An adaptive grid method and its application to CFD learning and prediction

Author

Becker, William ; Yu, Xinghuo ; Tu, Jiyuan

Author_Institution

Sch. of Aerosp., RMIT Univ., Bundoora, VIC

fYear

2008

fDate

10-13 Nov. 2008

Firstpage

1467

Lastpage

1472

Abstract

A knowledge based engineering system, CFDLearner, which automatically learns results from a number of CFD simulations with a neural network is enhanced to automatically determine the optimum grid resolution where grid independence is found. Simulations are thereafter able to be run at a combination of the optimum grid resolution and lower grid resolutions to decrease the time spent on some simulations at a minor loss of accuracy. The system is explained and tested using single compartment fire simulations.

Keywords

computational fluid dynamics; flow simulation; knowledge based systems; learning (artificial intelligence); mesh generation; neural nets; CFD learning; CFDLearner knowledge based engineering system; adaptive grid method; computational fluid dynamics simulation; fluid flow simulation; neural network; optimum grid resolution; single compartment fire simulation; Aerospace engineering; Application software; Computational fluid dynamics; Computational modeling; Fires; Knowledge engineering; Manufacturing; Neural networks; System testing; Systems engineering and theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Electronics, 2008. IECON 2008. 34th Annual Conference of IEEE

Conference_Location

Orlando, FL

ISSN

1553-572X

Print_ISBN

978-1-4244-1767-4

Electronic_ISBN

1553-572X

Type

conf

DOI

10.1109/IECON.2008.4758170

Filename

4758170