• Corpus ID: 251554630

Data-driven modeling of stagnation-line flow with heat and mass transfer in hypersonic reentry

  title={Data-driven modeling of stagnation-line flow with heat and mass transfer in hypersonic reentry},
  author={L. Gkimisis and B. R. Barros Dias and James B. Scoggins and Thierry E. Magin and Miguel Alfonso Mendez and Alessandro Turchi},
The entry phase constitutes a design driver for aerospace systems that include such a critical step. This phase is characterized by hypersonic flows encompassing multiscale phenomena that require advanced modeling capabilities. However, since high fidelity simulations are often computationally prohibitive, simplified models are needed in multidisciplinary analyses requiring fast predictions. This work proposes data-driven surrogate models to predict the flow, and mixture properties along the… 



Duplication of hypersonic stagnation-region aerothermochemistry and gas-surface interaction in high-enthalpy ground testing

Testing thermal protection system materials in ground-based facilities, such as plasma wind tunnels, is a key step in the development of entry vehicles. The Local Heat Transfer Simulation methodology

Challenges and Opportunities for Machine Learning in Fluid Mechanics

How machine learning can be integrated and combined with more classic methods in fluid dynamics is explored, including meshless integration of (partial) differential equations, super-resolution and flow control.

Comparative analysis of machine learning methods for active flow control

A comparative analysis of Genetic Programming and Reinforcement Learning is presented, bench-marking some of their most representative algorithms against global optimization techniques such as Bayesian Optimization (BO) and Lipschitz global optimization (LIPO).

Artificial neural networks modeling of wall pressure spectra beneath turbulent boundary layers

The results show that the ANN outperforms traditional models in adverse pressure gradients, and its predictive capabilities generalize better over the range of investigated conditions.

A Survey of Uncertainty in Deep Neural Networks

A comprehensive introduction to the most crucial sources of uncertainty in neural networks is given and their separation into reducible model uncertainty and not reducible data uncertainty is presented.

Data-Driven Model Order Reduction for Problems with Parameter-Dependent Jump-Discontinuities

  • N. SarnaP. Benner
  • Mathematics, Computer Science
    Computer Methods in Applied Mechanics and Engineering
  • 2021

A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges