A machine learning method for transition prediction in hypersonic flows over a cone with angles of attack
Source abstract
Abstract
The prediction of the transition location (TL) in three-dimensional (3D) hypersonic boundary layers is of great importance in hypersonic engineering. In the present work, a method using machine learning techniques is presented for the prediction of TLs based on experiment data over a Mach 6.5 inclined cone. A mapping function is directly constructed between TLs and the circumferential angle θ by neural networks (NNs). The results show that the present NN predicts well for both interpolations of both the angle of attack (AOA) and unit Reynolds number Re0 and extrapolation of only Re0 whereas errors increase for the extrapolation of a higher AOA. This work sheds new light on the fast prediction of TLs in hypersonic complex 3D boundary layers.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fluid Dynamics and Turbulent Flows · Aerodynamics and Acoustics in Jet Flows · Plasma and Flow Control in Aerodynamics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (24)
Show source-provided references
1. Aerodynamic heating in transitional hypersonic boundary layers: Role of second-mode instability10.1063/1.5005529 ↗
2. Transition and stability of high-speed boundary layers10.1146/annurev-fluid-122109-160750 ↗
3. Wall pressure beneath a transitional hypersonic boundary layer over an inclined straight circular cone10.1186/s42774-020-00057-4 ↗
4. Transition prediction of a hypersonic boundary layer over a cone at small angle of attack with the improvement of eN method10.1007/s11433-009-0006-4 ↗
5. Prediction and control of transition in supersonic and hypersonic boundary layers10.2514/3.10292 ↗
6. Direct numerical simulation of hypersonic boundary layer transition over a blunt cone with a small angle of attack10.1063/1.3313933 ↗
7. Engineering model for transition prediction based on a hypersonic quiet wind tunnel10.2514/1.j059054 ↗
8. Machine learning for fluid mechanics10.1146/annurev-fluid-010719-060214 ↗
9. Machine-learning-augmented predictive modeling of turbulent separated flows over airfoils10.2514/1.j055595 ↗
10. Modeling subgrid-scale forces by spatial artificial neural networks in large eddy simulation of turbulence10.1103/physrevfluids.5.054606 ↗
11. Spatial artificial neural network model for subgrid-scale stress and heat flux of compressible turbulence10.1016/j.taml.2020.01.006 ↗
12. Machine learning methods for turbulence modeling in subsonic flows around airfoils10.1063/1.5061693 ↗
13. Improving the k–ω–γ–Ar transition model by the field inversion and machine learning framework10.1063/5.0008493 ↗
14. Artificial neural network-based nonlinear algebraic models for large eddy simulation of turbulence10.1063/5.0025138 ↗
15. Deconvolutional artificial neural network models for large eddy simulation of turbulence10.1063/5.0027146 ↗
16. Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty10.1063/1.4927765 ↗
17. Fast flow field prediction over airfoils using deep learning approach10.1063/1.5094943 ↗
18. Computing mean fields with known Reynolds stresses at steady state10.1016/j.taml.2021.100244 ↗
19. Recurrent neural network for end-to-end modeling of laminar-turbulent transition10.1017/dce.2021.11 ↗
20. Inverse design of airfoil using a deep convolutional neural network10.2514/1.j057894 ↗
21. Efficient aerodynamic shape optimization with deep-learning-based geometric filtering10.2514/1.j059254 ↗
22. Multilayer feedforward networks are universal approximators10.1016/0893-6080(89)90020-8 ↗
23. Boundary-layer transition on cones at angle of attack in a Mach-6 quiet tunnel
24. Hypersonic boundary-layer transition on blunted cones at angle of attack