A hierarchical classification scheme for computationally efficient damage classification

C. K. Coelho, S. Das, Aditi Chattopadhyay

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

This article presents a methodology for data mining of sensor signals in a structural health monitoring (SHM) framework for damage classification using a machine-learning-based approach called support vector machines (SVMs). A hierarchical decision tree structure is constructed for damage classification and experiments were conducted on metallic and composite test specimens with surface mounted piezoelectric transducers. Damage was induced in the specimens by fatigue, impact, and tensile loading; in addition, specimens with seeded delaminations were also considered. Data were collected from the surface mounted sensors at different severities of induced damage. A matching pursuit decomposition (MPD) algorithm was used as a feature extraction technique to preprocess the sensor data and extract the input vectors used in classification. Using this binary tree framework, the computational intensity of each successive classifier is reduced and the efficiency of the algorithm as a whole is increased. The results obtained using this classification show that this type of architecture works well for large data sets because a reduced number of comparisons are required. Due to the hierarchical set-up of the classifiers, performance of the classifier as a whole is heavily dependent on the performance of the classifier at higher levels in the classification tree.

Original languageEnglish (US)
Pages (from-to)497-505
Number of pages9
JournalProceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering
Volume223
Issue number5
DOIs
StatePublished - Aug 1 2009

Fingerprint

Classifiers
Sensors
Binary trees
Piezoelectric transducers
Structural health monitoring
Decision trees
Delamination
Support vector machines
Data mining
Learning systems
Feature extraction
Fatigue of materials
Decomposition
Composite materials
Experiments

Keywords

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

ASJC Scopus subject areas

  • Aerospace Engineering
  • Mechanical Engineering

Cite this

@article{140f2df0a3f84fcda7c7c95f62e81665,
title = "A hierarchical classification scheme for computationally efficient damage classification",
abstract = "This article presents a methodology for data mining of sensor signals in a structural health monitoring (SHM) framework for damage classification using a machine-learning-based approach called support vector machines (SVMs). A hierarchical decision tree structure is constructed for damage classification and experiments were conducted on metallic and composite test specimens with surface mounted piezoelectric transducers. Damage was induced in the specimens by fatigue, impact, and tensile loading; in addition, specimens with seeded delaminations were also considered. Data were collected from the surface mounted sensors at different severities of induced damage. A matching pursuit decomposition (MPD) algorithm was used as a feature extraction technique to preprocess the sensor data and extract the input vectors used in classification. Using this binary tree framework, the computational intensity of each successive classifier is reduced and the efficiency of the algorithm as a whole is increased. The results obtained using this classification show that this type of architecture works well for large data sets because a reduced number of comparisons are required. Due to the hierarchical set-up of the classifiers, performance of the classifier as a whole is heavily dependent on the performance of the classifier at higher levels in the classification tree.",
keywords = "Damage classification, Hierarchical decision tree, Matching pursuit decomposition, Structural health monitoring, Support vector machines",
author = "Coelho, {C. K.} and S. Das and Aditi Chattopadhyay",
year = "2009",
month = "8",
day = "1",
doi = "10.1243/09544100JAERO428",
language = "English (US)",
volume = "223",
pages = "497--505",
journal = "Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering",
issn = "0954-4100",
publisher = "SAGE Publications Ltd",
number = "5",

}

TY - JOUR

T1 - A hierarchical classification scheme for computationally efficient damage classification

AU - Coelho, C. K.

AU - Das, S.

AU - Chattopadhyay, Aditi

PY - 2009/8/1

Y1 - 2009/8/1

N2 - This article presents a methodology for data mining of sensor signals in a structural health monitoring (SHM) framework for damage classification using a machine-learning-based approach called support vector machines (SVMs). A hierarchical decision tree structure is constructed for damage classification and experiments were conducted on metallic and composite test specimens with surface mounted piezoelectric transducers. Damage was induced in the specimens by fatigue, impact, and tensile loading; in addition, specimens with seeded delaminations were also considered. Data were collected from the surface mounted sensors at different severities of induced damage. A matching pursuit decomposition (MPD) algorithm was used as a feature extraction technique to preprocess the sensor data and extract the input vectors used in classification. Using this binary tree framework, the computational intensity of each successive classifier is reduced and the efficiency of the algorithm as a whole is increased. The results obtained using this classification show that this type of architecture works well for large data sets because a reduced number of comparisons are required. Due to the hierarchical set-up of the classifiers, performance of the classifier as a whole is heavily dependent on the performance of the classifier at higher levels in the classification tree.

AB - This article presents a methodology for data mining of sensor signals in a structural health monitoring (SHM) framework for damage classification using a machine-learning-based approach called support vector machines (SVMs). A hierarchical decision tree structure is constructed for damage classification and experiments were conducted on metallic and composite test specimens with surface mounted piezoelectric transducers. Damage was induced in the specimens by fatigue, impact, and tensile loading; in addition, specimens with seeded delaminations were also considered. Data were collected from the surface mounted sensors at different severities of induced damage. A matching pursuit decomposition (MPD) algorithm was used as a feature extraction technique to preprocess the sensor data and extract the input vectors used in classification. Using this binary tree framework, the computational intensity of each successive classifier is reduced and the efficiency of the algorithm as a whole is increased. The results obtained using this classification show that this type of architecture works well for large data sets because a reduced number of comparisons are required. Due to the hierarchical set-up of the classifiers, performance of the classifier as a whole is heavily dependent on the performance of the classifier at higher levels in the classification tree.

KW - Damage classification

KW - Hierarchical decision tree

KW - Matching pursuit decomposition

KW - Structural health monitoring

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=69249107220&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69249107220&partnerID=8YFLogxK

U2 - 10.1243/09544100JAERO428

DO - 10.1243/09544100JAERO428

M3 - Article

VL - 223

SP - 497

EP - 505

JO - Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering

JF - Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering

SN - 0954-4100

IS - 5

ER -