Book Chapter10.1007/978-3-030-38926-0_5
Triangulation-Based Constrained Modeling
Slawomir Koziel,Anna Pietrenko-Dabrowska +1 more
- 01 Jan 2020
- pp 153-177
1
TL;DR: This chapter discusses a systematic approach to constrained modeling that allows for an arbitrary allocation of the reference designs as well as, in principle, arbitrary number of performance figures.
read more
Abstract: This chapter discusses a systematic approach to constrained modeling that allows for an arbitrary allocation of the reference designs as well as, in principle, arbitrary number of performance figures. The surrogate model domain is spanned by the simplexes, obtained from triangulating of the reference designs, further extended into their orthogonal complements. Restricting the model domain permits dramatic reduction of the number of training data samples necessary to build a reliable model, in comparison to the conventional approach. The discussed modeling framework is demonstrated using several examples. Comprehensive benchmarking and application studies and experimental verification are also provided.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Book
Performance-Driven Surrogate Modeling of High-Frequency Structures
Slawomir Koziel,Anna Pietrenko-Dabrowska +1 more
- 19 Feb 2020
TL;DR: In this paper, the authors present a different methodological perspective on modeling of high-frequency structures, specifically, the concept and implementation of constrained or performance-driven surrogates, which addresses the issues of dimensionality and parameter ranges through appropriate confinement of the model do-main, focused on the regions that are promising from the point of view of relevant design objectives.
83
References
Surrogate-based Analysis and Optimization
Nestor V. Queipo,Raphael T. Haftka,Wei Shyy,Tushar Goel,Rajkumar Vaidyanathan,P. Kevin Tucker +5 more
TL;DR: The multi-objective optimal design of a liquid rocket injector is presented to highlight the state of the art and to help guide future efforts.
2.4K
Kriging metamodeling in simulation : A review
TL;DR: In this paper, the basic Kriging assumptions and formulas are presented and compared with classic linear regression metamodels and bootstrapping to estimate the variance of the kriging predictor.
1.1K
Dual-Band Slot Dipole Antenna Fed by a Coplanar Waveguide
You-Chieh Chen,Shih-Yuan Chen,Powen Hsu +2 more
- 09 Jul 2006
TL;DR: In this article, a modified slot dipole antenna fed by a coplanar waveguide for dual-frequency operation is presented, which is formed by placing an additional slot-dipole parallel to the IC antenna and inserting between them a pair of slot apertures shorter than the two slot dipoles.
105
Accurate Design-Oriented Modeling of Compact Microwave Couplers in Constrained Domains
Slawomir Koziel,Ari,Ari T. Siguresson,Freysteinn V. Vidarsson +3 more
- 01 Aug 2018
TL;DR: A technique for defining a surrogate model domain spanned by triangulated reference designs optimized w.r.t. selected figures of interest is described, which allows for dramatic reduction of the size of the design space that need to be samples without formally reducing the geometry parameter ranges.
25
Expedited multi-objective design optimization of miniaturized microwave structures using physics-based surrogates
Slawomir Koziel,Adrian Bekasiewicz,Piotr Kurgan,John W. Bandler +3 more
- 17 May 2015
TL;DR: A methodology for fast multi-objective design optimization of compact microwave circuits is presented, aiming at improving the surrogate model in the vicinity of the Pareto-optimal solutions.
18