Return to search

Advances in Reduced-Order Modeling Based on Proper Orthogonal Decomposition for Single and Two-Phase Flows

This thesis presents advances in reduced-order modeling based on proper orthogonal decomposition (POD) for single and two-phase flows. Reduced-order models (ROMs) are generated for two-phase gas-solid flows. A multiphase numerical flow solver, MFIX, is used to generate a database of solution snapshots for proper orthogonal decomposition. Time-independent basis functions are extracted using POD from the data, and the governing equations of the MFIX are projected onto the basis functions to generate the multiphase POD-based ROMs. Reduced-order models are constructed to simulate multiphase two-dimensional non-isothermal flow and isothermal flow particle kinetics and three-dimensional isothermal flow. These reduced-order models are applied to three reference cases. The results of this investigation show that the two-dimensional reduced-order models are capable of producing qualitatively accurate results with less than 5 percent error with at least an order of magnitude reduction of computational costs. The three-dimensional ROM shows improvements in computational costs. This thesis also presents an algorithm based on mathematical morphology used to extract discontinuities present in quasi-steady and unsteady flows for POD basis augmentation. Both MFIX and a Reynolds Average Navier-Stokes (RANS) flow solver, UNS3D, are used to generate solution databases for feature extraction. The algorithm is applied to bubbling uidized beds, transonic airfoils, and turbomachinery seals. The results of this investigation show that all of the important features are extracted without loss in accuracy.

Identiferoai:union.ndltd.org:tamu.edu/oai:repository.tamu.edu:1969.1/ETD-TAMU-2010-12-8750
Date2010 December 1900
CreatorsFontenot, Raymond Lee
ContributorsCizmas, Paul
Source SetsTexas A and M University
Languageen_US
Detected LanguageEnglish
Typethesis, text
Formatapplication/pdf

Page generated in 0.0021 seconds