenvectors matrix, and the eigenvectors which have the best divisibility were extracted based on the average euclidean distances of each scale factor. Finally, four bearing clearance fault states were extracted by the proposed method, and taken SVM as a pattern classifier, the faults were diagnosed accurately. Furthermore, the comparison of recognition results with other three feature extraction methods demonstrates the superiority of this method.