Delamination identification using machine learning methods and haar wavelets
Journal Title: Computer Assisted Methods in Engineering and Science - Year 2012, Vol 19, Issue 4
Abstract
The present paper focuses on the identification of delamination size and location in homogeneous and composite laminates. The modal analysis methods are employed to calculate the data patterns. An aggregated approach combining Haar wavelets, support vector machines (SVMs) and artificial neural networks (ANNs) is used to solve identification problems. The usability and effectiveness of the proposed technique are tested by several numerical experiments. The advantages of the proposed method lie in the ability to make fast and accurate calculations.
Authors and Affiliations
Ljubov Feklistova, Helle Hein
Keywords
Related Articles
- EP ID EP73956
- DOI -
- Views 194
- Downloads 0
Improved two-dimensional cracked finite element for crack fault diagnosis
In this paper the two-dimensional finite element with an embedded edge crack proposed by Potirniche et al. (2008) is improved further for crack depth ratios ranging up to 0.9 and for predicting the natural frequency of a...
Application of sensitivity analysis in microscale heat transfer
In the paper, the thin metal film subjected to the ultrashort laser pulse has been analyzed. The heat conduction in the domain considered has been described by two-temperature model consisting of the system of two couple...
Sequential stochastic identification of elastic constants using Lamb waves and particle filters
Sequential stochastic identification of elastic parameters of thin aluminum plates using Lamb waves is proposed. The identification process is formulated as a Bayesian state estimation problem in which the elastic consta...
Application of support vector machine in geodesy for the classification of vertical displacements
The article presents basic rules for constructing and training neural networks, called the Support Vector Machine technique. SVM networks can mainly be used for solving tasks of classification of linearly and nonlinearly...
A method of identification of kinematic chains and distinct mechanisms. (Received in the final form November 19, 2009)
A new method is proposed to identify the distinct mechanisms derived from a given kinematic chain in this paper. The kinematic chains and their derived mechanisms are presented in the form of a flow matrix. Two structura...