Stochastic Investigation of Natural Frequency for Functionally Graded Plates

3rd International Conference on Mechanical and Aeronautical Engineering

机械制造;航空航天工程

Karsh, P.K.^1 ; Mukhopadhyay, T.^2 ; Dey, S.^1

Mechanical Engineering Department, National Institute of Technology Silchar, India^1

Department of Engineering Science, University of Oxford, United Kingdom^2

关键词: ANN modeling;    Frequency Analysis;    Functionally graded plates;    Input parameter;    Latin hypercube sampling;    Mass densities;    Monte carlo simulations (MCS);    Stochastic variation;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/326/1/012003/pdf
DOI  :  10.1088/1757-899X/326/1/012003

学科分类：航空航天科学

来源: IOP

【 摘 要 】

This paper presents the stochastic natural frequency analysis of functionally graded plates by applying artificial neural network (ANN) approach. Latin hypercube sampling is utilised to train the ANN model. The proposed algorithm for stochastic natural frequency analysis of FGM plates is validated and verified with original finite element method and Monte Carlo simulation (MCS). The combined stochastic variation of input parameters such as, elastic modulus, shear modulus, Poisson ratio, and mass density are considered. Power law is applied to distribute the material properties across the thickness. The present ANN model reduces the sample size and computationally found efficient as compared to conventional Monte Carlo simulation.