Bearing fault diagnosis based on multi-scale permutation entropy and adaptive neuro fuzzy classifier. (February 2015)

• Record Type: Journal Article
• Authors: Tiwari, Rohit; Gupta, Vijay K; Kankar, PK
• Is Part Of: Journal of vibration and control. Volume 21:Number 3(2015)
• Page Start: 461
• Page End: 467
• Publication Date: 2015-02
• Subjects: Adaptive neuro-fuzzy classifier -- fault diagnosis -- multi-scale permutation entropy; Vibration -- Periodicals; Damping (Mechanics) -- Periodicals; 620.3
• DOI: 10.1177/1077546313490778
• Languages: English
• ISSNs: 1077-5463

Abstract

The rolling element bearing is among the most frequently encountered component in a rotating machine. Bearing fault can cause machinery breakdown and lead to productivity loss. A bearing fault diagnosis method has been proposed based on multi-scale permutation entropy (MPE) and adaptive neuro fuzzy classifier (ANFC). In this paper, MPE is applied for feature extraction to reduce the complexity of the feature vector. Extracted features are given input to the ANFC for an automated fault diagnosis procedure. Vibration signals are captured for healthy and faulty bearings. Experiment results pointed out that proposed method is a reliable approach for automated fault diagnosis. Thus, this approach has potential in diagnosis of incipient bearing faults.