Novel spectral kurtosis technology for adaptive vibration condition monitoring of multi-stage gearboxes

L. Gelman, N. Harish Chandra, R. Kurosz, F. Pellicano, M. Barbieri, A. Zippo

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this paper, the novel wavelet spectral kurtosis (WSK) technique is applied for the early diagnosis of gear tooth faults. Two variants of the wavelet spectral kurtosis technique, called variable resolution WSK and constant resolution WSK, are considered for the diagnosis of pitting gear faults. The gear residual signal, obtained by filtering the gear mesh frequencies, is used as the input to the SK algorithm. The advantages of using the wavelet-based SK techniques when compared to classical Fourier transform (FT)-based SK is confirmed by estimating the toothwise Fisher's criterion of diagnostic features. The final diagnosis decision is made by a three-stage decision-making technique based on the weighted majority rule. The probability of the correct diagnosis is estimated for each SK technique for comparison. An experimental study is presented in detail to test the performance of the wavelet spectral kurtosis techniques and the decision-making technique.

LanguageEnglish
Pages409-416
Number of pages8
JournalInsight: Non-Destructive Testing and Condition Monitoring
Volume58
Issue number8
DOIs
Publication statusPublished - 1 Aug 2016
Externally publishedYes

Fingerprint

Condition monitoring
Gears
Decision making
Gear teeth
Pitting
Fourier transforms

Cite this

Gelman, L. ; Harish Chandra, N. ; Kurosz, R. ; Pellicano, F. ; Barbieri, M. ; Zippo, A. / Novel spectral kurtosis technology for adaptive vibration condition monitoring of multi-stage gearboxes. In: Insight: Non-Destructive Testing and Condition Monitoring. 2016 ; Vol. 58, No. 8. pp. 409-416.
@article{1d4fa0f15d0b4c9ab70dcb07db7b77c4,
title = "Novel spectral kurtosis technology for adaptive vibration condition monitoring of multi-stage gearboxes",
abstract = "In this paper, the novel wavelet spectral kurtosis (WSK) technique is applied for the early diagnosis of gear tooth faults. Two variants of the wavelet spectral kurtosis technique, called variable resolution WSK and constant resolution WSK, are considered for the diagnosis of pitting gear faults. The gear residual signal, obtained by filtering the gear mesh frequencies, is used as the input to the SK algorithm. The advantages of using the wavelet-based SK techniques when compared to classical Fourier transform (FT)-based SK is confirmed by estimating the toothwise Fisher's criterion of diagnostic features. The final diagnosis decision is made by a three-stage decision-making technique based on the weighted majority rule. The probability of the correct diagnosis is estimated for each SK technique for comparison. An experimental study is presented in detail to test the performance of the wavelet spectral kurtosis techniques and the decision-making technique.",
keywords = "Condition monitoring, Decision making, Diagnosis, Gear teeth, Higher order statistics, Wavelet analysis",
author = "L. Gelman and {Harish Chandra}, N. and R. Kurosz and F. Pellicano and M. Barbieri and A. Zippo",
year = "2016",
month = "8",
day = "1",
doi = "10.1784/insi.2016.58.8.409",
language = "English",
volume = "58",
pages = "409--416",
journal = "Insight: Non-Destructive Testing and Condition Monitoring",
issn = "1354-2575",
publisher = "British Institute of Non-Destructive Testing",
number = "8",

}

Novel spectral kurtosis technology for adaptive vibration condition monitoring of multi-stage gearboxes. / Gelman, L.; Harish Chandra, N.; Kurosz, R.; Pellicano, F.; Barbieri, M.; Zippo, A.

In: Insight: Non-Destructive Testing and Condition Monitoring, Vol. 58, No. 8, 01.08.2016, p. 409-416.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Novel spectral kurtosis technology for adaptive vibration condition monitoring of multi-stage gearboxes

AU - Gelman, L.

AU - Harish Chandra, N.

AU - Kurosz, R.

AU - Pellicano, F.

AU - Barbieri, M.

AU - Zippo, A.

PY - 2016/8/1

Y1 - 2016/8/1

N2 - In this paper, the novel wavelet spectral kurtosis (WSK) technique is applied for the early diagnosis of gear tooth faults. Two variants of the wavelet spectral kurtosis technique, called variable resolution WSK and constant resolution WSK, are considered for the diagnosis of pitting gear faults. The gear residual signal, obtained by filtering the gear mesh frequencies, is used as the input to the SK algorithm. The advantages of using the wavelet-based SK techniques when compared to classical Fourier transform (FT)-based SK is confirmed by estimating the toothwise Fisher's criterion of diagnostic features. The final diagnosis decision is made by a three-stage decision-making technique based on the weighted majority rule. The probability of the correct diagnosis is estimated for each SK technique for comparison. An experimental study is presented in detail to test the performance of the wavelet spectral kurtosis techniques and the decision-making technique.

AB - In this paper, the novel wavelet spectral kurtosis (WSK) technique is applied for the early diagnosis of gear tooth faults. Two variants of the wavelet spectral kurtosis technique, called variable resolution WSK and constant resolution WSK, are considered for the diagnosis of pitting gear faults. The gear residual signal, obtained by filtering the gear mesh frequencies, is used as the input to the SK algorithm. The advantages of using the wavelet-based SK techniques when compared to classical Fourier transform (FT)-based SK is confirmed by estimating the toothwise Fisher's criterion of diagnostic features. The final diagnosis decision is made by a three-stage decision-making technique based on the weighted majority rule. The probability of the correct diagnosis is estimated for each SK technique for comparison. An experimental study is presented in detail to test the performance of the wavelet spectral kurtosis techniques and the decision-making technique.

KW - Condition monitoring

KW - Decision making

KW - Diagnosis

KW - Gear teeth

KW - Higher order statistics

KW - Wavelet analysis

UR - http://www.scopus.com/inward/record.url?scp=84982189625&partnerID=8YFLogxK

U2 - 10.1784/insi.2016.58.8.409

DO - 10.1784/insi.2016.58.8.409

M3 - Article

VL - 58

SP - 409

EP - 416

JO - Insight: Non-Destructive Testing and Condition Monitoring

T2 - Insight: Non-Destructive Testing and Condition Monitoring

JF - Insight: Non-Destructive Testing and Condition Monitoring

SN - 1354-2575

IS - 8

ER -