Detection of incipient tooth defect in helical gears using multivariate statistics

N. Baydar, Q. Chen, A. Ball, U. Kruger

Research output: Contribution to journalArticle

66 Citations (Scopus)

Abstract

Multivariate statistical techniques have been successfully used for monitoring process plants and their associated instrumentation. These techniques effectively detect disturbances related to individual measurement sources and consequently provide diagnostic information about the process input. This paper investigates and explores the use of multivariate statistical techniques in a two-stage industrial helical gearbox, to detect localised faults by using vibration signals. The vibration signals, obtained from a number of sensors, are synchronously averaged and then the multivariate statistics, based on principal components analysis, is employed to form a normal (reference) condition model. Fault conditions, which are deviations from a reference model, are detected by monitoring Q- and T2-statistics. Normal operating regions or confidence bounds, based on kernel density estimation (KDE) is introduced to capture the faulty conditions in the gearbox. It is found that Q- and T2-statistics based on PCA can detect incipient local faults at an early stage. The confidence regions, based on KDE can also reveal the growing faults in the gearbox.

LanguageEnglish
Pages303-321
Number of pages19
JournalMechanical Systems and Signal Processing
Volume15
Issue number2
DOIs
Publication statusPublished - 1 Mar 2001
Externally publishedYes

Fingerprint

Helical gears
Gear teeth
Statistics
Defects
Process monitoring
Principal component analysis
Monitoring
Sensors

Cite this

@article{d5d32305dd314750a05d29be72100164,
title = "Detection of incipient tooth defect in helical gears using multivariate statistics",
abstract = "Multivariate statistical techniques have been successfully used for monitoring process plants and their associated instrumentation. These techniques effectively detect disturbances related to individual measurement sources and consequently provide diagnostic information about the process input. This paper investigates and explores the use of multivariate statistical techniques in a two-stage industrial helical gearbox, to detect localised faults by using vibration signals. The vibration signals, obtained from a number of sensors, are synchronously averaged and then the multivariate statistics, based on principal components analysis, is employed to form a normal (reference) condition model. Fault conditions, which are deviations from a reference model, are detected by monitoring Q- and T2-statistics. Normal operating regions or confidence bounds, based on kernel density estimation (KDE) is introduced to capture the faulty conditions in the gearbox. It is found that Q- and T2-statistics based on PCA can detect incipient local faults at an early stage. The confidence regions, based on KDE can also reveal the growing faults in the gearbox.",
author = "N. Baydar and Q. Chen and A. Ball and U. Kruger",
year = "2001",
month = "3",
day = "1",
doi = "10.1006/mssp.2000.1315",
language = "English",
volume = "15",
pages = "303--321",
journal = "Mechanical Systems and Signal Processing",
issn = "0888-3270",
publisher = "Academic Press Inc.",
number = "2",

}

Detection of incipient tooth defect in helical gears using multivariate statistics. / Baydar, N.; Chen, Q.; Ball, A.; Kruger, U.

In: Mechanical Systems and Signal Processing, Vol. 15, No. 2, 01.03.2001, p. 303-321.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Detection of incipient tooth defect in helical gears using multivariate statistics

AU - Baydar, N.

AU - Chen, Q.

AU - Ball, A.

AU - Kruger, U.

PY - 2001/3/1

Y1 - 2001/3/1

N2 - Multivariate statistical techniques have been successfully used for monitoring process plants and their associated instrumentation. These techniques effectively detect disturbances related to individual measurement sources and consequently provide diagnostic information about the process input. This paper investigates and explores the use of multivariate statistical techniques in a two-stage industrial helical gearbox, to detect localised faults by using vibration signals. The vibration signals, obtained from a number of sensors, are synchronously averaged and then the multivariate statistics, based on principal components analysis, is employed to form a normal (reference) condition model. Fault conditions, which are deviations from a reference model, are detected by monitoring Q- and T2-statistics. Normal operating regions or confidence bounds, based on kernel density estimation (KDE) is introduced to capture the faulty conditions in the gearbox. It is found that Q- and T2-statistics based on PCA can detect incipient local faults at an early stage. The confidence regions, based on KDE can also reveal the growing faults in the gearbox.

AB - Multivariate statistical techniques have been successfully used for monitoring process plants and their associated instrumentation. These techniques effectively detect disturbances related to individual measurement sources and consequently provide diagnostic information about the process input. This paper investigates and explores the use of multivariate statistical techniques in a two-stage industrial helical gearbox, to detect localised faults by using vibration signals. The vibration signals, obtained from a number of sensors, are synchronously averaged and then the multivariate statistics, based on principal components analysis, is employed to form a normal (reference) condition model. Fault conditions, which are deviations from a reference model, are detected by monitoring Q- and T2-statistics. Normal operating regions or confidence bounds, based on kernel density estimation (KDE) is introduced to capture the faulty conditions in the gearbox. It is found that Q- and T2-statistics based on PCA can detect incipient local faults at an early stage. The confidence regions, based on KDE can also reveal the growing faults in the gearbox.

UR - http://www.scopus.com/inward/record.url?scp=0035271127&partnerID=8YFLogxK

U2 - 10.1006/mssp.2000.1315

DO - 10.1006/mssp.2000.1315

M3 - Article

VL - 15

SP - 303

EP - 321

JO - Mechanical Systems and Signal Processing

T2 - Mechanical Systems and Signal Processing

JF - Mechanical Systems and Signal Processing

SN - 0888-3270

IS - 2

ER -