2000 character limit reached
Physics-constrained Random Forests for Turbulence Model Uncertainty Estimation (2306.13370v2)
Published 23 Jun 2023 in cs.LG and physics.flu-dyn
Abstract: To achieve virtual certification for industrial design, quantifying the uncertainties in simulation-driven processes is crucial. We discuss a physics-constrained approach to account for epistemic uncertainty of turbulence models. In order to eliminate user input, we incorporate a data-driven machine learning strategy. In addition to it, our study focuses on developing an a priori estimation of prediction confidence when accurate data is scarce.
- Presentation of anisotropy properties of turbulence, invariants versus eigenvalue approaches. Journal of Turbulence, 8:N32, 2007. doi: 10.1080/14685240701506896.
- Flow over periodic hills – numerical and experimental study in a wide range of reynolds numbers. Computers & Fluids, 38(2):433 – 457, 2009. ISSN 0045-7930. doi: 10.1016/j.compfluid.2008.05.002.
- Optimization under turbulence model uncertainty for aerospace design. Physics of Fluids, 31(10):105111, 2019.
- Development and application of a cubic eddy-viscosity model of turbulence. International Journal of Heat and Fluid Flow, 17(2):108–115, 1996. ISSN 0142-727X. doi: 10.1016/0142-727X(95)00079-6.
- Model-form uncertainty quantification in RANS simulations of wakes and power losses in wind farms. Renewable Energy, 179:2212–2223, 2021. ISSN 0960-1481. doi: 10.1016/j.renene.2021.08.012.
- Modeling of structural uncertainties in Reynolds-averaged Navier-Stokes closures. Physics of Fluids, 25(11):110822, 2013. doi: 10.1063/1.4824659.
- Emory, M. A. Estimating model-form uncertainty in Reynolds-averaged Navier-Stokes closures. PhD thesis, Stanford University, Department of Mechanical Engineering, 2014.
- Estimating rans model uncertainty using machine learning. Journal of the Global Power and Propulsion Society, 2021(May):1–14, 2021.
- Eigenspace perturbations for uncertainty estimation of single-point turbulence closures. Physical Review Fluids, 2(2):024605, 2017.
- Karniadakis, G. Quantifying uncertainty in CFD. Journal of Fluids Engineering-transactions of the ASME, 124(1):2–3, 03 2002. doi: 10.1115/1.1447925.
- Uncertainty quantification for RANS predictions of wind loads on buildings. In Proceedings of the XV Conference of the Italian Association for Wind Engineering, pp. 402–412, Cham, 2019. Springer International Publishing.
- Direct numerical simulations of converging–diverging channel flow. In Progress in Wall Turbulence: Understanding and Modeling, pp. 203 – 209, 01 2011. doi: 10.1007/978-90-481-9603-6˙21.
- Direct numerical simulation of turbulent channel flow up to 𝑅𝑒τ≈5200subscript𝑅𝑒𝜏5200\mathit{Re}_{{\it\tau}}\approx 5200italic_Re start_POSTSUBSCRIPT italic_τ end_POSTSUBSCRIPT ≈ 5200. Journal of Fluid Mechanics, 774:395–415, 2015. doi: 10.1017/jfm.2015.268.
- Machine learning strategies for systems with invariance properties. Journal of Computational Physics, 318:22–35, 2016.
- Applicability of machine learning in uncertainty quantification of turbulence models, 2022.
- Evaluation of physics constrained data-driven methods for turbulence model uncertainty quantification. Computers & Fluids, pp. 105837, 2023. ISSN 0045-7930. doi: https://doi.org/10.1016/j.compfluid.2023.105837. URL https://www.sciencedirect.com/science/article/pii/S0045793023000622.
- Theoretical analysis of tensor perturbations for uncertainty quantification of reynolds averaged and subgrid scale closures. Physics of Fluids, 31(7):075101, 2019.
- Uncertainty estimation for reynolds-averaged navier–stokes predictions of high-speed aircraft nozzle jets. AIAA Journal, 55(11):3999–4004, 2017.
- Uncertainty estimation module for turbulence model predictions in su2. AIAA Journal, 57(3):1066–1077, 2019.
- Design exploration and optimization under uncertainty. Physics of Fluids, 32(8):085106, 2020.
- On predicting the turbulence-induced secondary flows using nonlinear k-ϵitalic-ϵ\epsilonitalic_ϵ models. Physics of Fluids, 8:1856–1868, 07 1996. doi: 10.1063/1.868968.
- Verification and Validation in Scientific Computing. 01 2010. doi: 10.1017/CBO9780511760396.
- Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830, 2011.
- Rossi, R. Passive scalar transport in turbulent flows over a wavy wall. PhD thesis, Università degli Studi di Bologna, Bologna, Italy, 2006.
- Scott, D. Multivariate density estimation: Theory, practice, and visualization: Second edition. 03 2015. doi: 10.1002/9781118575574.
- Augmentation of Turbulence Models Using Field Inversion and Machine Learning. 2017. doi: 10.2514/6.2017-0993.
- Speziale, C. G. Analytical methods for the development of Reynolds-Stress closures in turbulence. Annual Review of Fluid Mechanics, 23(1):107–157, 1991. doi: 10.1146/annurev.fl.23.010191.000543.
- Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework. Physical Review Fluids, 3(7), Jul 2018. ISSN 2469-990X. doi: 10.1103/physrevfluids.3.074602.
- A priori assessment of prediction confidence for data-driven turbulence modeling. Flow, Turbulence and Combustion, 99(1):25–46, mar 2017. doi: 10.1007/s10494-017-9807-0.
- Quantification of model uncertainty in RANS simulations: A review. Progress in Aerospace Sciences, 108:1–31, 2019. ISSN 0376-0421. doi: 10.1016/j.paerosci.2018.10.001.