What is it about?
Uncertainty Quantification (UQ) is an important issue in stochastic model updating and model validation. How to give a comprehensive measurement of the difference between the test and simulated data, can significantly influence the outcome of model updating and validation. This work just tries to answer this question.
Featured Image
Why is it important?
This work presents a comprehensive comparison study among the Euclidian distance, Mahalanobis distance, and Bhattacharyya distance to define various UQ metric with different levels of statistical information. Quite interesting results are obtained on the roles of these three distances in model updating and validation.
Perspectives
Clearly, the Bhattacharyya distance is a more novel concept than the typical Euclidian distance in the field of model updating and validation. However, it does not mean the Bhattacharyya is the best one. A combined application on these different concepts should generate better outcomes.
Dr. Sifeng BI
Leibniz Universität Hannover
Read the Original
This page is a summary of: Uncertainty Quantification Metrics with Varying Statistical Information in Model Calibration and Validation, AIAA Journal, October 2017, American Institute of Aeronautics and Astronautics (AIAA),
DOI: 10.2514/1.j055733.
You can read the full text:
Contributors
The following have contributed to this page
