Uncertainty Quantification in Case of Imperfect Models: A Review

TL;DR

This review discusses methods for quantifying uncertainty in complex systems when models are imperfect, emphasizing techniques that incorporate observed data to address model inadequacy, with applications demonstrated in mechanical engineering.

Contribution

It provides a comprehensive review of techniques that account for model imperfections in uncertainty quantification, with practical comparisons in mechanical engineering contexts.

Findings

Techniques effectively incorporate observed data to improve uncertainty estimates.

Comparison of methods highlights strengths and limitations in practical applications.

Illustrative examples demonstrate applicability in mechanical engineering.

Abstract

Uncertainty quantification of complex technical systems is often based on a computer model of the system. As all models such a computer model is always wrong in the sense that it does not describe the reality perfectly. The purpose of this article is to give a review of techniques which use observed values of the technical systems in order to take into account the inadequacy of a computer model in uncertainty quantification. The techniques reviewed in this article are illustrated and compared by applying them to applications in mechanical engineering.