Computational Technology Resources - CCP

Paper I.1

Neural Networks in the Analysis of Elastoplastic Plane Stress Problem with Unilateral Constraints

E. Pabisek and Z. Waszczyszyn

Institute of Computer Methods in Civil Engineering, Cracow University of Technology, Krakow, Poland

doi:10.4203/ccp.64.1.1

E. Pabisek, Z. Waszczyszyn, "Neural Networks in the Analysis of Elastoplastic Plane Stress Problem with Unilateral Constraints", in B.H.V. Topping, (Editor), "Computational Engineering using Metaphors from Nature", Civil-Comp Press, Edinburgh, UK, pp 1-6, 2000. doi:10.4203/ccp.64.1.1

Abstract

A hybrid system for the analysis of plane stress problem with unilateral constraints is formulated. The main idea lies in interaction of the hybrid FEM/neural program developed in [9] and the Hopfield-Tank Neural Network (HTNN) analog. The analog is formulated as an initial value problem of the FE equation analysis which can take into account the unilateral constraints. The algorithm of the hybrid system. formulated in [l0] for linear elasticity, needs time consuming updating of FE matrices when it is extended to the analysis of elastoplastic problems. A numerical example of a perforated strip with unilateral contact of a rigid bolt and the strip hole is computed.

purchase the full-text of this paper (price £20)

go to the next paper
return to the table of contents
return to the book description
purchase this book (price £52 +P&P)

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Proceedings ISSN 1759-3433 CCP: 64 COMPUTATIONAL ENGINEERING USING METAPHORS FROM NATURE Edited by: B.H.V. Topping Paper I.1 Neural Networks in the Analysis of Elastoplastic Plane Stress Problem with Unilateral Constraints E. Pabisek and Z. Waszczyszyn Institute of Computer Methods in Civil Engineering, Cracow University of Technology, Krakow, Poland doi:10.4203/ccp.64.1.1 purchase the full-text of this paper Full Bibliographic Reference for this paper E. Pabisek, Z. Waszczyszyn, "Neural Networks in the Analysis of Elastoplastic Plane Stress Problem with Unilateral Constraints", in B.H.V. Topping, (Editor), "Computational Engineering using Metaphors from Nature", Civil-Comp Press, Edinburgh, UK, pp 1-6, 2000. doi:10.4203/ccp.64.1.1 Abstract A hybrid system for the analysis of plane stress problem with unilateral constraints is formulated. The main idea lies in interaction of the hybrid FEM/neural program developed in [9] and the Hopfield-Tank Neural Network (HTNN) analog. The analog is formulated as an initial value problem of the FE equation analysis which can take into account the unilateral constraints. The algorithm of the hybrid system. formulated in [l0] for linear elasticity, needs time consuming updating of FE matrices when it is extended to the analysis of elastoplastic problems. A numerical example of a perforated strip with unilateral contact of a rigid bolt and the strip hole is computed. purchase the full-text of this paper (price £20) go to the next paper return to the table of contents return to the book description purchase this book (price £52 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions