Open AccessRolling element bearing fault diagnosis based on non‐local means de‐noising and empirical mode decomposition
Author(s) -
Van Mien,
Kang HeeJun,
Shin KyooSik
Publication year - 2014
Publication title -
iet science, measurement and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.418
H-Index - 49
eISSN - 1751-8830
pISSN - 1751-8822
DOI - 10.1049/iet-smt.2014.0023
Subject(s) - hilbert–huang transform , noise (video) , vibration , rolling element bearing , fault (geology) , signal (programming language) , bearing (navigation) , envelope (radar) , distortion (music) , interference (communication) , acoustics , background noise , noise reduction , computer science , engineering , electronic engineering , artificial intelligence , white noise , physics , telecommunications , seismology , image (mathematics) , programming language , geology , amplifier , radar , channel (broadcasting) , cmos
The presence of faults in the bearings of rotating machinery is usually observed with impulses in the vibration signals. However, the vibration signals are generally non‐stationary and usually contaminated by noise because of the compounded background noise present in the measuring device and the effect of interference from other machine elements. Therefore in order to enhance monitoring condition, the vibration signal needs to be properly de‐noised before analysis. In this study, a novel fault diagnosis method for rolling element bearings is proposed based on a hybrid technique of non‐local means (NLM) de‐noising and empirical mode decomposition (EMD). An NLM which removes the noise with minimal signal distortion is first employed to eliminate or at least reduce the background noise present in the measuring device. This de‐noised signal is then decomposed into a finite number of stationary intrinsic mode functions (IMF) to extract the impulsive fault features from the effect of interferences from other machine elements. Finally, envelope analyses are performed for IMFs to allow for easier detection of such characteristic fault frequencies. The results of simulated and real bearing vibration signal analyses show that the hybrid feature extraction technique of NLM de‐noising, EMD and envelope analyses successfully extract impulsive features from noise signals.