Shahab D. Mohaghegh, Ayodeji Aboaba, Yvon Martinez, Mehrdad Shahnam, Chris Guenther, Yong Liu, 'Chapter 11 - Application of artificial intelligence to computational fluid dynamics', Editor(s): Shuvajit Bhattacharya, Haibin Di, Advances in Subsurface Data Analytics, 2022, https://doi.org/10.1016/B978-0-12-822295-9.00001-7. (https://www.sciencedirect.com/science/article/abs/pii/B9780128222959000017)
Abstract: Smart proxy technology leverages the art and science of artificial intelligence and machine learning in order to build accurate and very fast proxy models for highly complex numerical simulation models. The main characteristics of the smart proxy modeling are (a) physics of the numerical simulation is not reduced or modified, (b) resolution of the numerical simulation is not reduced or modified, (c) detail cell results of the numerical simulation is replicated with high accuracy, and (d) deployment of the smart proxy to provide numerical simulation results for every cell will take few minutes using a laptop or desktop workstation. In this project, smart proxy technology is used to simulate the combustion of natural gas under various conditions such as varying natural gas composition and flow rate, inlet air flow rate and temperature, and outlet pressure in a high-pressure combustion facility (B6 combustor) with more than four million simulation cells.