Filters








11,316 Hits in 4.9 sec

Large scale variable fidelity surrogate modeling

A. Zaytsev, E. Burnaev
2017 Annals of Mathematics and Artificial Intelligence  
and coarse approximation of the same physical phenomenon) while constructing a surrogate model.  ...  Engineers widely use Gaussian process regression framework to construct surrogate models aimed to replace computationally expensive physical models while exploring design space.  ...  However, as far as we know there are no approaches to large scale variable fidelity Gaussian process regression in case of data without any specific structure.  ... 
doi:10.1007/s10472-017-9545-y fatcat:bm2rs3p3z5el5kkswqoczu4mhi

Multi-Fidelity Surrogate Based on Single Linear Regression [article]

Yiming Zhang, Nam-Ho Kim, Chanyoung Park, Raphael T. Haftka
2017 arXiv   pre-print
The key idea is to consider the low-fidelity model as a basis function in the multi-fidelity model with the scale factor as a regression coefficient.  ...  Besides enabling efficient estimation of the parameters, the proposed least-squares multi-fidelity surrogate (LS-MFS) can be applicable to other regression models by simply replacing the design matrix.  ...  Numerical performance of the least-squares multi-fidelity surrogate We selected an exponential function [8, 9] with two variables to test the LS-MFS. The high-fidelity model   H f x is given in Eq  ... 
arXiv:1705.02956v1 fatcat:namjvmz5vfd2zguutfho2qop3m

Computational Optimization, Modelling and Simulation: Smart Algorithms and Better Models

Xin-She Yang, Slawomir Koziel, Leifur Leifsson
2012 Procedia Computer Science  
This third workshop on Computational Optimization, Modelling and Simulation (COMS 2012) at ICCS 2012 will further summarize the latest developments of optimization and modelling and their applications  ...  models for variable-fidelity and variable-resolution optimization techniques.  ...  Variable-fidelity SBO (also referred to as multi-fidelity SBO) uses low-fidelity models and suitable correction techniques to construct the surrogates [11] .  ... 
doi:10.1016/j.procs.2012.04.091 fatcat:odx5nxavpfgahfbtsz3mx66an4

Multi-fidelity wake modelling based on Co-Kriging method

Y M Wang, P-E Réthoré, M P van der Laan, J P Murcia Leon, Y Q Liu, L Li
2016 Journal of Physics, Conference Series  
Both the univariate and multivariate based surrogate models are established by taking the local wind speed and wind direction as variables of the wind farm power efficiency function.  ...  The analysis shows that the multi-fidelity wake models could tremendously reduce the high fidelity model evaluations needed in building an accurate surrogate.  ...  By taking a large amount of low fidelity model results and only a few high fidelity model results to increase the accuracy of the surrogate model, the multifidelity method can significantly reduce the  ... 
doi:10.1088/1742-6596/753/3/032065 fatcat:zm57xbzjqrgqbimvrb44ztqewy

Computational Optimization, Modelling and Simulation: Recent Trends and Challenges

Xin-She Yang, Slawomir Koziel, Leifur Leifsson
2013 Procedia Computer Science  
We will discuss important topics for further research, including parameter-tuning, large-scale problems, and the gaps between theory and applications.  ...  However, many challenging issues remain unresolved, and the current trends tend to use nature-inspired algorithms and surrogate-based techniques for modelling and optimization.  ...  Will the methodology for small-scale problems scale up and works equally well for large-scale problems? What is the best way to construct a good surrogate model for a given problem?  ... 
doi:10.1016/j.procs.2013.05.250 fatcat:bg4clzm2bfbtnpsmysh5clpx4q

Multifidelity Surrogate Modeling of Experimental and Computational Aerodynamic Data Sets

Yuichi Kuya, Kenji Takeda, Xin Zhang, Alexander I. J. Forrester
2011 AIAA Journal  
This study highlights how lowfidelity data from computations contribute to improving surrogate models built with limited high-fidelity data from experiments.  ...  This study presents a multifidelity surrogate modeling approach, combining experimental and computational aerodynamic data sets. A multifidelity cokriging regression surrogate model is used.  ...  data to refine the low-fidelity surrogate model.  ... 
doi:10.2514/1.j050384 fatcat:mvamam7kuja63psi4o327pdf2e

Research on multi-fidelity aerodynamic optimization methods

Likeng Huang, Zhenghong Gao, Dehu Zhang
2013 Chinese Journal of Aeronautics  
Co-Kriging method can use a greater quantity of low-fidelity information to enhance the accuracy of a surrogate of the high-fidelity model by modeling the correlation between high and low fidelity model  ...  In this paper, using co-Kriging method, an efficient multifidelity surrogate model is constructed based on two independent high and low fidelity samples.  ...  Research on multi-fidelity aerodynamic optimization methods  ... 
doi:10.1016/j.cja.2013.02.004 fatcat:3vz5kr7ko5hvzj5l7itas7zvwa

Multi-Fidelity Aerodynamic Data Fusion with a Deep Neural Network Modeling Method

Lei He, Weiqi Qian, Tun Zhao, Qing Wang
2020 Entropy  
A fusion model of the longitudinal coefficients of lift CL and drag CD was constructed with the proposed method. For comparisons, variable complexity modeling and cokriging models were also built.  ...  We discuss the relationships between the low-fidelity and high-fidelity data, and then we describe the proposed architecture for an aerodynamic data fusion model.  ...  However, most surrogate models still have limitations in dealing with high-dimensional problems or large scale data [16] .  ... 
doi:10.3390/e22091022 pmid:33286791 pmcid:PMC7597116 fatcat:ouqcgrzzcnf5pcnqotldvrp4um

