An Efficient Algorithm for Constructing Optimal Design of Computer Experiments

By Ruichen Jin, Wei Chen, Agus Sudjianto. Design Automation Conference, 2005

730 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Industrial and Manufacturing Engineering, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/e92472e6eedd15688c9e903c6081ada75d2bbc2e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Industrial and Manufacturing Engineering

In Statistics and Probability

Citations in the corpus

Design of computer experiments: A review (2017, background): “These are a few commonly used types of discrepancies, however, the literature discusses a variety of discrepancies and their properties in terms of uniformity and projections of samples [52, 53, 83].”
A novel hybrid MCDM model combining the SAW, TOPSIS and GRA methods based on experimental design (2016, background): “The goal of this optimization process is to design a matrix in which the points are spread as evenly as possible [21].”
Reduced-Order Nonlinear Unsteady Aerodynamic Modeling Using a Surrogate-Based Recurrence Framework (2010, methodology): “In this study, the OLH algorithm from the iSIGHT software package was used [31–33].”
Metamodel based high-fidelity stochastic analysis of composite laminates: A concise review with critical comparative assessment (2017, methodology): “[65] applied simulated annealing to quickly generate optimal sampling points.”
An algorithm for fast optimal Latin hypercube design of experiments (2010, methodology): “[25]: set with maximum number of 20 iterations (but each simulation was allowed to run at most five iterations without improvement of the objective function).”
A non‐stationary covariance‐based Kriging method for metamodelling in engineering design (2007, methodology): “In this example, 18 sampling points are generated using the optimal Latin hypercube approach [32].”
Exploring multi-dimensional spaces: a Comparison of Latin Hypercube and Quasi Monte Carlo Sampling Techniques (2015, methodology): “Different optimality criterion such as entropy, integrated mean square error, minimax and maximin distances, and others can be used for optimizing LHS [3].”
A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality (2017, background): “…of the most common space-filling design methods – e.g. low discrepancy sequences [30–33], good lattice points [34], Latin Hypercube Sampling [35,36] and orthogonal Latin Hypercube Sampling [37] – and classified them according to two metrics, the Maximin (maximizing the minimum Euclidean…”
Computational microstructure characterization and reconstruction: Review of the state-of-the-art techniques (2018, neutral): “…rather than learning the descriptors from a microstructure image, one determines the values of a set of pre-selected descriptors (via, e.g., design of experiments [161–165]) and then proceeds to reconstruct the corresponding virtual microstructures and estimate their properties (via e.g., FEA).”
ORTHOGONAL-MAXIMIN LATIN HYPERCUBE DESIGNS (2008, methodology): “Because there are many designs that maximize the minimum inter-site distance, they proposed an extended definition of the maximin criterion.”
Statistical volume element method for predicting microstructure–constitutive property relations (2008, methodology): “Within the context of these material modeling methodologies and theories, the uncertainties in macroscale properties due to the randomness in microstructure parameters and constituent properties can be quantified via various techniques such as the Monte Carlo method [19], importance sampling [10], L”
Review of Metamodeling Techniques in Support of Engineering Design Optimization (2007, methodology): “[42] applied simulated annealing to quickly generate optimal sampling points and the method has been incorporated into the software iSight TM [43].”
Weighted stochastic response surface method considering sample weights (2011, methodology): “LHD is a computer experiment method which can produce sample points with good space-filling and projective properties ( Jin et al. 2005 ).”
A Python surrogate modeling framework with derivatives (2019, background): “Five construction criteria are available in SMT: four criteria defined in the pyDOE package6 and the enhanced stochastic evolutionary criterion [8].”