Multiple Fault Detection of Rolling Bearing through Ensemble Empirical Mode Decomposition of Vibration Signal
Sandip Kumar Singh
Sandip Kumar Singh*, Department of Mechanical Engineering, V B S Purvanchal University Jaunpur, Uttar Pradesh (INDIA).
Manuscript received on November 22, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 2624-2626 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B3562129219/2019©BEIESP | DOI: 10.35940/ijeat.B3562.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Generally, two or more faults occur simultaneously in the bearings. These Compound Faults (CF) in bearing, are most difficult type of faults to detect, by any data-driven method including machine learning. Hence, it is a primary requirement to decompose the fault vibration signals logically, so that frequencies can be grouped in parts. Empirical Mode Decomposition (EMD) is one of the simplest techniques of decomposition of signals. In this paper we have used Ensemble Empirical Mode Decomposition (EEMD) technique for compound fault detection/identification. Ensembled Empirical Mode Decomposition is found useful, where a white noise helps to detect the bearing frequencies. The graphs show clearly the capability of EEMD to detect the multiple faults in rolling bearings.
Keywords: Compound Fault (CF), Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD), Intrinsic Mode Functions (IMF)