Data-driven methods for vibration-based monitoring based on singular spectrum analysis

Irina Trendafilova, David Garcia Cava, Hussein Al-Bugharbee

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This chapter studies the application of data-driven methods and specifically principal component analysis (PCA) and singular spectrum analysis (SSA) for purposes of damage assessment in structures and machinery. In this study, data analysis methods PCA and SSA are applied to the measured vibration signals in order to extract information about the state of the structure/machinery and the presence of a fault in it. Two applications are offered, one for damage assessment on a wind turbine blade and another one for fault diagnosis in rolling element bearings. The results demonstrate strong capabilities of the investigated methodology for both structural damage detection and rolling element fault diagnosis. Eventually, a discussion about the capabilities of the studied methodology and the way forward regarding extending its capabilities and applications is offered.
LanguageEnglish
Title of host publicationVibration-Based Techniques for Damage Detection and Localization in Engineering Structures
EditorsAli Salehzadeh Nobari, M. H. Ferri Aliabadi
Place of PublicationLondon
Chapter2
Pages41-73
Number of pages32
DOIs
StatePublished - 31 Jul 2018

Publication series

NameComputational and Experimental Methods in Structures
PublisherWorld Scientific
Volume10
ISSN (Print)2044-9283

Fingerprint

Spectrum analysis
Principal component analysis
Failure analysis
Machinery
Monitoring
Bearings (structural)
Damage detection
Wind turbines
Turbomachine blades

Keywords

  • singular spectrum analysis
  • principal component analysis
  • outlier principle
  • wind turbine blade
  • structural monitoring

Cite this

Trendafilova, I., Garcia Cava, D., & Al-Bugharbee, H. (2018). Data-driven methods for vibration-based monitoring based on singular spectrum analysis. In A. S. Nobari, & M. H. F. Aliabadi (Eds.), Vibration-Based Techniques for Damage Detection and Localization in Engineering Structures (pp. 41-73). (Computational and Experimental Methods in Structures; Vol. 10). London. DOI: 10.1142/9781786344977_0002
Trendafilova, Irina ; Garcia Cava, David ; Al-Bugharbee, Hussein. / Data-driven methods for vibration-based monitoring based on singular spectrum analysis. Vibration-Based Techniques for Damage Detection and Localization in Engineering Structures. editor / Ali Salehzadeh Nobari ; M. H. Ferri Aliabadi. London, 2018. pp. 41-73 (Computational and Experimental Methods in Structures).
@inbook{676d623cafde49cd989f6f0378a46366,
title = "Data-driven methods for vibration-based monitoring based on singular spectrum analysis",
abstract = "This chapter studies the application of data-driven methods and specifically principal component analysis (PCA) and singular spectrum analysis (SSA) for purposes of damage assessment in structures and machinery. In this study, data analysis methods PCA and SSA are applied to the measured vibration signals in order to extract information about the state of the structure/machinery and the presence of a fault in it. Two applications are offered, one for damage assessment on a wind turbine blade and another one for fault diagnosis in rolling element bearings. The results demonstrate strong capabilities of the investigated methodology for both structural damage detection and rolling element fault diagnosis. Eventually, a discussion about the capabilities of the studied methodology and the way forward regarding extending its capabilities and applications is offered.",
keywords = "singular spectrum analysis, principal component analysis, outlier principle, wind turbine blade, structural monitoring",
author = "Irina Trendafilova and {Garcia Cava}, David and Hussein Al-Bugharbee",
year = "2018",
month = "7",
day = "31",
doi = "10.1142/9781786344977_0002",
language = "English",
isbn = "978-1-78634-496-0",
series = "Computational and Experimental Methods in Structures",
publisher = "World Scientific",
pages = "41--73",
editor = "Nobari, {Ali Salehzadeh} and Aliabadi, {M. H. Ferri}",
booktitle = "Vibration-Based Techniques for Damage Detection and Localization in Engineering Structures",

}

Trendafilova, I, Garcia Cava, D & Al-Bugharbee, H 2018, Data-driven methods for vibration-based monitoring based on singular spectrum analysis. in AS Nobari & MHF Aliabadi (eds), Vibration-Based Techniques for Damage Detection and Localization in Engineering Structures. Computational and Experimental Methods in Structures, vol. 10, London, pp. 41-73. DOI: 10.1142/9781786344977_0002

Data-driven methods for vibration-based monitoring based on singular spectrum analysis. / Trendafilova, Irina; Garcia Cava, David; Al-Bugharbee, Hussein.

Vibration-Based Techniques for Damage Detection and Localization in Engineering Structures. ed. / Ali Salehzadeh Nobari; M. H. Ferri Aliabadi. London, 2018. p. 41-73 (Computational and Experimental Methods in Structures; Vol. 10).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Data-driven methods for vibration-based monitoring based on singular spectrum analysis

AU - Trendafilova,Irina

AU - Garcia Cava,David

AU - Al-Bugharbee,Hussein

PY - 2018/7/31

Y1 - 2018/7/31

N2 - This chapter studies the application of data-driven methods and specifically principal component analysis (PCA) and singular spectrum analysis (SSA) for purposes of damage assessment in structures and machinery. In this study, data analysis methods PCA and SSA are applied to the measured vibration signals in order to extract information about the state of the structure/machinery and the presence of a fault in it. Two applications are offered, one for damage assessment on a wind turbine blade and another one for fault diagnosis in rolling element bearings. The results demonstrate strong capabilities of the investigated methodology for both structural damage detection and rolling element fault diagnosis. Eventually, a discussion about the capabilities of the studied methodology and the way forward regarding extending its capabilities and applications is offered.

AB - This chapter studies the application of data-driven methods and specifically principal component analysis (PCA) and singular spectrum analysis (SSA) for purposes of damage assessment in structures and machinery. In this study, data analysis methods PCA and SSA are applied to the measured vibration signals in order to extract information about the state of the structure/machinery and the presence of a fault in it. Two applications are offered, one for damage assessment on a wind turbine blade and another one for fault diagnosis in rolling element bearings. The results demonstrate strong capabilities of the investigated methodology for both structural damage detection and rolling element fault diagnosis. Eventually, a discussion about the capabilities of the studied methodology and the way forward regarding extending its capabilities and applications is offered.

KW - singular spectrum analysis

KW - principal component analysis

KW - outlier principle

KW - wind turbine blade

KW - structural monitoring

U2 - 10.1142/9781786344977_0002

DO - 10.1142/9781786344977_0002

M3 - Chapter

SN - 978-1-78634-496-0

T3 - Computational and Experimental Methods in Structures

SP - 41

EP - 73

BT - Vibration-Based Techniques for Damage Detection and Localization in Engineering Structures

CY - London

ER -

Trendafilova I, Garcia Cava D, Al-Bugharbee H. Data-driven methods for vibration-based monitoring based on singular spectrum analysis. In Nobari AS, Aliabadi MHF, editors, Vibration-Based Techniques for Damage Detection and Localization in Engineering Structures. London. 2018. p. 41-73. (Computational and Experimental Methods in Structures). Available from, DOI: 10.1142/9781786344977_0002