Published 6 issues per year
ISSN Print: 2152-5080
ISSN Online: 2152-5099
Indexed in
BIAS MINIMIZATION IN GAUSSIAN PROCESS SURROGATE MODELING FOR UNCERTAINTY QUANTIFICATION
ABSTRACT
Uncertainty quantification analyses often employ surrogate models as computationally efficient approximations of computer codes simulating the physical phenomena. The accuracy and economy in the construction of surrogate models depends on the quality and quantity of data collected from the computationally expensive system models. Computationally efficient methods for accurate surrogate model training are thus required. This paper develops a novel approach to surrogate model construction based on the hierarchical decomposition of the approximation error. The proposed algorithm employs sparse Gaussian processes on a hierarchical grid to achieve a sparse nonlinear approximation of the underlying function. In contrast to existing methods, which are based on minimizing prediction variance, the proposed approach focuses on model bias and aims to improve the quality of reconstruction represented by the model. The performance of the algorithm is compared to existing methods using several numerical examples. In the examples considered, the proposed method demonstrates significant improvement in the quality of reconstruction for the same sample size.
-
Pau George Shu Heng, Zhang Yingqi, Finsterle Stefan, Reduced order models for many-query subsurface flow applications, Computational Geosciences, 17, 4, 2013. Crossref
-
Bogdanor Michael, Crouch Robert D., Clay Stephen B., Oskay Caglar, Modeling Rate Dependent Damage Evolution in Composite Structures, 54th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, 2013. Crossref
-
Sankararaman Shankar, McLemore Kyle, Mahadevan Sankaran, Bradford Samuel Case, Peterson Lee D., Test Resource Allocation in Hierarchical Systems Using Bayesian Networks, AIAA Journal, 51, 3, 2013. Crossref
-
Strachan Alejandro, Mahadevan Sankaran, Hombal Vadiraj, Sun Lin, Functional derivatives for uncertainty quantification and error estimation and reduction via optimal high-fidelity simulations, Modelling and Simulation in Materials Science and Engineering, 21, 6, 2013. Crossref
-
Liang Chen, Mahadevan Sankaran, Bayesian Sensitivity Analysis and Uncertainty Integration for Robust Optimization, Journal of Aerospace Information Systems, 12, 1, 2015. Crossref
-
Xu Peida, Su Xiaoyan, Mahadevan Sankaran, Li Chenzhao, Deng Yong, A non-parametric method to determine basic probability assignment for classification problems, Applied Intelligence, 41, 3, 2014. Crossref
-
Mullins Joshua, Mahadevan Sankaran, Variable-fidelity model selection for stochastic simulation, Reliability Engineering & System Safety, 131, 2014. Crossref
-
Mullins Joshua G., Mahadevan Sankaran, Computational Effort vs. Accuracy Tradeoff in Uncertainty Quantification, 16th AIAA Non-Deterministic Approaches Conference, 2014. Crossref
-
Bogdanor Michael J., Oskay Caglar, Clay Stephen B., Multiscale modeling of failure in composites under model parameter uncertainty, Computational Mechanics, 56, 3, 2015. Crossref
-
Nannapaneni Saideep, Mahadevan Sankaran, Reliability analysis under epistemic uncertainty, Reliability Engineering & System Safety, 155, 2016. Crossref
-
Hu Zhen, Mahadevan Sankaran, A surrogate modeling approach for reliability analysis of a multidisciplinary system with spatio-temporal output, Structural and Multidisciplinary Optimization, 56, 3, 2017. Crossref
-
Hu Zhen, Mourelatos Zissimos, Efficient Global Surrogate Modeling Based on Multi-Layer Sampling, SAE International Journal of Materials and Manufacturing, 11, 4, 2018. Crossref
-
Absi Ghina N., Mahadevan Sankaran, Simulation Resource Optimization for Multi-Fidelity Model Calibration, AIAA Scitech 2019 Forum, 2019. Crossref
-
Hu Zhen, Mahadevan Sankaran, Adaptive Surrogate Modeling for Time-Dependent Multidisciplinary Reliability Analysis, Journal of Mechanical Design, 140, 2, 2018. Crossref
-
Neal Kyle, Hu Zhen, Mahadevan Sankaran, Zumberge Jon, Discrepancy Prediction in Dynamical System Models Under Untested Input Histories, Journal of Computational and Nonlinear Dynamics, 14, 2, 2019. Crossref
-
Liang Chen, Mahadevan Sankaran, Sankararaman Shankar, Stochastic Multidisciplinary Analysis Under Epistemic Uncertainty, Journal of Mechanical Design, 137, 2, 2015. Crossref
-
Sankararaman Shankar, Mahadevan Sankaran, Bayesian Methodology for Uncertainty Quantification in Complex Engineering Systems, in Numerical Methods for Reliability and Safety Assessment, 2015. Crossref
-
Absi Ghina N., Mahadevan Sankaran, Simulation and Sensor Optimization for Multifidelity Dynamics Model Calibration, AIAA Journal, 58, 2, 2020. Crossref
-
Nath Paromita, Olson Joseph D., Mahadevan Sankaran, Lee Yung-Tsun Tina, Optimization of fused filament fabrication process parameters under uncertainty to maximize part geometry accuracy, Additive Manufacturing, 35, 2020. Crossref
-
Whelan Gary, McDowell David L., Machine Learning-Enabled Uncertainty Quantification for Modeling Structure–Property Linkages for Fatigue Critical Engineering Alloys Using an ICME Workflow, Integrating Materials and Manufacturing Innovation, 9, 4, 2020. Crossref
-
Kotha Shravan, Ozturk Deniz, Smarslok Benjamin, Ghosh Somnath, Uncertainty Quantified Parametrically Homogenized Constitutive Models for Microstructure-Integrated Structural Simulations, Integrating Materials and Manufacturing Innovation, 9, 4, 2020. Crossref
-
Wang Xin, Duan Jiangyong, Yan Zhen, Prediction of Data Stream Based on Gaussian Process Regression with Online Free Variational Inference Approximation, IOP Conference Series: Materials Science and Engineering, 569, 5, 2019. Crossref
-
Ozturk Deniz, Kotha Shravan, Ghosh Somnath, An uncertainty quantification framework for multiscale parametrically homogenized constitutive models (PHCMs) of polycrystalline Ti alloys, Journal of the Mechanics and Physics of Solids, 148, 2021. Crossref
-
Xiao Cong, Tian Leng, Surrogate‐Based Joint Estimation of Subsurface Geological and Relative Permeability Parameters for High‐Dimensional Inverse Problem by Use of Smooth Local Parameterization, Water Resources Research, 56, 7, 2020. Crossref
-
Römer Ulrich, Liu Jintian, Böl Markus, Surrogate‐based Bayesian calibration of biomechanical models with isotropic material behavior, International Journal for Numerical Methods in Biomedical Engineering, 38, 4, 2022. Crossref
-
Kapusuzoglu Berkcan, Mahadevan Sankaran, Matsumoto Shunsaku, Miyagi Yoshitomo, Watanabe Daigo, Adaptive surrogate modeling for high-dimensional spatio-temporal output, Structural and Multidisciplinary Optimization, 65, 10, 2022. Crossref