Integrated DEsign Automation Laboratory

Integrated DEsign Automation Laboratory

Model Uncertainty Quantification and Validation

Model validation is an important research topic across different domains in science and engineering. In most of the existing work, model validation is achieved by verifying the model accuracy from the perspective of model builder, which requires enormous experimentation resources. To address this challenge, we have been developing a new design-driven model validation framework that combines both computer and physical experiments to improve the confidence of using predictive models in design. As an integral part of this framework, we aim to develop techniques for model uncertainty quantification, validation metrics, and the sequential experimentation strategy to minimize the amount of physical experiments. We have proposed a model updating framework for engineering design and techniques for improving the identifiability of model parameter uncertainty versus model discrepancy uncertainty.

Representative Papers

vide.gif

Integrated DEsign Automation Laboratory

McCormick School of Engineering Home | McCormick Chinese (中文网站) | Contact Us | Maps
Northwestern Home | Northwestern Calendar | Emergency Plan | Legal and Policy Statements
© 2012 Robert R. McCormick School of Engineering and Applied Science, Northwestern University