A novel manifold learning denoising method on bearing vibration signals

Jingwei Gao, Ruichen Wang, Lei Hu, Rui Zhang

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Bearing failures are a major source of problem in rotating machines. These faults appear as impulses at periodic intervals resulting in form of specific characteristic frequencies. However, the characteristic frequencies are submerged in noise causing by a result of small imperfections in the balance or smoothness of the components of the bearing. To retrieve the characteristic fault frequencies of the vibration signal, signal denoising is an essential processing step in fault diagnosis of the bearings. This paper presents time-frequency analysis and nonlinear manifold learning technique for denoising vibration signals corrupted by additive white Gaussian noise. According to keeping the computing time acceptable, a novel manifold learning denoising method is put forward combining data compression and reconstruct operations. Simulation and experiments are employed to verify the feasibility and effectiveness of the proposed method on bearing vibration signals. Furthermore, this method can be used in other fault detection fields, such as engine, suspension device, and vehicle structures.
Original languageEnglish
Article number1882
Pages (from-to)175-189
Number of pages15
JournalJournal of Vibroengineering
Volume18
Issue number1
Publication statusPublished - 15 Feb 2016

Fingerprint

Bearings (structural)
Signal denoising
Data compression
Fault detection
Failure analysis
Suspensions
Engines
Defects
Processing
Experiments

Cite this

Gao, Jingwei ; Wang, Ruichen ; Hu, Lei ; Zhang, Rui. / A novel manifold learning denoising method on bearing vibration signals. In: Journal of Vibroengineering. 2016 ; Vol. 18, No. 1. pp. 175-189.
@article{4626719ed45b4e45aef460a25682cbad,
title = "A novel manifold learning denoising method on bearing vibration signals",
abstract = "Bearing failures are a major source of problem in rotating machines. These faults appear as impulses at periodic intervals resulting in form of specific characteristic frequencies. However, the characteristic frequencies are submerged in noise causing by a result of small imperfections in the balance or smoothness of the components of the bearing. To retrieve the characteristic fault frequencies of the vibration signal, signal denoising is an essential processing step in fault diagnosis of the bearings. This paper presents time-frequency analysis and nonlinear manifold learning technique for denoising vibration signals corrupted by additive white Gaussian noise. According to keeping the computing time acceptable, a novel manifold learning denoising method is put forward combining data compression and reconstruct operations. Simulation and experiments are employed to verify the feasibility and effectiveness of the proposed method on bearing vibration signals. Furthermore, this method can be used in other fault detection fields, such as engine, suspension device, and vehicle structures.",
keywords = "bearing, vibration signals denoising, manifold learning, Time-frequency analysis",
author = "Jingwei Gao and Ruichen Wang and Lei Hu and Rui Zhang",
year = "2016",
month = "2",
day = "15",
language = "English",
volume = "18",
pages = "175--189",
journal = "Journal of Vibroengineering",
issn = "1392-8716",
publisher = "Vibromechanika",
number = "1",

}

A novel manifold learning denoising method on bearing vibration signals. / Gao, Jingwei; Wang, Ruichen; Hu, Lei; Zhang, Rui.

In: Journal of Vibroengineering, Vol. 18, No. 1, 1882, 15.02.2016, p. 175-189.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A novel manifold learning denoising method on bearing vibration signals

AU - Gao, Jingwei

AU - Wang, Ruichen

AU - Hu, Lei

AU - Zhang, Rui

PY - 2016/2/15

Y1 - 2016/2/15

N2 - Bearing failures are a major source of problem in rotating machines. These faults appear as impulses at periodic intervals resulting in form of specific characteristic frequencies. However, the characteristic frequencies are submerged in noise causing by a result of small imperfections in the balance or smoothness of the components of the bearing. To retrieve the characteristic fault frequencies of the vibration signal, signal denoising is an essential processing step in fault diagnosis of the bearings. This paper presents time-frequency analysis and nonlinear manifold learning technique for denoising vibration signals corrupted by additive white Gaussian noise. According to keeping the computing time acceptable, a novel manifold learning denoising method is put forward combining data compression and reconstruct operations. Simulation and experiments are employed to verify the feasibility and effectiveness of the proposed method on bearing vibration signals. Furthermore, this method can be used in other fault detection fields, such as engine, suspension device, and vehicle structures.

AB - Bearing failures are a major source of problem in rotating machines. These faults appear as impulses at periodic intervals resulting in form of specific characteristic frequencies. However, the characteristic frequencies are submerged in noise causing by a result of small imperfections in the balance or smoothness of the components of the bearing. To retrieve the characteristic fault frequencies of the vibration signal, signal denoising is an essential processing step in fault diagnosis of the bearings. This paper presents time-frequency analysis and nonlinear manifold learning technique for denoising vibration signals corrupted by additive white Gaussian noise. According to keeping the computing time acceptable, a novel manifold learning denoising method is put forward combining data compression and reconstruct operations. Simulation and experiments are employed to verify the feasibility and effectiveness of the proposed method on bearing vibration signals. Furthermore, this method can be used in other fault detection fields, such as engine, suspension device, and vehicle structures.

KW - bearing

KW - vibration signals denoising

KW - manifold learning

KW - Time-frequency analysis

UR - http://www.jve.lt/Vibro/JVE-2016-18-1/JVE0181602.html

M3 - Article

VL - 18

SP - 175

EP - 189

JO - Journal of Vibroengineering

JF - Journal of Vibroengineering

SN - 1392-8716

IS - 1

M1 - 1882

ER -