CNN-based tomographic reconstruction of laser absorption in a gas turbine model combustor
Authors:
- 1 January 2022
- conference paper
- Published by Optica Publishing Group
- p. LF1C.5
Abstract
Tomographic reconstruction of laser absorption of H2O is demonstrated in a swirl-stabilized gas turbine model combustor. Superior reconstruction performance is achieved against conventional methods using a nonlinear regression technique based primarily on convolutional neural networks.Keywords
This publication has 4 references indexed in Scilit:
- Deep neural network inversion for 3D laser absorption imaging of methane in reacting flowsOptics Letters, 2020
- Chemical species tomography of turbulent flows: Discrete ill-posed and rank deficient problems and the use of prior informationJournal of Quantitative Spectroscopy and Radiative Transfer, 2016
- High-speed chemical species tomography in a multi-cylinder automotive engineChemical Engineering Journal, 2010
- Detailed characterization of the dynamics of thermoacoustic pulsations in a lean premixed swirl flameCombustion and Flame, 2007