Effect of mesh refinement on the solution of the inverse uncertainty quantification problem for transient physics

摘要

In this paper, effect of mesh refinement on the solution of the IUQ problem for transient physics was studied. Two mathematical formulations, the Maximum Likelihood Estimate (MLE) and the Maximum A Posterior (MAP), were adopted to solve the IUQ problem. Global Sensitivity Analysis (GSA) and Local Sensitivity Analysis (LSA) were performed to provide the necessary data for MLE and MAP implementation. TRACE models with three different mesh numbers based on the transient Flooding Experiment with Blocked Array (FEBA) benchmark were developed. Results of this analysis show that statistical expectation of the physical models (statistical mean) tends to shift towards a certain value with mesh refinement. This shifting behavior can be related to the decrease in the truncation error resulting from numerical discretization due to mesh refinement, consequently, compensating for the mismatch between experimental data and code prediction results that may be falsely credited to the uncertainties inherent in the physical models. Moreover, the results show that the relative absolute error between experimental data and code prediction results was decreased upon incorporating the input parameter uncertainties that were determined based on MLE and MAP formulations. In all cases, the error was smallest for the most refined mesh.