Characterization and detection of delamination in composite laminates using artificial neural networks

Chaitanya A. Deenadayalu, Aditi Chattopadhyay, H. P. Chen

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

3 Citations (Scopus)

Abstract

A procedure has been developed for characterizing and detecting delaminations in composite structures using a combination of accurate analysis techniques, a strain-based damage index, artificial neural networks, and genetic algorithms. An improved laminate theory developed using a refined layerwise deformation field description to characterize the presence of multiple discrete delaminations in composite laminates is used to compute the layerwise in-plane modal strains. A damage indicator, based on the layerwise in plane modal strains, is used to identify the presence of both discrete and overlapping delamination in composite plates. An artificial neural network (ANN) model is developed to signal the presence of damage. It is then applied in conjunction with a genetic algorithm to describe the geometry of a random delamination for which the damage index distribution is already known. Four different types of delaminations -through-the-width, seeded, multiple seeded, and seeded overlapping delaminations, have been considered in the current study. The ANN model is found to work well as a predictive tool for detecting delaminations.

Original languageEnglish (US)
Title of host publicationCollection of Technical Papers - 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference
Pages3874-3903
Number of pages30
Volume6
StatePublished - 2004
EventCollection of Technical Papers - 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference - Albany, NY, United States
Duration: Aug 30 2004Sep 1 2004

Other

OtherCollection of Technical Papers - 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference
CountryUnited States
CityAlbany, NY
Period8/30/049/1/04

Fingerprint

Delamination
Laminates
Neural networks
Composite materials
Genetic algorithms
Composite structures
Geometry

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Deenadayalu, C. A., Chattopadhyay, A., & Chen, H. P. (2004). Characterization and detection of delamination in composite laminates using artificial neural networks. In Collection of Technical Papers - 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference (Vol. 6, pp. 3874-3903)

Characterization and detection of delamination in composite laminates using artificial neural networks. / Deenadayalu, Chaitanya A.; Chattopadhyay, Aditi; Chen, H. P.

Collection of Technical Papers - 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference. Vol. 6 2004. p. 3874-3903.

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

Deenadayalu, CA, Chattopadhyay, A & Chen, HP 2004, Characterization and detection of delamination in composite laminates using artificial neural networks. in Collection of Technical Papers - 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference. vol. 6, pp. 3874-3903, Collection of Technical Papers - 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, Albany, NY, United States, 8/30/04.
Deenadayalu CA, Chattopadhyay A, Chen HP. Characterization and detection of delamination in composite laminates using artificial neural networks. In Collection of Technical Papers - 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference. Vol. 6. 2004. p. 3874-3903
Deenadayalu, Chaitanya A. ; Chattopadhyay, Aditi ; Chen, H. P. / Characterization and detection of delamination in composite laminates using artificial neural networks. Collection of Technical Papers - 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference. Vol. 6 2004. pp. 3874-3903
@inproceedings{1753adae0acf4b99befa0cc6d75719c5,
title = "Characterization and detection of delamination in composite laminates using artificial neural networks",
abstract = "A procedure has been developed for characterizing and detecting delaminations in composite structures using a combination of accurate analysis techniques, a strain-based damage index, artificial neural networks, and genetic algorithms. An improved laminate theory developed using a refined layerwise deformation field description to characterize the presence of multiple discrete delaminations in composite laminates is used to compute the layerwise in-plane modal strains. A damage indicator, based on the layerwise in plane modal strains, is used to identify the presence of both discrete and overlapping delamination in composite plates. An artificial neural network (ANN) model is developed to signal the presence of damage. It is then applied in conjunction with a genetic algorithm to describe the geometry of a random delamination for which the damage index distribution is already known. Four different types of delaminations -through-the-width, seeded, multiple seeded, and seeded overlapping delaminations, have been considered in the current study. The ANN model is found to work well as a predictive tool for detecting delaminations.",
author = "Deenadayalu, {Chaitanya A.} and Aditi Chattopadhyay and Chen, {H. P.}",
year = "2004",
language = "English (US)",
isbn = "1563477165",
volume = "6",
pages = "3874--3903",
booktitle = "Collection of Technical Papers - 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference",

}

TY - GEN

T1 - Characterization and detection of delamination in composite laminates using artificial neural networks

AU - Deenadayalu, Chaitanya A.

AU - Chattopadhyay, Aditi

AU - Chen, H. P.

PY - 2004

Y1 - 2004

N2 - A procedure has been developed for characterizing and detecting delaminations in composite structures using a combination of accurate analysis techniques, a strain-based damage index, artificial neural networks, and genetic algorithms. An improved laminate theory developed using a refined layerwise deformation field description to characterize the presence of multiple discrete delaminations in composite laminates is used to compute the layerwise in-plane modal strains. A damage indicator, based on the layerwise in plane modal strains, is used to identify the presence of both discrete and overlapping delamination in composite plates. An artificial neural network (ANN) model is developed to signal the presence of damage. It is then applied in conjunction with a genetic algorithm to describe the geometry of a random delamination for which the damage index distribution is already known. Four different types of delaminations -through-the-width, seeded, multiple seeded, and seeded overlapping delaminations, have been considered in the current study. The ANN model is found to work well as a predictive tool for detecting delaminations.

AB - A procedure has been developed for characterizing and detecting delaminations in composite structures using a combination of accurate analysis techniques, a strain-based damage index, artificial neural networks, and genetic algorithms. An improved laminate theory developed using a refined layerwise deformation field description to characterize the presence of multiple discrete delaminations in composite laminates is used to compute the layerwise in-plane modal strains. A damage indicator, based on the layerwise in plane modal strains, is used to identify the presence of both discrete and overlapping delamination in composite plates. An artificial neural network (ANN) model is developed to signal the presence of damage. It is then applied in conjunction with a genetic algorithm to describe the geometry of a random delamination for which the damage index distribution is already known. Four different types of delaminations -through-the-width, seeded, multiple seeded, and seeded overlapping delaminations, have been considered in the current study. The ANN model is found to work well as a predictive tool for detecting delaminations.

UR - http://www.scopus.com/inward/record.url?scp=20344402790&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20344402790&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:20344402790

SN - 1563477165

SN - 9781563477164

VL - 6

SP - 3874

EP - 3903

BT - Collection of Technical Papers - 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference

ER -