This paper addresses the NASA Langley Research Center’s Multidisciplinary Uncertainty Quantification Challenge problem, which is intended to pose challenges to the uncertainty quantification and robust design communities. The goals of the Multidisciplinary Uncertainty Quantification Challenge problem can be formulated into four main topics that are commonly encountered in the model development process: calibration, sensitivity analysis, extreme-case analysis, and robust design. The analysis presented herein places a particular emphasis on the use of info-gap decision theory to address the goals of the Multidisciplinary Uncertainty Quantification Challenge problem. Info-gap decision theory provides a convenient framework to quantify the effect of uncertainty, herein referred to as robustness, when using simulation models for decision making. Robustness, as defined in the context of info-gap decision theory, is used to pursue calibration, uncertainty propagation, and robust design. Calibration is performed using info-gap decision theory to address the situation whereby deterministic calibration might result in nonunique solutions, meaning that different sets of calibration variables are able to replicate experiments with comparable fidelity. Extreme-case analysis is performed such that the worst-case and best-case performances of the model output are conditioned on the level of uncertainty that is permitted in the simulations. To pursue robust design, the robustness criterion is used to establish whether the amount of uncertainty tolerable in the optimized design is an improvement over the baseline design. Our analysis demonstrates that improving the robustness of the model requires different knowledge than improving the performance of the model. The main conclusion is that the info-gap decision theory provides a sound theoretical basis, and practical implementation, to meet the goals of the NASA Multidisciplinary Uncertainty Quantification Challenge problem without formulating simplifying assumptions.
Robust Decision Making Applied to the NASA Multidisciplinary Uncertainty Quantification Challenge Problem
Journal of Aerospace Information Systems ; 12 , 1 ; 35-48
2015-01-01
Conference paper , Article (Journal)
Electronic Resource
English