Kernel feature space based low velocity impact monitoring

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

Abstract

Impact damage has been identified as a critical form of defect that constantly threatens the reliability of composite structures, such as those used in aircrafts and naval vessels. Low energy impacts can introduce barely visible damage and cause structural degradation. Therefore, efficient structural health monitoring methods, which can accurately detect, quantify, and localize impact damage in complex composite structures, are required. In this paper a novel damage detection methodology is demonstrated for monitoring and quantifying the impact damage propagation. Statistical feature matrices, composed of features extracted from the time and frequency domains, are developed. Kernel Principal Component Analysis (KPCA) is used to compress and classify the statistical feature matrices. Compared with traditional PCA algorithm, KPCA method shows better feature clustering and damage quantification capabilities. A new damage index, formulated using Mahalanobis distance, is defined to quantify impact damage. The developed methodology has been validated using low velocity impact experiments with a sandwich composite wing.

Original languageEnglish (US)
Title of host publicationASME 2012 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2012
Pages917-924
Number of pages8
Volume1
DOIs
StatePublished - 2012
EventASME 2012 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2012 - Stone Mountain, GA, United States
Duration: Sep 19 2012Sep 21 2012

Other

OtherASME 2012 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2012
CountryUnited States
CityStone Mountain, GA
Period9/19/129/21/12

Fingerprint

Composite structures
Principal component analysis
Naval vessels
Monitoring
Damage detection
Structural health monitoring
Aircraft
Degradation
Defects
Composite materials
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Civil and Structural Engineering
  • Mechanics of Materials

Cite this

Liu, Y., Yekani Fard, M., & Chattopadhyay, A. (2012). Kernel feature space based low velocity impact monitoring. In ASME 2012 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2012 (Vol. 1, pp. 917-924) https://doi.org/10.1115/SMASIS2012-8242

Kernel feature space based low velocity impact monitoring. / Liu, Yingtao; Yekani Fard, Masoud; Chattopadhyay, Aditi.

ASME 2012 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2012. Vol. 1 2012. p. 917-924.

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

Liu, Y, Yekani Fard, M & Chattopadhyay, A 2012, Kernel feature space based low velocity impact monitoring. in ASME 2012 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2012. vol. 1, pp. 917-924, ASME 2012 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2012, Stone Mountain, GA, United States, 9/19/12. https://doi.org/10.1115/SMASIS2012-8242
Liu Y, Yekani Fard M, Chattopadhyay A. Kernel feature space based low velocity impact monitoring. In ASME 2012 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2012. Vol. 1. 2012. p. 917-924 https://doi.org/10.1115/SMASIS2012-8242
Liu, Yingtao ; Yekani Fard, Masoud ; Chattopadhyay, Aditi. / Kernel feature space based low velocity impact monitoring. ASME 2012 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2012. Vol. 1 2012. pp. 917-924
@inproceedings{ec09ba6694de49b6b88bd16fa424e50f,
title = "Kernel feature space based low velocity impact monitoring",
abstract = "Impact damage has been identified as a critical form of defect that constantly threatens the reliability of composite structures, such as those used in aircrafts and naval vessels. Low energy impacts can introduce barely visible damage and cause structural degradation. Therefore, efficient structural health monitoring methods, which can accurately detect, quantify, and localize impact damage in complex composite structures, are required. In this paper a novel damage detection methodology is demonstrated for monitoring and quantifying the impact damage propagation. Statistical feature matrices, composed of features extracted from the time and frequency domains, are developed. Kernel Principal Component Analysis (KPCA) is used to compress and classify the statistical feature matrices. Compared with traditional PCA algorithm, KPCA method shows better feature clustering and damage quantification capabilities. A new damage index, formulated using Mahalanobis distance, is defined to quantify impact damage. The developed methodology has been validated using low velocity impact experiments with a sandwich composite wing.",
author = "Yingtao Liu and {Yekani Fard}, Masoud and Aditi Chattopadhyay",
year = "2012",
doi = "10.1115/SMASIS2012-8242",
language = "English (US)",
isbn = "9780791845097",
volume = "1",
pages = "917--924",
booktitle = "ASME 2012 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2012",

}

TY - GEN

T1 - Kernel feature space based low velocity impact monitoring

AU - Liu, Yingtao

AU - Yekani Fard, Masoud

AU - Chattopadhyay, Aditi

PY - 2012

Y1 - 2012

N2 - Impact damage has been identified as a critical form of defect that constantly threatens the reliability of composite structures, such as those used in aircrafts and naval vessels. Low energy impacts can introduce barely visible damage and cause structural degradation. Therefore, efficient structural health monitoring methods, which can accurately detect, quantify, and localize impact damage in complex composite structures, are required. In this paper a novel damage detection methodology is demonstrated for monitoring and quantifying the impact damage propagation. Statistical feature matrices, composed of features extracted from the time and frequency domains, are developed. Kernel Principal Component Analysis (KPCA) is used to compress and classify the statistical feature matrices. Compared with traditional PCA algorithm, KPCA method shows better feature clustering and damage quantification capabilities. A new damage index, formulated using Mahalanobis distance, is defined to quantify impact damage. The developed methodology has been validated using low velocity impact experiments with a sandwich composite wing.

AB - Impact damage has been identified as a critical form of defect that constantly threatens the reliability of composite structures, such as those used in aircrafts and naval vessels. Low energy impacts can introduce barely visible damage and cause structural degradation. Therefore, efficient structural health monitoring methods, which can accurately detect, quantify, and localize impact damage in complex composite structures, are required. In this paper a novel damage detection methodology is demonstrated for monitoring and quantifying the impact damage propagation. Statistical feature matrices, composed of features extracted from the time and frequency domains, are developed. Kernel Principal Component Analysis (KPCA) is used to compress and classify the statistical feature matrices. Compared with traditional PCA algorithm, KPCA method shows better feature clustering and damage quantification capabilities. A new damage index, formulated using Mahalanobis distance, is defined to quantify impact damage. The developed methodology has been validated using low velocity impact experiments with a sandwich composite wing.

UR - http://www.scopus.com/inward/record.url?scp=84892640610&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84892640610&partnerID=8YFLogxK

U2 - 10.1115/SMASIS2012-8242

DO - 10.1115/SMASIS2012-8242

M3 - Conference contribution

AN - SCOPUS:84892640610

SN - 9780791845097

VL - 1

SP - 917

EP - 924

BT - ASME 2012 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2012

ER -