Supervised and non-supervised AE data classification of nanomodified CFRP during DCB tests

N. Fallahi, G. Nardoni, H. Heidary, R. Palazzetti, X.T. Yan, A. Zucchelli

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Aim of the paper is to use acoustic emissions to study the effect of electrospun nylon 6,6 Nanofibrous mat on carbon-epoxy composites during Double Cantilever beam (DCB) tests. In order to recognize the effect of the nanofibres and to detect different damage mechanisms, k-means clustering of acoustic emission signals applied to rise time, count, energy, duration and amplitude of the events is used. Supervised neural network (NN) is then applied to verify clustered signals. Results showed that clustered acoustic emission signals are a reliable tool to detect different damage mechanisms; neural network showed the method has a 99% of accuracy.
LanguageEnglish
Pages415-421
Number of pages7
JournalFME Transactions
Volume44
Issue number4
DOIs
Publication statusAccepted/In press - 21 Jun 2016

Fingerprint

Carbon fiber reinforced plastics
Cantilever beams
Acoustic emissions
Neural networks
Nanofibers
Carbon
Composite materials
carbon fiber reinforced plastic

Keywords

  • acoustic emission
  • artificial neural network
  • K-means
  • CFRP
  • electrospinning

Cite this

Fallahi, N., Nardoni, G., Heidary, H., Palazzetti, R., Yan, X. T., & Zucchelli, A. (Accepted/In press). Supervised and non-supervised AE data classification of nanomodified CFRP during DCB tests. FME Transactions, 44(4), 415-421. https://doi.org/10.5937/fmet1604415F
Fallahi, N. ; Nardoni, G. ; Heidary, H. ; Palazzetti, R. ; Yan, X.T. ; Zucchelli, A. / Supervised and non-supervised AE data classification of nanomodified CFRP during DCB tests. In: FME Transactions. 2016 ; Vol. 44, No. 4. pp. 415-421.
@article{9630de5c1cf2471e86efd9f8ee9d0e78,
title = "Supervised and non-supervised AE data classification of nanomodified CFRP during DCB tests",
abstract = "Aim of the paper is to use acoustic emissions to study the effect of electrospun nylon 6,6 Nanofibrous mat on carbon-epoxy composites during Double Cantilever beam (DCB) tests. In order to recognize the effect of the nanofibres and to detect different damage mechanisms, k-means clustering of acoustic emission signals applied to rise time, count, energy, duration and amplitude of the events is used. Supervised neural network (NN) is then applied to verify clustered signals. Results showed that clustered acoustic emission signals are a reliable tool to detect different damage mechanisms; neural network showed the method has a 99{\%} of accuracy.",
keywords = "acoustic emission, artificial neural network, K-means, CFRP, electrospinning",
author = "N. Fallahi and G. Nardoni and H. Heidary and R. Palazzetti and X.T. Yan and A. Zucchelli",
year = "2016",
month = "6",
day = "21",
doi = "10.5937/fmet1604415F",
language = "English",
volume = "44",
pages = "415--421",
journal = "FME Transactions",
issn = "1451-2092",
publisher = "Faculty of Mechanical Engineering, Belgrade University",
number = "4",

}

Fallahi, N, Nardoni, G, Heidary, H, Palazzetti, R, Yan, XT & Zucchelli, A 2016, 'Supervised and non-supervised AE data classification of nanomodified CFRP during DCB tests' FME Transactions, vol. 44, no. 4, pp. 415-421. https://doi.org/10.5937/fmet1604415F

Supervised and non-supervised AE data classification of nanomodified CFRP during DCB tests. / Fallahi, N.; Nardoni, G.; Heidary, H.; Palazzetti, R.; Yan, X.T.; Zucchelli, A.

In: FME Transactions, Vol. 44, No. 4, 21.06.2016, p. 415-421.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Supervised and non-supervised AE data classification of nanomodified CFRP during DCB tests

AU - Fallahi, N.

AU - Nardoni, G.

AU - Heidary, H.

AU - Palazzetti, R.

AU - Yan, X.T.

AU - Zucchelli, A.

PY - 2016/6/21

Y1 - 2016/6/21

N2 - Aim of the paper is to use acoustic emissions to study the effect of electrospun nylon 6,6 Nanofibrous mat on carbon-epoxy composites during Double Cantilever beam (DCB) tests. In order to recognize the effect of the nanofibres and to detect different damage mechanisms, k-means clustering of acoustic emission signals applied to rise time, count, energy, duration and amplitude of the events is used. Supervised neural network (NN) is then applied to verify clustered signals. Results showed that clustered acoustic emission signals are a reliable tool to detect different damage mechanisms; neural network showed the method has a 99% of accuracy.

AB - Aim of the paper is to use acoustic emissions to study the effect of electrospun nylon 6,6 Nanofibrous mat on carbon-epoxy composites during Double Cantilever beam (DCB) tests. In order to recognize the effect of the nanofibres and to detect different damage mechanisms, k-means clustering of acoustic emission signals applied to rise time, count, energy, duration and amplitude of the events is used. Supervised neural network (NN) is then applied to verify clustered signals. Results showed that clustered acoustic emission signals are a reliable tool to detect different damage mechanisms; neural network showed the method has a 99% of accuracy.

KW - acoustic emission

KW - artificial neural network

KW - K-means

KW - CFRP

KW - electrospinning

UR - http://www.mas.bg.ac.rs/istrazivanje/fme/

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-84988939483&origin=inward&txGid=B04CDA73593EF9930F61A420A9F1024C.wsnAw8kcdt7IPYLO0V48gA%3a12

U2 - 10.5937/fmet1604415F

DO - 10.5937/fmet1604415F

M3 - Article

VL - 44

SP - 415

EP - 421

JO - FME Transactions

T2 - FME Transactions

JF - FME Transactions

SN - 1451-2092

IS - 4

ER -