Sensor fusion and damage classification in composite materials

Wenfan Zhou, Whitney D. Reynolds, Albert Moncada, Narayan Kovvali, Aditi Chattopadhyay, Antonia Papandreou-Suppappola, Douglas Cochran

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

2 Citations (Scopus)

Abstract

We describe a statistical method for the classification of damage in complex structures. Our approach is based on a Bayesian framework using hidden Markov models (HMMs) to model time-frequency features extracted from structural data. We also propose two different methods for sensor fusion to combine information from multiple distributed sensors such that the overall classification performance is increased. The proposed approaches are applied to the classification and localization of delamination in a laminated composite plate. Results using both discrete and continuous observation density HMMs, together with the sensor fusion, are presented and discussed.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume6926
DOIs
StatePublished - 2008
EventModeling, Signal Processing, and Control for Smart Structures 2008 - San Diego, CA, United States
Duration: Mar 10 2008Mar 12 2008

Other

OtherModeling, Signal Processing, and Control for Smart Structures 2008
CountryUnited States
CitySan Diego, CA
Period3/10/083/12/08

Fingerprint

multisensor fusion
Fusion reactions
Hidden Markov models
damage
composite materials
Sensors
Composite materials
Laminated composites
Delamination
Statistical methods
sensors

Keywords

  • Damage detection and classification
  • Hidden Markov models
  • Sensor fusion
  • Structural health monitoring

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Zhou, W., Reynolds, W. D., Moncada, A., Kovvali, N., Chattopadhyay, A., Papandreou-Suppappola, A., & Cochran, D. (2008). Sensor fusion and damage classification in composite materials. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6926). [69260N] https://doi.org/10.1117/12.776608

Sensor fusion and damage classification in composite materials. / Zhou, Wenfan; Reynolds, Whitney D.; Moncada, Albert; Kovvali, Narayan; Chattopadhyay, Aditi; Papandreou-Suppappola, Antonia; Cochran, Douglas.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6926 2008. 69260N.

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

Zhou, W, Reynolds, WD, Moncada, A, Kovvali, N, Chattopadhyay, A, Papandreou-Suppappola, A & Cochran, D 2008, Sensor fusion and damage classification in composite materials. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6926, 69260N, Modeling, Signal Processing, and Control for Smart Structures 2008, San Diego, CA, United States, 3/10/08. https://doi.org/10.1117/12.776608
Zhou W, Reynolds WD, Moncada A, Kovvali N, Chattopadhyay A, Papandreou-Suppappola A et al. Sensor fusion and damage classification in composite materials. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6926. 2008. 69260N https://doi.org/10.1117/12.776608
Zhou, Wenfan ; Reynolds, Whitney D. ; Moncada, Albert ; Kovvali, Narayan ; Chattopadhyay, Aditi ; Papandreou-Suppappola, Antonia ; Cochran, Douglas. / Sensor fusion and damage classification in composite materials. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6926 2008.
@inproceedings{ac52d67f71ae4ed8b75178f0bfa56516,
title = "Sensor fusion and damage classification in composite materials",
abstract = "We describe a statistical method for the classification of damage in complex structures. Our approach is based on a Bayesian framework using hidden Markov models (HMMs) to model time-frequency features extracted from structural data. We also propose two different methods for sensor fusion to combine information from multiple distributed sensors such that the overall classification performance is increased. The proposed approaches are applied to the classification and localization of delamination in a laminated composite plate. Results using both discrete and continuous observation density HMMs, together with the sensor fusion, are presented and discussed.",
keywords = "Damage detection and classification, Hidden Markov models, Sensor fusion, Structural health monitoring",
author = "Wenfan Zhou and Reynolds, {Whitney D.} and Albert Moncada and Narayan Kovvali and Aditi Chattopadhyay and Antonia Papandreou-Suppappola and Douglas Cochran",
year = "2008",
doi = "10.1117/12.776608",
language = "English (US)",
isbn = "9780819471123",
volume = "6926",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Sensor fusion and damage classification in composite materials

AU - Zhou, Wenfan

AU - Reynolds, Whitney D.

AU - Moncada, Albert

AU - Kovvali, Narayan

AU - Chattopadhyay, Aditi

AU - Papandreou-Suppappola, Antonia

AU - Cochran, Douglas

PY - 2008

Y1 - 2008

N2 - We describe a statistical method for the classification of damage in complex structures. Our approach is based on a Bayesian framework using hidden Markov models (HMMs) to model time-frequency features extracted from structural data. We also propose two different methods for sensor fusion to combine information from multiple distributed sensors such that the overall classification performance is increased. The proposed approaches are applied to the classification and localization of delamination in a laminated composite plate. Results using both discrete and continuous observation density HMMs, together with the sensor fusion, are presented and discussed.

AB - We describe a statistical method for the classification of damage in complex structures. Our approach is based on a Bayesian framework using hidden Markov models (HMMs) to model time-frequency features extracted from structural data. We also propose two different methods for sensor fusion to combine information from multiple distributed sensors such that the overall classification performance is increased. The proposed approaches are applied to the classification and localization of delamination in a laminated composite plate. Results using both discrete and continuous observation density HMMs, together with the sensor fusion, are presented and discussed.

KW - Damage detection and classification

KW - Hidden Markov models

KW - Sensor fusion

KW - Structural health monitoring

UR - http://www.scopus.com/inward/record.url?scp=44449133242&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44449133242&partnerID=8YFLogxK

U2 - 10.1117/12.776608

DO - 10.1117/12.776608

M3 - Conference contribution

AN - SCOPUS:44449133242

SN - 9780819471123

VL - 6926

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -