Binary tree SVM based framework for mining fatigue induced damage attributes in complex lug joints

Clyde K. Coelho, Santanu Das, Aditi Chattopadhyay

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

5 Citations (Scopus)

Abstract

Research is being conducted in damage diagnosis and prognosis to develop state awareness models and residual useful life estimates of aerospace structures. This work describes a methodology using Support Vector Machines (SVMs), organized in a binary tree structure to classify the extent of a growing crack in lug joints. A lug joint is a common aerospace 'hotspot' where fatigue damage is highly probable. The test specimen was instrumented with surface mounted piezoelectric transducers and then subjected to fatigue load until failure. A Matching Pursuit Decomposition (MPD) algorithm was used to preprocess the sensor data and extract the input vectors used in classification. The results of this classification scheme show that this type of architecture works well for categorizing fatigue induced damage (crack) in a computationally efficient manner. However, due to the nature of the overlap of the collected data patterns, a classifier at each node in the binary tree is limited by the performance of the classifier that is higher up in the tree.

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

lugs
Binary trees
Support vector machines
Classifiers
Fatigue of materials
classifiers
damage
Cracks
Piezoelectric transducers
Fatigue damage
cracks
prognosis
piezoelectric transducers
Decomposition
Sensors
methodology
decomposition
sensors
estimates

Keywords

  • Binary tree
  • Damage classification
  • Matching pursuit decomposition
  • Structural health monitoring
  • Support vector machines

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Coelho, C. K., Das, S., & Chattopadhyay, A. (2008). Binary tree SVM based framework for mining fatigue induced damage attributes in complex lug joints. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6926). [69260Q] https://doi.org/10.1117/12.776481

Binary tree SVM based framework for mining fatigue induced damage attributes in complex lug joints. / Coelho, Clyde K.; Das, Santanu; Chattopadhyay, Aditi.

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

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

Coelho, CK, Das, S & Chattopadhyay, A 2008, Binary tree SVM based framework for mining fatigue induced damage attributes in complex lug joints. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6926, 69260Q, Modeling, Signal Processing, and Control for Smart Structures 2008, San Diego, CA, United States, 3/10/08. https://doi.org/10.1117/12.776481
Coelho CK, Das S, Chattopadhyay A. Binary tree SVM based framework for mining fatigue induced damage attributes in complex lug joints. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6926. 2008. 69260Q https://doi.org/10.1117/12.776481
Coelho, Clyde K. ; Das, Santanu ; Chattopadhyay, Aditi. / Binary tree SVM based framework for mining fatigue induced damage attributes in complex lug joints. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6926 2008.
@inproceedings{e51329b209144593a14d80f36df09c22,
title = "Binary tree SVM based framework for mining fatigue induced damage attributes in complex lug joints",
abstract = "Research is being conducted in damage diagnosis and prognosis to develop state awareness models and residual useful life estimates of aerospace structures. This work describes a methodology using Support Vector Machines (SVMs), organized in a binary tree structure to classify the extent of a growing crack in lug joints. A lug joint is a common aerospace 'hotspot' where fatigue damage is highly probable. The test specimen was instrumented with surface mounted piezoelectric transducers and then subjected to fatigue load until failure. A Matching Pursuit Decomposition (MPD) algorithm was used to preprocess the sensor data and extract the input vectors used in classification. The results of this classification scheme show that this type of architecture works well for categorizing fatigue induced damage (crack) in a computationally efficient manner. However, due to the nature of the overlap of the collected data patterns, a classifier at each node in the binary tree is limited by the performance of the classifier that is higher up in the tree.",
keywords = "Binary tree, Damage classification, Matching pursuit decomposition, Structural health monitoring, Support vector machines",
author = "Coelho, {Clyde K.} and Santanu Das and Aditi Chattopadhyay",
year = "2008",
doi = "10.1117/12.776481",
language = "English (US)",
isbn = "9780819471123",
volume = "6926",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Binary tree SVM based framework for mining fatigue induced damage attributes in complex lug joints

AU - Coelho, Clyde K.

AU - Das, Santanu

AU - Chattopadhyay, Aditi

PY - 2008

Y1 - 2008

N2 - Research is being conducted in damage diagnosis and prognosis to develop state awareness models and residual useful life estimates of aerospace structures. This work describes a methodology using Support Vector Machines (SVMs), organized in a binary tree structure to classify the extent of a growing crack in lug joints. A lug joint is a common aerospace 'hotspot' where fatigue damage is highly probable. The test specimen was instrumented with surface mounted piezoelectric transducers and then subjected to fatigue load until failure. A Matching Pursuit Decomposition (MPD) algorithm was used to preprocess the sensor data and extract the input vectors used in classification. The results of this classification scheme show that this type of architecture works well for categorizing fatigue induced damage (crack) in a computationally efficient manner. However, due to the nature of the overlap of the collected data patterns, a classifier at each node in the binary tree is limited by the performance of the classifier that is higher up in the tree.

AB - Research is being conducted in damage diagnosis and prognosis to develop state awareness models and residual useful life estimates of aerospace structures. This work describes a methodology using Support Vector Machines (SVMs), organized in a binary tree structure to classify the extent of a growing crack in lug joints. A lug joint is a common aerospace 'hotspot' where fatigue damage is highly probable. The test specimen was instrumented with surface mounted piezoelectric transducers and then subjected to fatigue load until failure. A Matching Pursuit Decomposition (MPD) algorithm was used to preprocess the sensor data and extract the input vectors used in classification. The results of this classification scheme show that this type of architecture works well for categorizing fatigue induced damage (crack) in a computationally efficient manner. However, due to the nature of the overlap of the collected data patterns, a classifier at each node in the binary tree is limited by the performance of the classifier that is higher up in the tree.

KW - Binary tree

KW - Damage classification

KW - Matching pursuit decomposition

KW - Structural health monitoring

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=44349154887&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44349154887&partnerID=8YFLogxK

U2 - 10.1117/12.776481

DO - 10.1117/12.776481

M3 - Conference contribution

AN - SCOPUS:44349154887

SN - 9780819471123

VL - 6926

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

ER -