Parameterised modelling technique and its application to artificial neural network-based structural health monitoring

Nao Huang, Lin Ye, Zhongqing Su

Research output: Chapter in book / Conference proceedingChapter in an edited book (as author)Academic researchpeer-review

3 Citations (Scopus)

Abstract

A Parameterised Modelling Technique (PMT) for composite structures was developed on PATRAN® PCL platform. Such a method is able to offer end users a friendly environment to build FEM models for complicated engineering systems while with minimum human efforts and cost. This technique was then validated by selected case study, in which quasi-isotropic CFIEP composite laminates containing delamination with various locations, interlaminar positions and geometric identities were automatically and successively modelled in terms of provided parameters (laminate geometric characteristics, materials properties, delamination location/shape/size/orientation, mesh density, constraint conditions, etc.). An interface was also programmed to conduct dynamic FEM simulation based on developed models using ABAQUS/EXPLICT FEM code. In the selected case study, the proposed approach was also employed to develop an artificial neural network-based structural delamination detection system. It was observed that computational effort and expenditure have been exponentially decreased via such a technique.
Original languageEnglish
Title of host publicationComposites Technologies For 2020
PublisherWoodhead Publishing Limited
Pages999-1004
Number of pages6
ISBN (Print)9781855738317
Publication statusPublished - 1 Jan 2004
Externally publishedYes

ASJC Scopus subject areas

  • Materials Science(all)

Cite this