Variable-fidelity model selection for stochastic simulation

• Published in: Reliability engineering & system safety Vol. 131; pp. 40 - 52
• Main Authors: Mullins, Joshua, Mahadevan, Sankaran
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.11.2014; Elsevier
• Subjects: Applied sciences; Blocking; Budgeting; Computational effort; Computer science; control theory; systems; Computer simulation; Crack propagation; Decision theory. Utility theory; Exact sciences and technology; Fracture mechanics (crack, fatigue, damage...); Fundamental areas of phenomenology (including applications); Mathematical models; Mathematics; Model discrepancy; Model selection; Monte Carlo methods; Nonlinearity; Operational research and scientific management; Operational research. Management science; Parametric inference; Physics; Probability and statistics; Resource allocation; Sciences and techniques of general use; Simulation; Software; Solid mechanics; Statistics; Stochastic simulation; Stochasticity; Structural and continuum mechanics; Time dependent simulation; Time dependent simulation; Stochastic simulation; Model discrepancy; Computational effort; Model selection; Resource allocation; Fidelity; Stochastic model; Monte Carlo method; Non linear material; Probabilistic approach; Methodology; Computer simulation; Decision making; Information quantity; Modeling; Crack propagation; Time dependence; Model matching; Non linear model; Budget; Metamodel; Expertise
• ISSN: 0951-8320; 1879-0836
• DOI: 10.1016/j.ress.2014.06.011

This paper presents a model selection methodology for maximizing the accuracy in the predicted distribution of a stochastic output of interest subject to an available computational budget. Model choices of different resolutions/fidelities such as coarse vs. fine mesh and linear vs. nonlinear material model are considered. The proposed approach makes use of efficient simulation techniques and mathematical surrogate models to develop a model selection framework. The model decision is made by considering the expected (or estimated) discrepancy between model prediction and the best available information about the quantity of interest, as well as the simulation effort required for the particular model choice. The form of the best available information may be the result of a maximum fidelity simulation, a physical experiment, or expert opinion. Several different situations corresponding to the type and amount of data are considered for a Monte Carlo simulation over the input space. The proposed methods are illustrated for a crack growth simulation problem in which model choices must be made for each cycle or cycle block even within one input sample.