Structural optimization using evolution strategies and neural networks

Papadrakakis, M; Lagaros, ND; Tsompanakis, Y

dc.contributor.author	Papadrakakis, M	en
dc.contributor.author	Lagaros, ND	en
dc.contributor.author	Tsompanakis, Y	en
dc.date.accessioned	2014-03-01T01:14:12Z
dc.date.available	2014-03-01T01:14:12Z
dc.date.issued	1998	en
dc.identifier.issn	0045-7825	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/12918
dc.subject	Back Propagation Algorithm	en
dc.subject	Combinatorial Optimization	en
dc.subject	Evolution Strategy	en
dc.subject	Large Scale	en
dc.subject	Large Scale Optimization	en
dc.subject	Optimization Problem	en
dc.subject	Size Structure	en
dc.subject	Structure Analysis	en
dc.subject	Structure Optimization	en
dc.subject	Neural Network	en
dc.subject.classification	Engineering, Multidisciplinary	en
dc.subject.classification	Mathematics, Interdisciplinary Applications	en
dc.subject.classification	Mechanics	en
dc.subject.other	DESIGN	en
dc.title	Structural optimization using evolution strategies and neural networks	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/S0045-7825(97)00215-6	en
heal.identifier.secondary	http://dx.doi.org/10.1016/S0045-7825(97)00215-6	en
heal.language	English	en
heal.publicationDate	1998	en
heal.abstract	The objective of this paper is to investigate the efficiency of combinatorial optimization methods, in particular algorithms based on evolution strategies (ES) when incorporated into the solution of large-scale, continuous or discrete, structural optimization problems. Two types of applications have been investigated, namely shape and sizing structural optimization problems. Furthermore, a neural network (NN) model is used in order to replace the structural analysis phase and to compute the necessary data for the ES optimization procedure. The use of NN was motivated by the time-consuming repeated analyses required by ES during the optimization process. A back propagation algorithm is implemented for training the NN using data derived from selected analyses. The trained NN is then used to predict, within an acceptable accuracy, the values of the objective and constraint functions. The numerical tests presented demonstrate the computational advantages of the proposed approach which become more pronounced in large-scale optimization problems. (C) 1998 Elsevier Science S.A.	en
heal.publisher	ELSEVIER SCIENCE SA	en
heal.journalName	Computer Methods in Applied Mechanics and Engineering	en
dc.identifier.doi	10.1016/S0045-7825(97)00215-6	en
dc.identifier.isi	ISI:000073491400017	en
dc.identifier.volume	156	en
dc.identifier.issue	1-4	en
dc.identifier.spage	309	en
dc.identifier.epage	333	en