Characterization of failure modes in CFRP composites - An ANN approach

Chandrashekhar Bhat, M. R. Bhat, C. R.L. Murthy

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Carbon fiber reinforced polymer (CFRP) composite specimens with different thickness, geometry, and stacking sequences were subjected to fatigue spectrum loading in stages. Another set of specimens was subjected to static compression load. On-line acoustic Emission (AE) monitoring was carried out during these tests. Two artificial neural networks, Kohonen-self organizing feature map (KSOM), and multi-layer perceptron (MLP) have been developed for AE signal analysis. AE signals from specimens were clustered using the unsupervised learning KSOM. These clusters were correlated to the failure modes using available a priori information such as AE signal amplitude distributions, time of occurrence of signals, ultrasonic imaging, design of the laminates (stacking sequences, orientation of fibers), and AE parametric plots. Thereafter, AE signals generated from the rest of the specimens were classified by supervised learning MLP. The network developed is made suitable for on-line monitoring of AE signals in the presence of noise, which can be used for detection and identification of failure modes and their growth. The results indicate that the characteristics of AE signals from different failure modes in CFRP remain largely unaffected by the type of load, fiber orientation, and stacking sequences, they being representatives of the type of failure phenomena. The type of loading can have effect only on the extent of damage allowed before the specimens fail and hence on the number of AE signals during the test. The artificial neural networks (ANN) developed and the methods and procedures adopted show significant success in AE signal characterization under noisy environment (detection and identification of failure modes and their growth).

Original languageEnglish
Pages (from-to)257-276
Number of pages20
JournalJournal of Composite Materials
Volume42
Issue number3
DOIs
Publication statusPublished - 01-02-2008

Fingerprint

Acoustic emissions
Failure modes
Carbon fibers
Polymers
Neural networks
Composite materials
Self organizing maps
Multilayer neural networks
carbon fiber
Ultrasonic imaging
Unsupervised learning
Monitoring
Signal analysis
Supervised learning
Fiber reinforced materials
Acoustic noise
Laminates
Fatigue of materials
Geometry
Fibers

All Science Journal Classification (ASJC) codes

  • Ceramics and Composites
  • Mechanics of Materials
  • Mechanical Engineering
  • Materials Chemistry

Cite this

Bhat, Chandrashekhar ; Bhat, M. R. ; Murthy, C. R.L. / Characterization of failure modes in CFRP composites - An ANN approach. In: Journal of Composite Materials. 2008 ; Vol. 42, No. 3. pp. 257-276.
@article{559fc87250434ae19e661b9ac716344c,
title = "Characterization of failure modes in CFRP composites - An ANN approach",
abstract = "Carbon fiber reinforced polymer (CFRP) composite specimens with different thickness, geometry, and stacking sequences were subjected to fatigue spectrum loading in stages. Another set of specimens was subjected to static compression load. On-line acoustic Emission (AE) monitoring was carried out during these tests. Two artificial neural networks, Kohonen-self organizing feature map (KSOM), and multi-layer perceptron (MLP) have been developed for AE signal analysis. AE signals from specimens were clustered using the unsupervised learning KSOM. These clusters were correlated to the failure modes using available a priori information such as AE signal amplitude distributions, time of occurrence of signals, ultrasonic imaging, design of the laminates (stacking sequences, orientation of fibers), and AE parametric plots. Thereafter, AE signals generated from the rest of the specimens were classified by supervised learning MLP. The network developed is made suitable for on-line monitoring of AE signals in the presence of noise, which can be used for detection and identification of failure modes and their growth. The results indicate that the characteristics of AE signals from different failure modes in CFRP remain largely unaffected by the type of load, fiber orientation, and stacking sequences, they being representatives of the type of failure phenomena. The type of loading can have effect only on the extent of damage allowed before the specimens fail and hence on the number of AE signals during the test. The artificial neural networks (ANN) developed and the methods and procedures adopted show significant success in AE signal characterization under noisy environment (detection and identification of failure modes and their growth).",
author = "Chandrashekhar Bhat and Bhat, {M. R.} and Murthy, {C. R.L.}",
year = "2008",
month = "2",
day = "1",
doi = "10.1177/0021998307086209",
language = "English",
volume = "42",
pages = "257--276",
journal = "Journal of Composite Materials",
issn = "0021-9983",
publisher = "SAGE Publications Ltd",
number = "3",

}

Characterization of failure modes in CFRP composites - An ANN approach. / Bhat, Chandrashekhar; Bhat, M. R.; Murthy, C. R.L.

In: Journal of Composite Materials, Vol. 42, No. 3, 01.02.2008, p. 257-276.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Characterization of failure modes in CFRP composites - An ANN approach

AU - Bhat, Chandrashekhar

AU - Bhat, M. R.

AU - Murthy, C. R.L.

PY - 2008/2/1

Y1 - 2008/2/1

N2 - Carbon fiber reinforced polymer (CFRP) composite specimens with different thickness, geometry, and stacking sequences were subjected to fatigue spectrum loading in stages. Another set of specimens was subjected to static compression load. On-line acoustic Emission (AE) monitoring was carried out during these tests. Two artificial neural networks, Kohonen-self organizing feature map (KSOM), and multi-layer perceptron (MLP) have been developed for AE signal analysis. AE signals from specimens were clustered using the unsupervised learning KSOM. These clusters were correlated to the failure modes using available a priori information such as AE signal amplitude distributions, time of occurrence of signals, ultrasonic imaging, design of the laminates (stacking sequences, orientation of fibers), and AE parametric plots. Thereafter, AE signals generated from the rest of the specimens were classified by supervised learning MLP. The network developed is made suitable for on-line monitoring of AE signals in the presence of noise, which can be used for detection and identification of failure modes and their growth. The results indicate that the characteristics of AE signals from different failure modes in CFRP remain largely unaffected by the type of load, fiber orientation, and stacking sequences, they being representatives of the type of failure phenomena. The type of loading can have effect only on the extent of damage allowed before the specimens fail and hence on the number of AE signals during the test. The artificial neural networks (ANN) developed and the methods and procedures adopted show significant success in AE signal characterization under noisy environment (detection and identification of failure modes and their growth).

AB - Carbon fiber reinforced polymer (CFRP) composite specimens with different thickness, geometry, and stacking sequences were subjected to fatigue spectrum loading in stages. Another set of specimens was subjected to static compression load. On-line acoustic Emission (AE) monitoring was carried out during these tests. Two artificial neural networks, Kohonen-self organizing feature map (KSOM), and multi-layer perceptron (MLP) have been developed for AE signal analysis. AE signals from specimens were clustered using the unsupervised learning KSOM. These clusters were correlated to the failure modes using available a priori information such as AE signal amplitude distributions, time of occurrence of signals, ultrasonic imaging, design of the laminates (stacking sequences, orientation of fibers), and AE parametric plots. Thereafter, AE signals generated from the rest of the specimens were classified by supervised learning MLP. The network developed is made suitable for on-line monitoring of AE signals in the presence of noise, which can be used for detection and identification of failure modes and their growth. The results indicate that the characteristics of AE signals from different failure modes in CFRP remain largely unaffected by the type of load, fiber orientation, and stacking sequences, they being representatives of the type of failure phenomena. The type of loading can have effect only on the extent of damage allowed before the specimens fail and hence on the number of AE signals during the test. The artificial neural networks (ANN) developed and the methods and procedures adopted show significant success in AE signal characterization under noisy environment (detection and identification of failure modes and their growth).

UR - http://www.scopus.com/inward/record.url?scp=38949162217&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38949162217&partnerID=8YFLogxK

U2 - 10.1177/0021998307086209

DO - 10.1177/0021998307086209

M3 - Article

VL - 42

SP - 257

EP - 276

JO - Journal of Composite Materials

JF - Journal of Composite Materials

SN - 0021-9983

IS - 3

ER -