HIGH FIDELITY CFD-TRAINED MACHINE LEARNING TO INFORM RANS-MODELLED INTERFACIAL TURBULENCE

Bertolotti, Luc; Jefferson-Loveday, Richard; Ambrose, Stephen; Korsukova, Evgenia

Abstract

In aero-engine bearing chambers, two-phase shearing flows are difficult to predict as Computational Fluid Dynamics (CFD) RANS models tend to overestimate interfacial turbulence levels, leading to inaccuracies in the modelling of the flow. Turbulence damping methods have been developed to address this problem, such as Egorov's correction, however, this method is mesh dependent and results differ considerably according to the choice of turbulence damping coefficient. In addition, this approach assumes a smooth interface between the air and oil phases when in reality they are wavy. In this paper, a Machine Learning method is used to inform an unsteady RANS turbulence modelling. It is trained using high fidelity quasi-DNS simulation data and used to provide an appropriate correction to the popular Wilcox's standard RANS í µí±˜ − í µí¼” turbulence model. The correction consists of a machine learning-predicted source term which is used to adjust the energy budget in the RANS transport equations. Demonstration of the approach is presented for a range of interfacial flow regimes.

Citation

Bertolotti, L., Jefferson-Loveday, R., Ambrose, S., & Korsukova, E. (2022). HIGH FIDELITY CFD-TRAINED MACHINE LEARNING TO INFORM RANS-MODELLED INTERFACIAL TURBULENCE. In Proceedings of Global Power and Propulsion Society. https://doi.org/10.33737/gpps22-tc-30

• Conference Name: GPPS Chania22
• Conference Location: Chania, Greece
• Start Date: Sep 12, 2022
• End Date: Sep 14, 2022
• Acceptance Date: Sep 1, 2022
• Online Publication Date: Sep 28, 2022
• Publication Date: Sep 14, 2022
• Deposit Date: Nov 3, 2022
• Publicly Available Date: Nov 3, 2022
• Series ISSN: 2504-4400
• Book Title: Proceedings of Global Power and Propulsion Society
• DOI: https://doi.org/10.33737/gpps22-tc-30
• Public URL: https://nottingham-repository.worktribe.com/output/13177361
• Publisher URL: https://gpps.global/wp-content/uploads/2022/09/GPPS-TC-2022_paper_30.pdf
• Additional Information: GPPS-TC-2022-0030