Abstract

Adaptive learning techniques have recently been considered for structural health monitoring applications due to their flexibility and effectiveness in addressing real-world challenges such as variability in the monitoring of environmental and operating conditions. In this paper, an active learning data selection procedure is proposed that adaptively selects the most informative measurements to include, from multiple available measurements, in estimating structural damage. This is important, since not all the measurements may provide useful information and could reduce performance when processed. Within the adaptive learning framework, the data selection problem is formulated to choose those measurements which are most representative of the diversity within a damage state. This is achieved by extracting time-frequency analysis based statistical similarity features from the measurements, and selecting uniformly distributed subsets to build representative reference sets. The utility of the proposed method is demonstrated by improvements in adaptive learning performance for the estimation of fatigue damage in an aluminum compact tension sample.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume7649
DOIs
StatePublished - 2010
EventNondestructive Characterization for Composite Materials, Aerospace Engineering, Civil Infrastructure, and Homeland Security 2010 - San Diego, CA, United States
Duration: Mar 8 2010Mar 11 2010

Other

OtherNondestructive Characterization for Composite Materials, Aerospace Engineering, Civil Infrastructure, and Homeland Security 2010
CountryUnited States
CitySan Diego, CA
Period3/8/103/11/10

Fingerprint

Active Learning
learning
Damage
Adaptive Learning
damage
Time-frequency Analysis
Fatigue Damage
structural health monitoring
Structural health monitoring
Selection Procedures
Fatigue damage
Health Monitoring
Aluminum
set theory
flexibility
estimating
Choose
Flexibility
Problem-Based Learning
Monitoring

Keywords

  • active data selection
  • adaptive learning
  • damage classification
  • discrepancy
  • matching pursuit decomposition
  • optimization
  • statistical similarity
  • structural health monitoring
  • time-frequency analysis

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Chakraborty, D., Kovvali, N., Papandreou-Suppappola, A., & Chattopadhyay, A. (2010). Active learning data selection for adaptive online structural damage estimation. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 7649). [764915] https://doi.org/10.1117/12.848891

Active learning data selection for adaptive online structural damage estimation. / Chakraborty, Debejyo; Kovvali, Narayan; Papandreou-Suppappola, Antonia; Chattopadhyay, Aditi.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7649 2010. 764915.

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

Chakraborty, D, Kovvali, N, Papandreou-Suppappola, A & Chattopadhyay, A 2010, Active learning data selection for adaptive online structural damage estimation. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 7649, 764915, Nondestructive Characterization for Composite Materials, Aerospace Engineering, Civil Infrastructure, and Homeland Security 2010, San Diego, CA, United States, 3/8/10. https://doi.org/10.1117/12.848891
Chakraborty D, Kovvali N, Papandreou-Suppappola A, Chattopadhyay A. Active learning data selection for adaptive online structural damage estimation. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7649. 2010. 764915 https://doi.org/10.1117/12.848891
Chakraborty, Debejyo ; Kovvali, Narayan ; Papandreou-Suppappola, Antonia ; Chattopadhyay, Aditi. / Active learning data selection for adaptive online structural damage estimation. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7649 2010.
@inproceedings{2090bda6efb445e386bc6623a31060bf,
title = "Active learning data selection for adaptive online structural damage estimation",
abstract = "Adaptive learning techniques have recently been considered for structural health monitoring applications due to their flexibility and effectiveness in addressing real-world challenges such as variability in the monitoring of environmental and operating conditions. In this paper, an active learning data selection procedure is proposed that adaptively selects the most informative measurements to include, from multiple available measurements, in estimating structural damage. This is important, since not all the measurements may provide useful information and could reduce performance when processed. Within the adaptive learning framework, the data selection problem is formulated to choose those measurements which are most representative of the diversity within a damage state. This is achieved by extracting time-frequency analysis based statistical similarity features from the measurements, and selecting uniformly distributed subsets to build representative reference sets. The utility of the proposed method is demonstrated by improvements in adaptive learning performance for the estimation of fatigue damage in an aluminum compact tension sample.",
keywords = "active data selection, adaptive learning, damage classification, discrepancy, matching pursuit decomposition, optimization, statistical similarity, structural health monitoring, time-frequency analysis",
author = "Debejyo Chakraborty and Narayan Kovvali and Antonia Papandreou-Suppappola and Aditi Chattopadhyay",
year = "2010",
doi = "10.1117/12.848891",
language = "English (US)",
isbn = "9780819480644",
volume = "7649",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Active learning data selection for adaptive online structural damage estimation

AU - Chakraborty, Debejyo

AU - Kovvali, Narayan

AU - Papandreou-Suppappola, Antonia

AU - Chattopadhyay, Aditi

PY - 2010

Y1 - 2010

N2 - Adaptive learning techniques have recently been considered for structural health monitoring applications due to their flexibility and effectiveness in addressing real-world challenges such as variability in the monitoring of environmental and operating conditions. In this paper, an active learning data selection procedure is proposed that adaptively selects the most informative measurements to include, from multiple available measurements, in estimating structural damage. This is important, since not all the measurements may provide useful information and could reduce performance when processed. Within the adaptive learning framework, the data selection problem is formulated to choose those measurements which are most representative of the diversity within a damage state. This is achieved by extracting time-frequency analysis based statistical similarity features from the measurements, and selecting uniformly distributed subsets to build representative reference sets. The utility of the proposed method is demonstrated by improvements in adaptive learning performance for the estimation of fatigue damage in an aluminum compact tension sample.

AB - Adaptive learning techniques have recently been considered for structural health monitoring applications due to their flexibility and effectiveness in addressing real-world challenges such as variability in the monitoring of environmental and operating conditions. In this paper, an active learning data selection procedure is proposed that adaptively selects the most informative measurements to include, from multiple available measurements, in estimating structural damage. This is important, since not all the measurements may provide useful information and could reduce performance when processed. Within the adaptive learning framework, the data selection problem is formulated to choose those measurements which are most representative of the diversity within a damage state. This is achieved by extracting time-frequency analysis based statistical similarity features from the measurements, and selecting uniformly distributed subsets to build representative reference sets. The utility of the proposed method is demonstrated by improvements in adaptive learning performance for the estimation of fatigue damage in an aluminum compact tension sample.

KW - active data selection

KW - adaptive learning

KW - damage classification

KW - discrepancy

KW - matching pursuit decomposition

KW - optimization

KW - statistical similarity

KW - structural health monitoring

KW - time-frequency analysis

UR - http://www.scopus.com/inward/record.url?scp=77953443630&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953443630&partnerID=8YFLogxK

U2 - 10.1117/12.848891

DO - 10.1117/12.848891

M3 - Conference contribution

SN - 9780819480644

VL - 7649

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

ER -