Improvement in classification accuracy and computational speed in bearing fault diagnosis using multiscale fuzzy entropy
- PDF / 3,567,198 Bytes
- 21 Pages / 595.276 x 790.866 pts Page_size
- 92 Downloads / 184 Views
(2020) 42:586
TECHNICAL PAPER
Improvement in classification accuracy and computational speed in bearing fault diagnosis using multiscale fuzzy entropy Amrinder Singh Minhas1 · Nipun Sharma1 · Gurpreet Singh2 · Pavan Kumar Kankar3 · Sukhjeet Singh1 Received: 1 November 2019 / Accepted: 1 October 2020 © The Brazilian Society of Mechanical Sciences and Engineering 2020
Abstract The operation of ball bearings under varying faulty conditions comprises complex time-varying modulations in the acquired vibration signals. In such circumstances, the extraction of nonlinear dynamic parameters based on multiscale fuzzy entropy (MFE) and refined composite multiscale fuzzy entropy (RCMFE) have proved to be more efficient in fault recognition than the conventional feature extraction methods. However, the accuracy of the methods in classifying several fault classes should not arrive at the expense of higher computational cost. The two major factors responsible for affecting the computational cost are the sampling length and number of features. This paper investigates the capabilities of MFE and RCMFE methods to estimate several health states of bearing at a different range of sampling lengths and scale factors. The bearing condition comprises normal and defective states, where the defective state considers incipient and severe faulty conditions of bearing. The diagnosis capability of both methods is verified by employing the support vector machine classifier. Although the results demonstrate higher fault classification ability of RCMFE for both incipient and severe bearing faults, the results are more impressive, especially at a higher range of scale factors as well as at lower sampling lengths. Keywords Rolling element bearings · Multiscale fuzzy entropy · Refined composite multiscale entropy · Sampling length
1 Introduction
Technical Editor: Thiago Ritto. * Sukhjeet Singh [email protected] Amrinder Singh Minhas [email protected] Nipun Sharma [email protected] Gurpreet Singh [email protected] Pavan Kumar Kankar [email protected] 1
Department of Mechanical Engineering, Guru Nanak Dev University, Amritsar, Punjab, India
2
Department of Electronics Technology, Guru Nanak Dev University, Amritsar, Punjab, India
3
Discipline of Mechanical Engineering, Indian Institute of Technology, Indore, India
Bearings are one of the essential components in rotating machinery. A large contribution of the research is focused on developing the methods that can reliably identify the intrusion of the fault in the bearing [1]. The faults, if unattended, can surge from the incipient conditions to severe conditions [2]. For both the situations, several breakthroughs have been accomplished by developing theoretical models [3, 4], monitoring condition of bearing with vibration signals and more recently through current signatures [5–7] and recently by several fault feature extraction methods [8–10]. On reviewing different techniques, it is seen that bearing fault diagnosis has been accomplished by several linear
Data Loading...
