A Study of Model Validation Method for Dynamic Systems

2010-01-0419

04/12/2010

Event
SAE 2010 World Congress & Exhibition
Authors Abstract
Content
This paper presents an enhanced Bayesian based model validation method together with probabilistic principal component analysis (PPCA). The PPCA is employed to address multivariate correlation and to reduce the dimensionality of the multivariate functional responses. The Bayesian hypothesis testing is used to quantitatively assess the quality of a multivariate dynamic system. Unlike the previous approach, the differences between test and CAE results are used for dimension reduction though PPCA and then to assess the model validity. In addition, physics-based thresholds are defined and transformed to the PPCA space for Bayesian hypothesis testing. This new approach resolves some critical drawbacks of the previous method and provides desirable properties of a validation method, e.g., symmetry. A dynamic system with multiple functional responses is used to demonstrate this new approach.
Meta Tags
Topics
Affiliated or Co-Author
Details
DOI
https://doi.org/10.4271/2010-01-0419
Pages
7
Citation
Fu, Y., Zhan, Z., and Yang, R., "A Study of Model Validation Method for Dynamic Systems," SAE Technical Paper 2010-01-0419, 2010, https://doi.org/10.4271/2010-01-0419.
Additional Details
Publisher
Published
Apr 12, 2010
Product Code
2010-01-0419
Content Type
Technical Paper
Language
English