Abstract

A key challenge in real-world structural health monitoring (SHM) is diversity of damage phenomena and variability in environmental and operational conditions. Conventional learning techniques, while adequate for moderately complex inference tasks, can be limiting in highly complex and rapidly changing environments, especially when insufficient data is available. We present an adaptive learning methodology where stochastic models continuously evolve with the time-varying environment and Dirichlet process mixture models are utilized to self-adapt to structure within the data. Coupled with appropriate physics-based phenomenology, the approach provides an adaptive and effective framework for online SHM. The proposed technique is demonstrated for the detection of progressive fatigue damage in a metallic structure under variable-amplitude loading.

Original languageEnglish (US)
Title of host publicationConference Record - Asilomar Conference on Signals, Systems and Computers
Pages1678-1682
Number of pages5
DOIs
StatePublished - 2009
Event43rd Asilomar Conference on Signals, Systems and Computers - Pacific Grove, CA, United States
Duration: Nov 1 2009Nov 4 2009

Other

Other43rd Asilomar Conference on Signals, Systems and Computers
CountryUnited States
CityPacific Grove, CA
Period11/1/0911/4/09

Fingerprint

Structural health monitoring
Fatigue damage
Stochastic models
Physics

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Chakraborty, D., Kovvali, N., Zhang, J. J., Papandreou-Suppappola, A., & Chattopadhyay, A. (2009). Adaptive learning for damage classification in structural health monitoring. In Conference Record - Asilomar Conference on Signals, Systems and Computers (pp. 1678-1682). [5469782] https://doi.org/10.1109/ACSSC.2009.5469782

Adaptive learning for damage classification in structural health monitoring. / Chakraborty, D.; Kovvali, N.; Zhang, J. J.; Papandreou-Suppappola, Antonia; Chattopadhyay, Aditi.

Conference Record - Asilomar Conference on Signals, Systems and Computers. 2009. p. 1678-1682 5469782.

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

Chakraborty, D, Kovvali, N, Zhang, JJ, Papandreou-Suppappola, A & Chattopadhyay, A 2009, Adaptive learning for damage classification in structural health monitoring. in Conference Record - Asilomar Conference on Signals, Systems and Computers., 5469782, pp. 1678-1682, 43rd Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, United States, 11/1/09. https://doi.org/10.1109/ACSSC.2009.5469782
Chakraborty D, Kovvali N, Zhang JJ, Papandreou-Suppappola A, Chattopadhyay A. Adaptive learning for damage classification in structural health monitoring. In Conference Record - Asilomar Conference on Signals, Systems and Computers. 2009. p. 1678-1682. 5469782 https://doi.org/10.1109/ACSSC.2009.5469782
Chakraborty, D. ; Kovvali, N. ; Zhang, J. J. ; Papandreou-Suppappola, Antonia ; Chattopadhyay, Aditi. / Adaptive learning for damage classification in structural health monitoring. Conference Record - Asilomar Conference on Signals, Systems and Computers. 2009. pp. 1678-1682
@inproceedings{c3579de27faf427087e02fbda8007cba,
title = "Adaptive learning for damage classification in structural health monitoring",
abstract = "A key challenge in real-world structural health monitoring (SHM) is diversity of damage phenomena and variability in environmental and operational conditions. Conventional learning techniques, while adequate for moderately complex inference tasks, can be limiting in highly complex and rapidly changing environments, especially when insufficient data is available. We present an adaptive learning methodology where stochastic models continuously evolve with the time-varying environment and Dirichlet process mixture models are utilized to self-adapt to structure within the data. Coupled with appropriate physics-based phenomenology, the approach provides an adaptive and effective framework for online SHM. The proposed technique is demonstrated for the detection of progressive fatigue damage in a metallic structure under variable-amplitude loading.",
author = "D. Chakraborty and N. Kovvali and Zhang, {J. J.} and Antonia Papandreou-Suppappola and Aditi Chattopadhyay",
year = "2009",
doi = "10.1109/ACSSC.2009.5469782",
language = "English (US)",
isbn = "9781424458271",
pages = "1678--1682",
booktitle = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

}

TY - GEN

T1 - Adaptive learning for damage classification in structural health monitoring

AU - Chakraborty, D.

AU - Kovvali, N.

AU - Zhang, J. J.

AU - Papandreou-Suppappola, Antonia

AU - Chattopadhyay, Aditi

PY - 2009

Y1 - 2009

N2 - A key challenge in real-world structural health monitoring (SHM) is diversity of damage phenomena and variability in environmental and operational conditions. Conventional learning techniques, while adequate for moderately complex inference tasks, can be limiting in highly complex and rapidly changing environments, especially when insufficient data is available. We present an adaptive learning methodology where stochastic models continuously evolve with the time-varying environment and Dirichlet process mixture models are utilized to self-adapt to structure within the data. Coupled with appropriate physics-based phenomenology, the approach provides an adaptive and effective framework for online SHM. The proposed technique is demonstrated for the detection of progressive fatigue damage in a metallic structure under variable-amplitude loading.

AB - A key challenge in real-world structural health monitoring (SHM) is diversity of damage phenomena and variability in environmental and operational conditions. Conventional learning techniques, while adequate for moderately complex inference tasks, can be limiting in highly complex and rapidly changing environments, especially when insufficient data is available. We present an adaptive learning methodology where stochastic models continuously evolve with the time-varying environment and Dirichlet process mixture models are utilized to self-adapt to structure within the data. Coupled with appropriate physics-based phenomenology, the approach provides an adaptive and effective framework for online SHM. The proposed technique is demonstrated for the detection of progressive fatigue damage in a metallic structure under variable-amplitude loading.

UR - http://www.scopus.com/inward/record.url?scp=77953865222&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953865222&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2009.5469782

DO - 10.1109/ACSSC.2009.5469782

M3 - Conference contribution

SN - 9781424458271

SP - 1678

EP - 1682

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

ER -