A DEEP LEARNING BASED MODEL FOR IDENTIFYING RECIRCULATION ZONES FROM EXPERIMENTAL IMAGES OF TRAPPED VORTEX COMBUSTORS

Dash, P and Mallik, T and Verma, N and Choudhury, AR and Ravikrishna, RV and Aditya, K (2024) A DEEP LEARNING BASED MODEL FOR IDENTIFYING RECIRCULATION ZONES FROM EXPERIMENTAL IMAGES OF TRAPPED VORTEX COMBUSTORS. In: 69th ASME Turbo Expo 2024: Turbomachinery Technical Conference and Exposition, GT 2024, 24 June 2024 through 28 June 2024, London.

PDF Tur_Tec_Con_and_Exp_GT_2024.pdf - Published Version Restricted to Registered users only Download (10MB) | Request a copy

Abstract

Particle image velocimetry (PIV) is a standard method for studying primary recirculation zones in trapped vortex combustors (TVCs), which can operate in an RQL configuration. However, its intrusive nature can disrupt the flow, flame, and equipment in compact combustors, leading to inaccuracies. As an alternative, we use deep learning models based on generative adversarial networks (GAN, a widely used approach) and vision transformers (ViT, a recently devised promising architecture) to estimate the position and overall structure of large-scale vortices from a non-invasively measured quantity, such as the planar laser-induced fluorescence (PLIF) of a species. These models are trained using datasets from large-eddy simulations (LES) of TVCs with information regarding all scalars constituting the state variable, with the addition of noise to mimic experimental data. Quantitative metrics such as relative errors and PDFs of velocity components and their orientation have been used to demonstrate that the ViT exhibits better performance than the GAN. Sensitivity to the type of noise added to simulation data during training is studied as well. The trained model is then used to infer velocity vectors from noisy OH-PLIF data. In the absence of ground truth for that case, qualitative observations reinforce our earlier notion of the superiority of ViT. Such models will facilitate intelligent data fusion and the development of digital twins of combustors. Copyright © 2024 by ASME.

Item Type:	Conference Paper
Publication:	Proceedings of the ASME Turbo Expo
Publisher:	American Society of Mechanical Engineers (ASME)
Additional Information:	The copyright for this article belongs to the publishers.
Keywords:	Combustors; Gas turbines; Hadrons; Photons; Radial basis function networks, Adversarial networks; Deep learning; Image velocimetry; Learning Based Models; Machine-learning; Particle images; Planar laser-induced fluorescence; Recirculation zones; Transformer; Trapped vortex combustor, Vortex flow
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences Division of Mechanical Sciences > Mechanical Engineering
Date Deposited:	06 Nov 2024 17:33
Last Modified:	06 Nov 2024 17:33
URI:	http://eprints.iisc.ac.in/id/eprint/86733

Actions (login required)

View Item