Integrated optimal topology design and shape optimization using neural networks

Yıldız, Ali Rıza; Öztürk, Nursel; Kaya, Necmettin; Öztürk, Ferruh

doi:10.1007/s00158-003-0300-0

Cited by 79 publications

(10 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Koguchi and Kikuchi (2006) proposed a three-step method based on an enclosed isosurface of the TO-solution and biquartic surface splines to build the CAD model. Yildiz et al (2003) applied a neural networkbased image-processing technique in order to automatically interpret the TO-solution. Tang and Chang (2001) fitted B-splines to a smoothed representation of the TO-solution.…”

Section: Introductionmentioning

confidence: 99%

Efficient detailed design optimization of topology optimization concepts by using support vector machines and metamodels

Strömberg

2019

Engineering Optimization

View full text Add to dashboard Cite

In this article, an approach for metamodel-based design optimization (MBDO) of topology optimization (TO) concepts is proposed by using support vector machines (SVMs) as geometric models of the concepts instead of traditional parametric computer aided design (CAD) models. In such a manner, an efficient approach for the MBDO-driven design of TO-based concepts is obtained. An implicit hypersurface representing the TO-based concept is generated by classifying the TO-solutions of zeros and ones by using the 1-norm SVM of Mangasarian. The implicit SVM-based hypersurfaces are then utilized to set up designs of experiments of nonlinear finite element analyses by morphing the TO-based concepts by using Boolean and blending operations. Finally, MBDO is performed by using an ensemble of metamodels consisting of quadratic regression, Kriging, radial basis function networks, polynomial chaos expansion and support vector regression models. The proposed MBDO framework is demonstrated by minimizing the mass of a three-dimensional design domain with a constraint on the plastic limit load. The performance of the approach is most promising.

show abstract

Section: Introductionmentioning

confidence: 99%

Efficient detailed design optimization of topology optimization concepts by using support vector machines and metamodels

Strömberg

2019

Engineering Optimization

View full text Add to dashboard Cite

show abstract

“…Neural network-and feature-based approaches are introduced by Yildiz et al [22] to overcome current shortcomings in the automated integration of topology design and shape optimization. The topology optimization results are reconstructed in terms of features, which consist of attributes required for automation and integration in subsequent applications.…”

Section: Literature Reviewmentioning

confidence: 99%

Simulated annealing algorithm for balanced allocation problem

Rajesh

Pugazhendhi

Ganesh

2011

Int J Adv Manuf Technol

View full text Add to dashboard Cite

This paper deals with the balanced allocation of customers to multiple third party logistics warehouses. The allocation problem generally deals with clustering of customers so as to achieve minimum total resource viz. cost or time. But the real challenge arises when it is required to strike a balance between the allocation while also minimizing the total cost or time. Since the problem develops to be non-deterministic polynomial-time hard, the paper uses simulated annealing approach to solve the problem. The balanced solution is achieved by using the min-max function. The effectiveness of the new algorithm is presented through simulation of large sets of problems.

show abstract

“…Among others, the most widespread are feature recognition 1 of Catia, Holemaking of UG/NX, Feature Recogniser of SolidEdge and Feature Works of Solid Works. On the other hand, in literature, the present researches recommend the use of genetic algorithms and neural networks, in order to expand and improve the feature libraries [16,17]. However, these researches deal with few features to recognize and with 2D or 2D1/2 shapes (obtained by a projection of a 2D shape into 3rd dimension) and never with complex geometry [18][19][20].…”

Section: Kbe Systems and Design Optimization Integrationmentioning

confidence: 99%