Classification of damage signatures in composite plates using one-class SVMs

Santanu Das, Ashok N. Srivastava, Aditi Chattopadhyay

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

19 Citations (Scopus)

Abstract

Damage characterization through wave propagation and scattering is of considerable interest to many non-destructive evaluation techniques. For fiber-reinforced composites, complex waves can be generated during the tests due to the non-homogeneous and anisotropic nature of the material when compared to isotropic materials. Additional complexities are introduced due to the presence of the damage and thus results in difficulty to characterize these defects. The inability to detect damage in composite structures limits their use in practice. A major task of structural health monitoring is to identify and characterize the existing defects or defect evolution through the interactions between structural features and multidisciplinary physical phenomena. In a wave-based approach to addressing this problem, the presence of damage is characterized by the changes in the signature of the resultant wave that propagates through the structure. In order to measure and characterize the wave propagation, we use the response of the surface-mounted piezoelectric transducers as input to an advanced machine-learning based classifier known as a Support Vector Machine.123

Original languageEnglish (US)
Title of host publicationIEEE Aerospace Conference Proceedings
DOIs
StatePublished - 2007
Event2007 IEEE Aerospace Conference - Big Sky, MT, United States
Duration: Mar 3 2007Mar 10 2007

Other

Other2007 IEEE Aerospace Conference
CountryUnited States
CityBig Sky, MT
Period3/3/073/10/07

Fingerprint

Wave propagation
Defects
Composite materials
Piezoelectric transducers
Structural health monitoring
Composite structures
Learning systems
Classifiers
Scattering
Fibers

ASJC Scopus subject areas

  • Aerospace Engineering

Cite this

Classification of damage signatures in composite plates using one-class SVMs. / Das, Santanu; Srivastava, Ashok N.; Chattopadhyay, Aditi.

IEEE Aerospace Conference Proceedings. 2007. 4161669.

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

Das, S, Srivastava, AN & Chattopadhyay, A 2007, Classification of damage signatures in composite plates using one-class SVMs. in IEEE Aerospace Conference Proceedings., 4161669, 2007 IEEE Aerospace Conference, Big Sky, MT, United States, 3/3/07. https://doi.org/10.1109/AERO.2007.352912
Das, Santanu ; Srivastava, Ashok N. ; Chattopadhyay, Aditi. / Classification of damage signatures in composite plates using one-class SVMs. IEEE Aerospace Conference Proceedings. 2007.
@inproceedings{ffebae66b0524807bf0645fba2c5282c,
title = "Classification of damage signatures in composite plates using one-class SVMs",
abstract = "Damage characterization through wave propagation and scattering is of considerable interest to many non-destructive evaluation techniques. For fiber-reinforced composites, complex waves can be generated during the tests due to the non-homogeneous and anisotropic nature of the material when compared to isotropic materials. Additional complexities are introduced due to the presence of the damage and thus results in difficulty to characterize these defects. The inability to detect damage in composite structures limits their use in practice. A major task of structural health monitoring is to identify and characterize the existing defects or defect evolution through the interactions between structural features and multidisciplinary physical phenomena. In a wave-based approach to addressing this problem, the presence of damage is characterized by the changes in the signature of the resultant wave that propagates through the structure. In order to measure and characterize the wave propagation, we use the response of the surface-mounted piezoelectric transducers as input to an advanced machine-learning based classifier known as a Support Vector Machine.123",
author = "Santanu Das and Srivastava, {Ashok N.} and Aditi Chattopadhyay",
year = "2007",
doi = "10.1109/AERO.2007.352912",
language = "English (US)",
isbn = "1424405254",
booktitle = "IEEE Aerospace Conference Proceedings",

}

TY - GEN

T1 - Classification of damage signatures in composite plates using one-class SVMs

AU - Das, Santanu

AU - Srivastava, Ashok N.

AU - Chattopadhyay, Aditi

PY - 2007

Y1 - 2007

N2 - Damage characterization through wave propagation and scattering is of considerable interest to many non-destructive evaluation techniques. For fiber-reinforced composites, complex waves can be generated during the tests due to the non-homogeneous and anisotropic nature of the material when compared to isotropic materials. Additional complexities are introduced due to the presence of the damage and thus results in difficulty to characterize these defects. The inability to detect damage in composite structures limits their use in practice. A major task of structural health monitoring is to identify and characterize the existing defects or defect evolution through the interactions between structural features and multidisciplinary physical phenomena. In a wave-based approach to addressing this problem, the presence of damage is characterized by the changes in the signature of the resultant wave that propagates through the structure. In order to measure and characterize the wave propagation, we use the response of the surface-mounted piezoelectric transducers as input to an advanced machine-learning based classifier known as a Support Vector Machine.123

AB - Damage characterization through wave propagation and scattering is of considerable interest to many non-destructive evaluation techniques. For fiber-reinforced composites, complex waves can be generated during the tests due to the non-homogeneous and anisotropic nature of the material when compared to isotropic materials. Additional complexities are introduced due to the presence of the damage and thus results in difficulty to characterize these defects. The inability to detect damage in composite structures limits their use in practice. A major task of structural health monitoring is to identify and characterize the existing defects or defect evolution through the interactions between structural features and multidisciplinary physical phenomena. In a wave-based approach to addressing this problem, the presence of damage is characterized by the changes in the signature of the resultant wave that propagates through the structure. In order to measure and characterize the wave propagation, we use the response of the surface-mounted piezoelectric transducers as input to an advanced machine-learning based classifier known as a Support Vector Machine.123

UR - http://www.scopus.com/inward/record.url?scp=34548775773&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548775773&partnerID=8YFLogxK

U2 - 10.1109/AERO.2007.352912

DO - 10.1109/AERO.2007.352912

M3 - Conference contribution

AN - SCOPUS:34548775773

SN - 1424405254

SN - 9781424405251

BT - IEEE Aerospace Conference Proceedings

ER -