Building Accurate Emulators for Stochastic Simulations via Quantile Kriging

Computer simulation has increasingly become popular for analysis of systems that cannot be feasibly changed because of costs or scale. This work proposes a method to construct an emulator for stochastic simulations by performing a designed experiment on the simulator and developing an emulative distribution. Existing emulators have focused on estimation of the mean of the simulation output, but this work presents an emulator for the distribution of the output. This construction provides both an explicit distribution and a fast sampling scheme. Beyond the emulator description, this work demonstrates the emulator’s efficiency, that is, its convergence rate is the asymptotically optimal among all possible emulators using the same sample size (under certain conditions). An example of its practical use is demonstrated using a stochastic simulation of fracture mechanics. Supplementary materials for this article are available online.

[1]  H. O. Fuchs,et al.  Metal fatigue in engineering , 2001 .

[2]  C. J. Stone,et al.  Optimal Global Rates of Convergence for Nonparametric Regression , 1982 .

[3]  C. J. Stone,et al.  OPTIMAL GLOBAL RATES OF CONVERGENCE FOR NONPARAMETRIC ESTIMATORS , 1982 .

[4]  Bernhard Schölkopf,et al.  A Generalized Representer Theorem , 2001, COLT/EuroCOLT.

[5]  S. MacEachern,et al.  An ANOVA Model for Dependent Random Measures , 2004 .

[6]  Nadine Gissibl,et al.  Using Proper Divergence Functions to Evaluate Climate Models , 2013, SIAM/ASA J. Uncertain. Quantification.

[7]  G. C. Salivar,et al.  Statistical modeling of fatigue-crack growth in a nickel-base superalloy , 1983 .

[8]  Martin L. Puterman,et al.  The Censored Newsvendor and the Optimal Acquisition of Information , 2002, Oper. Res..

[9]  T. J. Mitchell,et al.  Bayesian Prediction of Deterministic Functions, with Applications to the Design and Analysis of Computer Experiments , 1991 .

[10]  Asok Ray,et al.  Stochastic modeling of fatigue crack dynamics for on-line failure prognostics , 1996, IEEE Trans. Control. Syst. Technol..

[11]  Barry L. Nelson,et al.  Estimating Cycle Time Percentile Curves for Manufacturing Systems via Simulation , 2008, INFORMS J. Comput..

[12]  David Y. Sze,et al.  OR Practice - A Queueing Model for Telephone Operator Staffing , 1984, Oper. Res..

[13]  Harry van Zanten,et al.  Information Rates of Nonparametric Gaussian Process Methods , 2011, J. Mach. Learn. Res..

[14]  G. Matheron.  Principles of geostatistics , 1963 .

[15]  Holger Wendland,et al.  Scattered Data Approximation: Conditionally positive definite functions , 2004 .

[16]  G. Wahba.  Spline models for observational data , 1990 .

[17]  R. Rigby,et al.  Generalized additive models for location, scale and shape , 2005 .

[18]  Xiaohong Chen,et al.  The Estimation of Conditional Densities , 2001 .

[19]  J. Rice,et al.  Smoothing spline models for the analysis of nested and crossed samples of curves , 1998 .

[20]  R. Tibshirani,et al.  Generalized Additive Models , 1986 .

[21]  Victor Picheny,et al.  Quantile-Based Optimization of Noisy Computer Experiments With Tunable Precision , 2013, Technometrics.

[22]  Jianqing Fan,et al.  Estimation of conditional densities and sensitivity measures in nonlinear dynamical systems , 1996 .

[23]  R. Forman,et al.  Numerical Analysis of Crack Propagation in Cyclic-Loaded Structures , 1967 .

[24]  M. Grujicic,et al.  A comparative investigation of the use of laminate-level meso-scale and fracture-mechanics-enriched meso-scale composite-material models in ballistic-resistance analyses , 2010 .

[25]  Jack P. C. Kleijnen.  Design and Analysis of Simulation Experiments , 2007 .

[26]  Russell R. Barton,et al.  Simulation metamodels , 1998, 1998 Winter Simulation Conference. Proceedings (Cat. No.98CH36274).

[27]  Peter Z. G. Qian,et al.  Accurate emulators for large-scale computer experiments , 2011, 1203.2433.

[28]  A. A. Bahashwan.  Effect of stress ratio on fatigue crack growth , 2014 .

[29]  Kazimierz Sobczyk,et al.  Modelling of random fatigue crack growth , 1986 .

[30]  Barry L. Nelson,et al.  Stochastic kriging for simulation metamodeling , 2008, WSC 2008.

[31]  C. Hudson,et al.  Effect of stress ratio on fatigue-crack growth in 7075-T6 aluminum-alloy sheet , 1969 .

[32]  R. Koenker.  Quantile Regression: Name Index , 2005 .

[33]  John R. Rice,et al.  Smoothing Spline Models for the Analysis of Nested and Crossed Samples of Curves: Rejoinder , 1998 .

[34]  N. Pillai,et al.  Bayesian density regression , 2007 .

[35]  P. Diggle,et al.  Model‐based geostatistics , 2007 .

[36]  Thomas J. Santner,et al.  Design and analysis of computer experiments , 1998 .

[37]  Thomas J. Santner,et al.  The Design and Analysis of Computer Experiments , 2003, Springer Series in Statistics.

[38]  Matemática,et al.  Society for Industrial and Applied Mathematics , 2010 .

[39]  Darren J. Wilkinson,et al.  Bayesian Emulation and Calibration of a Stochastic Computer Model of Mitochondrial DNA Deletions in Substantia Nigra Neurons , 2009 .

[40]  Ji Zhu,et al.  Quantile Regression in Reproducing Kernel Hilbert Spaces , 2007 .

[41]  Paul Steinmann,et al.  On local tracking algorithms for the simulation of three-dimensional discontinuities , 2008 .

[42]  Yong-Dong Li,et al.  Fracture analysis on the arc-shaped interface in a layered cylindrical piezoelectric sensor polarized along its axis , 2009 .

[43]  J. Yang,et al.  On statistical moments of fatigue crack propagation , 1983 .