Damage detection in structural health monitoring using kernel PLS based GLR

Marwa Chaabane, Majdi Mansouri, Hazem Nounou, Mohamed Nounou, Mohamed Ben Slima, Ahmed Ben Hamida

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

The objective of this paper is to extend the applicability of the GLR method to a wide range of practical systems. Most real systems are nonlinear, multivariate, and are best represented by input-output type of models. Kernel partial least squares (KPLS) models have been widely used to represent such systems. Therefore, in this paper, kernel PLS-based GLR method will be utilized in practice to improve damage detection in Structural Health Monitoring (SHM). The developed kernel PLS-based GLR technique combines the benefits of the multivariate input-output kernel PLS model and the statistical fault detection GLR statistic which showed performance in the cases where process models are not available. GLR is a well-known statistical detection method that relies on maximizing the detection probability for a given false alarm rate. To calculate the kernel PLS model, we use the data collected from the complex 3DOF spring-mass-dashpot system. The simulation results show improved performance of kernel PLS-based GLR in damage detection compared to the classical kernel PLS method.

Original languageEnglish
Title of host publicationProceedings - 3rd International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538605516
DOIs
Publication statusPublished - 19 Oct 2017
Event3rd International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2017 - Fez, Morocco
Duration: 22 May 201724 May 2017

Other

Other3rd International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2017
CountryMorocco
CityFez
Period22/5/1724/5/17

Fingerprint

Damage detection
Structural health monitoring
Fault detection
Nonlinear systems
Statistics

Keywords

  • Damage Detection
  • Generalized Likelihood Ratio
  • Kernel Partial Least Squares
  • Structural Health Monitoring

ASJC Scopus subject areas

  • Signal Processing

Cite this

Chaabane, M., Mansouri, M., Nounou, H., Nounou, M., Ben Slima, M., & Ben Hamida, A. (2017). Damage detection in structural health monitoring using kernel PLS based GLR. In Proceedings - 3rd International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2017 [8075555] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ATSIP.2017.8075555

Damage detection in structural health monitoring using kernel PLS based GLR. / Chaabane, Marwa; Mansouri, Majdi; Nounou, Hazem; Nounou, Mohamed; Ben Slima, Mohamed; Ben Hamida, Ahmed.

Proceedings - 3rd International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 8075555.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chaabane, M, Mansouri, M, Nounou, H, Nounou, M, Ben Slima, M & Ben Hamida, A 2017, Damage detection in structural health monitoring using kernel PLS based GLR. in Proceedings - 3rd International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2017., 8075555, Institute of Electrical and Electronics Engineers Inc., 3rd International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2017, Fez, Morocco, 22/5/17. https://doi.org/10.1109/ATSIP.2017.8075555
Chaabane M, Mansouri M, Nounou H, Nounou M, Ben Slima M, Ben Hamida A. Damage detection in structural health monitoring using kernel PLS based GLR. In Proceedings - 3rd International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2017. Institute of Electrical and Electronics Engineers Inc. 2017. 8075555 https://doi.org/10.1109/ATSIP.2017.8075555
Chaabane, Marwa ; Mansouri, Majdi ; Nounou, Hazem ; Nounou, Mohamed ; Ben Slima, Mohamed ; Ben Hamida, Ahmed. / Damage detection in structural health monitoring using kernel PLS based GLR. Proceedings - 3rd International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2017. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{12b2ddd9f27b4f609e506ca1c3be9d4c,
title = "Damage detection in structural health monitoring using kernel PLS based GLR",
abstract = "The objective of this paper is to extend the applicability of the GLR method to a wide range of practical systems. Most real systems are nonlinear, multivariate, and are best represented by input-output type of models. Kernel partial least squares (KPLS) models have been widely used to represent such systems. Therefore, in this paper, kernel PLS-based GLR method will be utilized in practice to improve damage detection in Structural Health Monitoring (SHM). The developed kernel PLS-based GLR technique combines the benefits of the multivariate input-output kernel PLS model and the statistical fault detection GLR statistic which showed performance in the cases where process models are not available. GLR is a well-known statistical detection method that relies on maximizing the detection probability for a given false alarm rate. To calculate the kernel PLS model, we use the data collected from the complex 3DOF spring-mass-dashpot system. The simulation results show improved performance of kernel PLS-based GLR in damage detection compared to the classical kernel PLS method.",
keywords = "Damage Detection, Generalized Likelihood Ratio, Kernel Partial Least Squares, Structural Health Monitoring",
author = "Marwa Chaabane and Majdi Mansouri and Hazem Nounou and Mohamed Nounou and {Ben Slima}, Mohamed and {Ben Hamida}, Ahmed",
year = "2017",
month = "10",
day = "19",
doi = "10.1109/ATSIP.2017.8075555",
language = "English",
booktitle = "Proceedings - 3rd International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Damage detection in structural health monitoring using kernel PLS based GLR

AU - Chaabane, Marwa

AU - Mansouri, Majdi

AU - Nounou, Hazem

AU - Nounou, Mohamed

AU - Ben Slima, Mohamed

AU - Ben Hamida, Ahmed

PY - 2017/10/19

Y1 - 2017/10/19

N2 - The objective of this paper is to extend the applicability of the GLR method to a wide range of practical systems. Most real systems are nonlinear, multivariate, and are best represented by input-output type of models. Kernel partial least squares (KPLS) models have been widely used to represent such systems. Therefore, in this paper, kernel PLS-based GLR method will be utilized in practice to improve damage detection in Structural Health Monitoring (SHM). The developed kernel PLS-based GLR technique combines the benefits of the multivariate input-output kernel PLS model and the statistical fault detection GLR statistic which showed performance in the cases where process models are not available. GLR is a well-known statistical detection method that relies on maximizing the detection probability for a given false alarm rate. To calculate the kernel PLS model, we use the data collected from the complex 3DOF spring-mass-dashpot system. The simulation results show improved performance of kernel PLS-based GLR in damage detection compared to the classical kernel PLS method.

AB - The objective of this paper is to extend the applicability of the GLR method to a wide range of practical systems. Most real systems are nonlinear, multivariate, and are best represented by input-output type of models. Kernel partial least squares (KPLS) models have been widely used to represent such systems. Therefore, in this paper, kernel PLS-based GLR method will be utilized in practice to improve damage detection in Structural Health Monitoring (SHM). The developed kernel PLS-based GLR technique combines the benefits of the multivariate input-output kernel PLS model and the statistical fault detection GLR statistic which showed performance in the cases where process models are not available. GLR is a well-known statistical detection method that relies on maximizing the detection probability for a given false alarm rate. To calculate the kernel PLS model, we use the data collected from the complex 3DOF spring-mass-dashpot system. The simulation results show improved performance of kernel PLS-based GLR in damage detection compared to the classical kernel PLS method.

KW - Damage Detection

KW - Generalized Likelihood Ratio

KW - Kernel Partial Least Squares

KW - Structural Health Monitoring

UR - http://www.scopus.com/inward/record.url?scp=85035327077&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035327077&partnerID=8YFLogxK

U2 - 10.1109/ATSIP.2017.8075555

DO - 10.1109/ATSIP.2017.8075555

M3 - Conference contribution

AN - SCOPUS:85035327077

BT - Proceedings - 3rd International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -