Bearing fault diagnosis based on feature extraction of empirical wavelet transform (EWT) and fuzzy logic system (FLS) under variable operating conditions

Journal of Vibroengineering. 2019;21(6):1636-1650 DOI 10.21595/jve.2019.20092

 

Journal Homepage

Journal Title: Journal of Vibroengineering

ISSN: 1392-8716 (Print); 2538-8460 (Online)

Publisher: JVE International

LCC Subject Category: Technology: Mechanical engineering and machinery

Country of publisher: Lithuania

Language of fulltext: English

Full-text formats available: PDF, XML

 

AUTHORS


Fawzi Gougam (Solid Mechanics and Systems Laboratory (LMSS), University M’hamed Bougara Boumerdes, Algeria)

Chemseddine Rahmoune (Solid Mechanics and Systems Laboratory (LMSS), University M’hamed Bougara Boumerdes, Algeria)

Djamel Benazzouz (Solid Mechanics and Systems Laboratory (LMSS), University M’hamed Bougara Boumerdes, Algeria)

Boualem Merainani (Solid Mechanics and Systems Laboratory (LMSS), University M’hamed Bougara Boumerdes, Algeria)

EDITORIAL INFORMATION

Blind peer review

Editorial Board

Instructions for authors

Time From Submission to Publication: 25 weeks

 

Abstract | Full Text

Condition monitoring of rotating machines has become a more important strategy in structural health monitoring (SHM) research. For fault recognition, the analysis is categorized in two essential main parts: Feature extraction and classification; the first one is used for extracting the information from the signal and the other for decision-making based on these features. A higher accuracy is needed for sensitive places to avoid all kinds of damages that can lead to economic losses and it may affect the human safety as well. In this paper, we propose a new hybrid and automatic approach for bearing faults diagnosis. This method uses a combination between Empirical wavelet Transform (EWT) and Fuzzy logic System (FLS), in order to detect and localize the early degradation of bearing state under different working conditions. EWT build a wavelet filter bank to extract amplitude modulated-frequency modulated component of signal. Modes presenting a high impulsiveness is then selected using the kurtosis indicator. Thereafter, time domain features (TDFs) are applied for the reconstructed signal to extract the fault features which are finally used as an inputs of FLS in order to identify and classify the bearing states. The experimental results shows that the proposed method can accurately extract and classify the bearing fault under variable conditions. Moreover, performance of EWT and empirical mode decomposition (EMD) are studied and shows the superiority of the proposed method.