Development of hypersonic aircraft and weapon systems has become a critical focus for the Department of Defense to maintain global strike and projection of force capabilities. Despite decades of research, traditional computational fluid dynamics (CFD) methods are either incapable of adequately predicting complex features in hypersonic flows or too expensive to be of practical use for vehicle design in this regime. Therefore, a new modeling methodology is required that approaches the accuracy of scale-resolved CFD simulations at a cost similar to Reynolds-averaged Navier-Stokes (RANS). ATA Engineering, in partnership with the University of Arkansas, proposes a data-driven RANS turbulence closure that uses machine learning (ML) to modify several terms in a standard RANS turbulence model to improve its accuracy in hypersonic flows. The term modifications will use genetically programmed symbolic regression to derive the functional form of each term from scale-resolved CFD data from representative flow configurations. In Phase I, ATA will create and train the ML algorithms and validate the modified turbulence closure against up to three training cases. A detailed development and validation plan to be executed in Phase II will be formulated to expand the prototype model to additional flow configurations and include a laminar-to-turbulent transition model. The proposed ML-based methodology will be packaged as an adaptable, general framework for improving the accuracy of RANS turbulence closures in the hypersonic regime, and it will be known as the HYpersonic Physics-informed Energy-tracing RANS (HYPER) Tuner.
Benefit: Accurate prediction of the performance of hypersonic vehicles hinges on resolving the boundary layer turbulence which directly impacts shockboundary-layer interaction (SBLI), flow separation, and wall heat flux predictions. Typically, resolving the turbulence to sufficient accuracy at the Reynolds numbers and Mach numbers associated with hypersonic flows requires costly scale-resolving simulations. The proposed HYPER Tuner framework for modifying RANS turbulence models will use scale-resolved CFD data to learn trends in the salient mean quantities for these flows, as functions of local dimensionless parameters. The Phase I prototype product will include a modified version of a single RANS turbulence closure trained on multiple flow configurations. As development continues, the envisioned product will incorporate laminar-to-turbulent transition modeling and automated parameter selection to improve usability. The final iteration of the HYPER Tuner framework will also include uncertainty quantification tools for understanding the uncertainty in the predictions of tuned RANS models. HYPER Tuner will be extensible to other RANS turbulence closure varieties, at least one of which will be available in the final software product alongside the original prototype model. HYPER Tuner and the modified RANS turbulence closures it generates will provide a unique capability for accurately capturing the time-averaged effects of turbulence in hypersonic flows without needing to resolve the broad range of spatiotemporal scales.
Keywords: Hypersonics, Hypersonics, shock-boundary layer interaction, Turbulence Modeling, CFD, Machine Learning, heat transfer
