A machine learning method for transition prediction in hypersonic flows over a cone with angles of attack

Meng, Deying; Shi, Mingtao; Shi, Yipeng; Zhu, Yiding

doi:10.1063/5.0077734

Cited by 7 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the complex transition mechanism has achieved much attention, and the calculation and prediction of the transition is the key factor in the design of the aircraft. In recent years, with the development of algorithms and the accumulation of transition data, boundary layer transition modeling methods incorporating machine learning have gradually developed [99,101,102,[114][115][116][117]. Transition theories, models, and methods through artificial intelligence have been established to promote the intelligent application of fluid mechanics to overcome the lack of theory and experience.…”

Section: Transition Modeling and Turbulence Modelingmentioning

confidence: 99%

“…Li et al [114] trained a model to identify the turbulent/non-turbulent interface in the flow past a circular cylinder by machine learning method. Meng et al [115] validated the effectiveness of prediction neural networks-model of transition location in three-dimensional (3D) hypersonic boundary layers. Besides the application of machine learning model for transition location determination, it is also critical to improve the predictive performance of conventional transition models by constructing advanced models for Reynolds-averaged simulations.…”

Section: Transition Modeling and Turbulence Modelingmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Intelligent Airfoil Aerodynamic Optimization Methods Based on Data-Driven Advanced Models

Wang,

Zhang,

Wang

et al. 2024

Mathematics

View full text Add to dashboard Cite

With the rapid development of artificial intelligence technology, data-driven advanced models have provided new ideas and means for airfoil aerodynamic optimization. As the advanced models update and iterate, many useful explorations and attempts have been made by researchers on the integrated application of artificial intelligence and airfoil aerodynamic optimization. In this paper, many critical aerodynamic optimization steps where data-driven advanced models are employed are reviewed. These steps include geometric parameterization, aerodynamic solving and performance evaluation, and model optimization. In this way, the improvements in the airfoil aerodynamic optimization area led by data-driven advanced models are introduced. These improvements involve more accurate global description of airfoil, faster prediction of aerodynamic performance, and more intelligent optimization modeling. Finally, the challenges and prospect of applying data-driven advanced models to aerodynamic optimization are discussed.

show abstract

Section: Transition Modeling and Turbulence Modelingmentioning

confidence: 99%

Section: Transition Modeling and Turbulence Modelingmentioning

confidence: 99%

A Review of Intelligent Airfoil Aerodynamic Optimization Methods Based on Data-Driven Advanced Models

Wang,

Zhang,

Wang

et al. 2024

Mathematics

View full text Add to dashboard Cite

show abstract

On the identification of cross-flow mode in three-dimensional boundary layers

Liu

2023

AIP Advances

View full text Add to dashboard Cite

Parametric zones are obtained where the cross-flow instability can be identified as a mode in the three-dimensional boundary layers with the Mach number ranging from 0 to 10. Although the term cross-flow mode is widely used in the investigations on boundary-layer instability, the previous work [Z. Liu, Phys. Fluids 34, 094110 (2022)] has demonstrated that a cross-flow mode cannot be designated in certain circumstances. The identification of the cross-flow mode is significant not only in the justifiable use of the term but also in judging whether a disturbance is more inclined to a cross-flow type or not. In this work, a criterion is built to identify the cross-flow mode based on the growth-rate peak and disturbance shape. By means of extensive calculations and identifications, parametric zones are presented for the unstable cross-flow mode. It is found that the cross-flow mode cannot be identified at large local sweep or at Mach numbers larger than 1.6. In parametric zones, the cross-flow mode can be distinguished from the Tollmien–Schlichting mode, or identified as the solely dominant mode. Based on the identifications, the maximum growth rates of the cross-flow mode, the Tollmien–Schlichting mode, and the Mack modes in the three-dimensional boundary layers are provided. The dominant mode can be determined at different Mach numbers. The cross-flow mode is revealed to dominate the boundary-layer instability at low Mach numbers. Under large cross-flow strengths, the second mode could not be the dominant mode in the hypersonic boundary layers, which contrasts sharply with the two-dimensional case.

show abstract

Fast flow prediction of airfoil dynamic stall based on Fourier neural operator

Meng,

Zhu,

Wang

et al. 2023

Physics of Fluids

View full text Add to dashboard Cite

Dynamic stall on airfoil is of great importance in engineering applications. In the present work, Fourier neural operator (FNO) is applied to predict flow fields during the dynamic stall process of the NACA0012 airfoil. Two cases with different angles of attack are simulated by Reynolds averaged numerical simulation with the Spalart–Allmaras (SA) model at Re=4×104. A prediction model is directly constructed between the flow fields at several previous time nodes and that at the future time node by FNO. The prediction of sequence flow fields based on the iterative prediction strategy is achieved for the dynamic stall. The results show that FNO can achieve a fast and accurate prediction of streamwise velocity, normal velocity, pressure, and vorticity for both cases. The dynamics of vortices around the airfoil is analyzed to demonstrate the prediction accuracy of FNO. In addition, FNOs with different configurations are tested to achieve a lower error and a shorter training time-consuming.

show abstract

A machine learning method for transition prediction in hypersonic flows over a cone with angles of attack

Cited by 7 publications

References 22 publications

A Review of Intelligent Airfoil Aerodynamic Optimization Methods Based on Data-Driven Advanced Models

A Review of Intelligent Airfoil Aerodynamic Optimization Methods Based on Data-Driven Advanced Models

On the identification of cross-flow mode in three-dimensional boundary layers

Fast flow prediction of airfoil dynamic stall based on Fourier neural operator

Contact Info

Product

Resources

About