Uncertain natural frequency analysis of composite plates including effect of noise – A polynomial neural network approach

S. Dey, S. Naskar, T. Mukhopadhyay, U. Gohs, A. Spickenheuer, L. Bittrich, S. Sriramula, S. Adhikari, G. Heinrich

Research output: Contribution to journalArticle

39 Citations (Scopus)
6 Downloads (Pure)

Abstract

This paper presents the quantification of uncertain natural frequency for laminated composite plates by using a novel surrogate model. A group method of data handling in conjunction to polynomial neural network (PNN) is employed as surrogate for numerical model and is trained by using Latin hypercube sampling. Subsequently the effect of noise on a PNN based uncertainty quantification algorithm is explored in this study. The convergence of the proposed algorithm for stochastic natural frequency analysis of composite plates is verified and validated with original finite element method (FEM). Both individual and combined variation of stochastic input parameters are considered to address the influence on the output of interest. The sample size and computational cost are reduced by employing the present approach compared to direct Monte Carlo simulation (MCS).
Original languageEnglish
Pages (from-to)130-142
Number of pages13
JournalComposite Structures
Volume143
Early online date13 Feb 2016
DOIs
Publication statusPublished - 20 May 2016

Fingerprint

Natural frequencies
Polynomials
Neural networks
Data handling
Composite materials
Laminated composites
Numerical models
Sampling
Finite element method
Costs
Monte Carlo simulation
Uncertainty

Keywords

  • uncertainty quantification
  • polynomial neural network
  • stochastic natural frequency
  • latin hypercube
  • composite plate

Cite this

Uncertain natural frequency analysis of composite plates including effect of noise – A polynomial neural network approach. / Dey, S. ; Naskar, S.; Mukhopadhyay, T. ; Gohs, U. ; Spickenheuer, A. ; Bittrich, L. ; Sriramula, S.; Adhikari, S.; Heinrich, G. .

In: Composite Structures, Vol. 143, 20.05.2016, p. 130-142.

Research output: Contribution to journalArticle

Dey, S. ; Naskar, S. ; Mukhopadhyay, T. ; Gohs, U. ; Spickenheuer, A. ; Bittrich, L. ; Sriramula, S. ; Adhikari, S. ; Heinrich, G. . / Uncertain natural frequency analysis of composite plates including effect of noise – A polynomial neural network approach. In: Composite Structures. 2016 ; Vol. 143. pp. 130-142.
@article{314ee784a24b480cb6d7b580e2e74229,
title = "Uncertain natural frequency analysis of composite plates including effect of noise – A polynomial neural network approach",
abstract = "This paper presents the quantification of uncertain natural frequency for laminated composite plates by using a novel surrogate model. A group method of data handling in conjunction to polynomial neural network (PNN) is employed as surrogate for numerical model and is trained by using Latin hypercube sampling. Subsequently the effect of noise on a PNN based uncertainty quantification algorithm is explored in this study. The convergence of the proposed algorithm for stochastic natural frequency analysis of composite plates is verified and validated with original finite element method (FEM). Both individual and combined variation of stochastic input parameters are considered to address the influence on the output of interest. The sample size and computational cost are reduced by employing the present approach compared to direct Monte Carlo simulation (MCS).",
keywords = "uncertainty quantification, polynomial neural network, stochastic natural frequency, latin hypercube, composite plate",
author = "S. Dey and S. Naskar and T. Mukhopadhyay and U. Gohs and A. Spickenheuer and L. Bittrich and S. Sriramula and S. Adhikari and G. Heinrich",
note = "Acknowledgement SN and SS gratefully acknowledge the financial support from Lloyd’s Register Foundation Centre during this work.",
year = "2016",
month = "5",
day = "20",
doi = "10.1016/j.compstruct.2016.02.007",
language = "English",
volume = "143",
pages = "130--142",
journal = "Composite Structures",
issn = "0263-8223",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Uncertain natural frequency analysis of composite plates including effect of noise – A polynomial neural network approach

AU - Dey, S.

AU - Naskar, S.

AU - Mukhopadhyay, T.

AU - Gohs, U.

AU - Spickenheuer, A.

AU - Bittrich, L.

AU - Sriramula, S.

AU - Adhikari, S.

AU - Heinrich, G.

N1 - Acknowledgement SN and SS gratefully acknowledge the financial support from Lloyd’s Register Foundation Centre during this work.

PY - 2016/5/20

Y1 - 2016/5/20

N2 - This paper presents the quantification of uncertain natural frequency for laminated composite plates by using a novel surrogate model. A group method of data handling in conjunction to polynomial neural network (PNN) is employed as surrogate for numerical model and is trained by using Latin hypercube sampling. Subsequently the effect of noise on a PNN based uncertainty quantification algorithm is explored in this study. The convergence of the proposed algorithm for stochastic natural frequency analysis of composite plates is verified and validated with original finite element method (FEM). Both individual and combined variation of stochastic input parameters are considered to address the influence on the output of interest. The sample size and computational cost are reduced by employing the present approach compared to direct Monte Carlo simulation (MCS).

AB - This paper presents the quantification of uncertain natural frequency for laminated composite plates by using a novel surrogate model. A group method of data handling in conjunction to polynomial neural network (PNN) is employed as surrogate for numerical model and is trained by using Latin hypercube sampling. Subsequently the effect of noise on a PNN based uncertainty quantification algorithm is explored in this study. The convergence of the proposed algorithm for stochastic natural frequency analysis of composite plates is verified and validated with original finite element method (FEM). Both individual and combined variation of stochastic input parameters are considered to address the influence on the output of interest. The sample size and computational cost are reduced by employing the present approach compared to direct Monte Carlo simulation (MCS).

KW - uncertainty quantification

KW - polynomial neural network

KW - stochastic natural frequency

KW - latin hypercube

KW - composite plate

U2 - 10.1016/j.compstruct.2016.02.007

DO - 10.1016/j.compstruct.2016.02.007

M3 - Article

VL - 143

SP - 130

EP - 142

JO - Composite Structures

JF - Composite Structures

SN - 0263-8223

ER -