Model Updating Strategy of the DLR-AIRMOD Test Structure

Edoardo Patelli, Matteo Broggi, Yves Govers, John E. Mottershead
2017 Procedia Engineering  
This paper presents a high fidelity surrogate model that allows to significantly reduce the computational costs associated with the Bayesian model updating technique.  ...  This paper presents a high fidelity surrogate model that allows to significantly reduce the computational costs associated with the Bayesian model updating technique.  ...  The availability of high fidelity surrogate models allows the implementation of stochastic model updating on large scale complex models allowing taking into account the unavailable variability of parameters  ... 
doi:10.1016/j.proeng.2017.09.221 fatcat:wve33tfg6ndmdobbzbdcqm3a64

A Step Towards Efficient Evaluation of Complex Perception Tasks in Simulation [article]

Jonathan Sadeghi, Blaine Rogers, James Gunn, Thomas Saunders, Sina Samangooei, Puneet Kumar Dokania, John Redford
2021 arXiv   pre-print
In this work, we propose an approach that enables efficient large-scale testing using simplified low-fidelity simulators and without the computational cost of executing expensive deep learning models.  ...  However, characterising such behaviour usually requires large-scale testing of the model that can be extremely computationally expensive for complex real-world tasks.  ...  Acknowledgments and Disclosure of Funding We are grateful to all colleagues at Five who have contributed to insightful discussions about Perception Error Models, including Philip Torr, Andrew Blake, Simon  ... 
arXiv:2110.02739v2 fatcat:eby6vdwgpjasle7y4myaadwywi

Coarse-Grid Computational Fluid Dynamic (CG-CFD) Error Prediction using Machine Learning [article]

Botros N Hanna, Nam T. Dinh, Robert W. Youngblood, Igor A. Bolotnov
2017 arXiv   pre-print
Hence, a method is suggested to produce a surrogate model that predicts the CG-CFD local errors to correct the variables of interest.  ...  Given high-fidelity data, a surrogate model is trained to predict the CG-CFD local errors as a function of the coarse grid local features.  ...  In LES, the large-scale motions (energycontaining eddies) are captured, while the small-scale flow motions are either modelled using an explicit sub-grid scale model, or implicitly modeled using the numerical  ... 
arXiv:1710.09105v1 fatcat:c4bvns7nzfdm7ayby2e6b5m7zi

An adaptive surrogate modeling based on deep neural networks for large-scale Bayesian inverse problems [article]

Liang Yan, Tao Zhou
2020 arXiv   pre-print
scale problems.  ...  In particular, in the refine procedure, we construct a new shallow neural network that view the previous constructed surrogate as an input variable -- yielding a composite multi-fidelity neural network  ...  This motivate the present work: we shall present an adaptive multi-fidelity deep neural networks (DNNs) based surrogate modeling for large-scale BIPs, motivated by the facts that DNNs can potentially handle  ... 
arXiv:1911.08926v2 fatcat:ckekmjp3obemvlvpm3can2gfiu

Customized data-driven RANS closures for bi-fidelity LES-RANS optimization [article]

Yu Zhang and Richard P. Dwight and Martin Schmelzer and Javier F. Gomez and Stefan Hickel and Zhong-hua Han
2020 arXiv   pre-print
- and low-fidelity models within a hierarchical-Kriging surrogate modelling framework.  ...  In this article, we propose an efficient bi-fidelity shape optimization method for turbulent fluid-flow applications with Large-Eddy Simulation (LES) and Reynolds-averaged Navier-Stokes (RANS) as the high  ...  Then a surrogate for the high-fidelity cost function is built using the scaled low-fidelity Kriging model̂ Low as the model trend.  ... 
arXiv:2004.03003v1 fatcat:col4pvxqkjbljcl5e54aivpdxy

On Rapid Re-Design of UWB Antennas with Respect to Substrate Permittivity

Slawomir Koziel, Adrian Bekasiewicz
2016 Metrology and Measurement Systems  
The surrogate is set up at the level of coarse-discretization EM simulation model of the antenna and, subsequently, corrected to provide prediction at the high-fidelity EM model level.  ...  The proposed approach is based on inverse surrogate modeling with the scaling model constructed for several reference designs that are optimized for selected values of the substrate permittivity.  ...  Dimension prediction of scaled design The surrogate model is created using low-fidelity model reference designs so that it has to be corrected before being used for scaling the antenna dimensions at the  ... 
doi:10.1515/mms-2016-0051 fatcat:6w6jylhgfzg77bm36wpipccjoy

Review of surrogate modeling in water resources

Saman Razavi, Bryan A. Tolson, Donald H. Burn
2012 Water Resources Research  
Two broad families of surrogates namely response surface surrogates, which are statistical or empirical data-driven models emulating the high-fidelity model responses, and lower-fidelity physically based  ...  A wide variety of methods and tools have been introduced for surrogate modeling aiming to develop and utilize computationally more efficient surrogates of high-fidelity models mostly in optimization frameworks  ...  There are two broad families under the large umbrella of surrogate modeling, response surface modeling and lower-fidelity modeling.  ... 
doi:10.1029/2011wr011527 fatcat:rvib7d3zhjei3olhldarvpyhpy
« Previous Showing results 1 — 15 out of 11,316 results