Neurocomputing strategies for solving reliability-robust design optimization problems

Lagaros, ND; Plevris, V; Papadrakakis, M

dc.contributor.author	Lagaros, ND	en
dc.contributor.author	Plevris, V	en
dc.contributor.author	Papadrakakis, M	en
dc.date.accessioned	2014-03-01T01:33:53Z
dc.date.available	2014-03-01T01:33:53Z
dc.date.issued	2010	en
dc.identifier.issn	0264-4401	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/20610
dc.subject	Neural nets	en
dc.subject	Optimization techniques	en
dc.subject	Structural design	en
dc.subject	Structural engineering	en
dc.subject.classification	Computer Science, Interdisciplinary Applications	en
dc.subject.classification	Engineering, Multidisciplinary	en
dc.subject.classification	Mathematics, Interdisciplinary Applications	en
dc.subject.classification	Mechanics	en
dc.subject.other	Applied loading	en
dc.subject.other	Combined reliability	en
dc.subject.other	Computational costs	en
dc.subject.other	Computational time	en
dc.subject.other	Construction costs	en
dc.subject.other	Cross section	en
dc.subject.other	Four-order	en
dc.subject.other	Low probability	en
dc.subject.other	Modulus of elasticity	en
dc.subject.other	Monte Carlo simulation methods	en
dc.subject.other	Multi-objective optimization problem	en
dc.subject.other	Network prediction	en
dc.subject.other	Neural net	en
dc.subject.other	Neurocomputing	en
dc.subject.other	Numerical results	en
dc.subject.other	Optimization problems	en
dc.subject.other	Optimization techniques	en
dc.subject.other	Probabilistic analysis	en
dc.subject.other	Probabilistic constraints	en
dc.subject.other	Real-world	en
dc.subject.other	Robust design optimization	en
dc.subject.other	Standard deviation	en
dc.subject.other	Structural engineering	en
dc.subject.other	Structural response	en
dc.subject.other	Structural systems	en
dc.subject.other	Computer simulation	en
dc.subject.other	Monte Carlo methods	en
dc.subject.other	Multiobjective optimization	en
dc.subject.other	Neural networks	en
dc.subject.other	Quality assurance	en
dc.subject.other	Random variables	en
dc.subject.other	Reliability	en
dc.subject.other	Shape optimization	en
dc.subject.other	Stress analysis	en
dc.subject.other	Structural design	en
dc.subject.other	Yield stress	en
dc.subject.other	Structural optimization	en
dc.title	Neurocomputing strategies for solving reliability-robust design optimization problems	en
heal.type	journalArticle	en
heal.identifier.primary	10.1108/02644401011073674	en
heal.identifier.secondary	http://dx.doi.org/10.1108/02644401011073674	en
heal.language	English	en
heal.publicationDate	2010	en
heal.abstract	Purpose - This paper, by taking randomness and uncertainty of structural systems into account aims to implement a combined reliability-based robust design optimization (RRDO) formulation. The random variables to be considered include the cross section dimensions, modulus of elasticity, yield stress, and applied loading. The RRDO problem is to be formulated as a multi-objective optimization problem where the construction cost and the standard deviation of the structural response are the objectives to be minimized. Design/methodology/ approach - The solution of the optimization problem is performed with the non-dominant cascade evolutionary algorithm with the weighted Tchebycheff metric, while the probabilistic analysis required is carried out with the Monte Carlo simulation method. Despite the computational advances, the solution of a RRDO problem for real-world structures is extremely computationally demanding and for this reason neurocomputing estimations are implemented. Findings - The obtained estimates with the neural network predictions are shown to be very satisfactory in terms of accuracy for performing this type of computation. Furthermore, the present numerical results manage to achieve a reduction in computational time up to four orders of magnitude, for low probabilities of violation, compared to the conventional procedure making thus feasible the reliability-robust design optimization of realistic structures under probabilistic constraints. Originality/value - The novel parts of the present work include the implementation of neurocomputing strategies in RRDO problems for reducing the computational cost and the comparison of the results given by RRDO and robust design optimization formulations, where the significance of taking into account probabilistic constraints is emphasized. © Emerald Group Publishing Limited.	en
heal.publisher	EMERALD GROUP PUBLISHING LIMITED	en
heal.journalName	Engineering Computations (Swansea, Wales)	en
dc.identifier.doi	10.1108/02644401011073674	en
dc.identifier.isi	ISI:000286569400003	en
dc.identifier.volume	27	en
dc.identifier.issue	7	en
dc.identifier.spage	819	en
dc.identifier.epage	840	en