Damage classification for structural health monitoring using time-frequency feature extraction and continuous hidden Markov models

W. Zhou, D. Chakraborty, N. Kovvali, Antonia Papandreou-Suppappola, Douglas Cochran, Aditi Chattopadhyay

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

15 Citations (Scopus)

Abstract

We propose an algorithm for the classification of structural damage based on the use of the continuous hidden Markov modeling (HMM) technique. Our approach employs HMMs to model time-frequency damage features extracted from structural data using the matching pursuit decomposition algorithm. We investigate modeling with continuous observation-density HMMs and discuss the trade-offs involved as compared to the discrete HMM case. A variational Bayesian method is employed to automatically estimate the HMM state number and adapt the classifier for real-time use. We present results that classify structural and material (fatigue) damage in a boltedjoint structure.

Original languageEnglish (US)
Title of host publicationConference Record - Asilomar Conference on Signals, Systems and Computers
Pages848-852
Number of pages5
DOIs
StatePublished - 2007
Event41st Asilomar Conference on Signals, Systems and Computers, ACSSC - Pacific Grove, CA, United States
Duration: Nov 4 2007Nov 7 2007

Other

Other41st Asilomar Conference on Signals, Systems and Computers, ACSSC
CountryUnited States
CityPacific Grove, CA
Period11/4/0711/7/07

Fingerprint

Structural health monitoring
Hidden Markov models
Feature extraction
Fatigue damage
Classifiers
Fatigue of materials
Decomposition

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Zhou, W., Chakraborty, D., Kovvali, N., Papandreou-Suppappola, A., Cochran, D., & Chattopadhyay, A. (2007). Damage classification for structural health monitoring using time-frequency feature extraction and continuous hidden Markov models. In Conference Record - Asilomar Conference on Signals, Systems and Computers (pp. 848-852). [4487337] https://doi.org/10.1109/ACSSC.2007.4487337

Damage classification for structural health monitoring using time-frequency feature extraction and continuous hidden Markov models. / Zhou, W.; Chakraborty, D.; Kovvali, N.; Papandreou-Suppappola, Antonia; Cochran, Douglas; Chattopadhyay, Aditi.

Conference Record - Asilomar Conference on Signals, Systems and Computers. 2007. p. 848-852 4487337.

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

Zhou, W, Chakraborty, D, Kovvali, N, Papandreou-Suppappola, A, Cochran, D & Chattopadhyay, A 2007, Damage classification for structural health monitoring using time-frequency feature extraction and continuous hidden Markov models. in Conference Record - Asilomar Conference on Signals, Systems and Computers., 4487337, pp. 848-852, 41st Asilomar Conference on Signals, Systems and Computers, ACSSC, Pacific Grove, CA, United States, 11/4/07. https://doi.org/10.1109/ACSSC.2007.4487337
Zhou W, Chakraborty D, Kovvali N, Papandreou-Suppappola A, Cochran D, Chattopadhyay A. Damage classification for structural health monitoring using time-frequency feature extraction and continuous hidden Markov models. In Conference Record - Asilomar Conference on Signals, Systems and Computers. 2007. p. 848-852. 4487337 https://doi.org/10.1109/ACSSC.2007.4487337
Zhou, W. ; Chakraborty, D. ; Kovvali, N. ; Papandreou-Suppappola, Antonia ; Cochran, Douglas ; Chattopadhyay, Aditi. / Damage classification for structural health monitoring using time-frequency feature extraction and continuous hidden Markov models. Conference Record - Asilomar Conference on Signals, Systems and Computers. 2007. pp. 848-852
@inproceedings{9ee29f77b49743ae89be02804353e872,
title = "Damage classification for structural health monitoring using time-frequency feature extraction and continuous hidden Markov models",
abstract = "We propose an algorithm for the classification of structural damage based on the use of the continuous hidden Markov modeling (HMM) technique. Our approach employs HMMs to model time-frequency damage features extracted from structural data using the matching pursuit decomposition algorithm. We investigate modeling with continuous observation-density HMMs and discuss the trade-offs involved as compared to the discrete HMM case. A variational Bayesian method is employed to automatically estimate the HMM state number and adapt the classifier for real-time use. We present results that classify structural and material (fatigue) damage in a boltedjoint structure.",
author = "W. Zhou and D. Chakraborty and N. Kovvali and Antonia Papandreou-Suppappola and Douglas Cochran and Aditi Chattopadhyay",
year = "2007",
doi = "10.1109/ACSSC.2007.4487337",
language = "English (US)",
isbn = "9781424421107",
pages = "848--852",
booktitle = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

}

TY - GEN

T1 - Damage classification for structural health monitoring using time-frequency feature extraction and continuous hidden Markov models

AU - Zhou, W.

AU - Chakraborty, D.

AU - Kovvali, N.

AU - Papandreou-Suppappola, Antonia

AU - Cochran, Douglas

AU - Chattopadhyay, Aditi

PY - 2007

Y1 - 2007

N2 - We propose an algorithm for the classification of structural damage based on the use of the continuous hidden Markov modeling (HMM) technique. Our approach employs HMMs to model time-frequency damage features extracted from structural data using the matching pursuit decomposition algorithm. We investigate modeling with continuous observation-density HMMs and discuss the trade-offs involved as compared to the discrete HMM case. A variational Bayesian method is employed to automatically estimate the HMM state number and adapt the classifier for real-time use. We present results that classify structural and material (fatigue) damage in a boltedjoint structure.

AB - We propose an algorithm for the classification of structural damage based on the use of the continuous hidden Markov modeling (HMM) technique. Our approach employs HMMs to model time-frequency damage features extracted from structural data using the matching pursuit decomposition algorithm. We investigate modeling with continuous observation-density HMMs and discuss the trade-offs involved as compared to the discrete HMM case. A variational Bayesian method is employed to automatically estimate the HMM state number and adapt the classifier for real-time use. We present results that classify structural and material (fatigue) damage in a boltedjoint structure.

UR - http://www.scopus.com/inward/record.url?scp=50249118247&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50249118247&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2007.4487337

DO - 10.1109/ACSSC.2007.4487337

M3 - Conference contribution

AN - SCOPUS:50249118247

SN - 9781424421107

SP - 848

EP - 852

BT - Conference Record - Asilomar Conference on Signals, Systems and Computers

ER -