Coaxial-Injector Surrogate Modeling Based on Reynolds-Averaged Navier–Stokes Simulations Using Deep Learning

Krügener, Moritz; Usandivaras, José Felix Zapata; Bauerheim, Michaël; Urbano, Annafederica

doi:10.2514/1.b38696

Cited by 9 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1 × 10 -5 ) (1 × 10 typically encountered in such non-convex optimisation problems. The NSGA II algorithm has proven to be efficient in predicting Pareto fronts in fluid mechanics, and has already been coupled to neural networks, as proposed by Krügener et al (2022) to optimise the combustion chamber of a rocket engine. For each generation of the algorithm, a mating pool is formed by selecting individuals from the previous generation population.…”

Section: Liftmentioning

confidence: 99%

“…Nevertheless, for low-dimensional spaces where dense sampling can be achieved, standard training strategies can be sufficient. For instance, Krügener et al (2022) trained an MLP from Reynolds-averaged Navier-Stokes simulations to optimise the geometry of the combustion chamber of a rocket engine on a 10-dimensional space, showing an accurate Pareto front for this configuration. Similarly, Baqué et al (2018) trained a geodesic convolutional neural network (GCNN) to minimise the drag of 3-D objects such as a sphere and a car.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, Krügener et al. (2022) trained an MLP from Reynolds-averaged Navier–Stokes simulations to optimise the geometry of the combustion chamber of a rocket engine on a 10-dimensional space, showing an accurate Pareto front for this configuration. Similarly, Baqué et al.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Discovering optimal flapping wing kinematics using active deep learning

Corban,

Bauerheim,

Jardin

2023

J. Fluid Mech.

View full text Add to dashboard Cite

This paper focuses on the discovery of optimal flapping wing kinematics using a deep learning surrogate model for unsteady aerodynamics and multi-objective optimisation. First, a surrogate model of the unsteady forces experienced by a 3-D flapping wing is built, based on deep neural networks. The model is trained on a dataset of randomly generated kinematics simulated using direct numerical simulation (DNS). Once trained, the neural networks can quickly predict the unsteady lift and torques experienced by the wing, using sparse information on the kinematics. This fast surrogate model allows multi-objective optimisation to be performed. The resulting Pareto front consists of new kinematics that may be very different from the kinematics of the initial dataset. A few arbitrarily chosen kinematics on the Pareto front are thus simulated using DNS and used to enhance the database. The new dataset is used to train again the networks, and this active deep learning/optimisation framework is performed until convergence, obtained after only two iterations. Overall, this method reduced the cost of optimisation by 83 %. Results reveal two distinct families of motions. Kinematics promoting high efficiency are characterised by large stroke amplitudes and relatively low angles of attack, as observed for fruit flies, honeybees or hawkmoths. For those, lift production is driven by quasi-steady effects and the formation of a stable leading edge vortex. Kinematics promoting high lift are characterised by small stroke amplitudes and high angles of attack, reminiscent of mosquitoes. Lift production is driven by the rapid generation of vorticity at the trailing edge.

show abstract

Section: Liftmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discovering optimal flapping wing kinematics using active deep learning

Corban,

Bauerheim,

Jardin

2023

J. Fluid Mech.

View full text Add to dashboard Cite

show abstract

“…The latter modeling toolbox is developed by ONERA, ISAE-Supaero, ICA (CNRS), NASA Glenn and the University of Michigan [26]. Our modeling software is free and open-source and has been used regularly in the aircraft industry, for example with a deep learning model [27][28][29][30] or with a deep gaussian process [31,32].…”

Section: Introductionmentioning

confidence: 99%

A mixed-categorical correlation kernel for Gaussian process

Saves¹,

Diouane²,

Bartoli³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recently, there has been a growing interest for mixed-categorical meta-models based on Gaussian process (GP) surrogates. In this setting, several existing approaches use different strategies either by using continuous kernels (e.g., continuous relaxation and Gower distance based GP) or by using a direct estimation of the correlation matrix. In this paper, we present a kernel-based approach that extends continuous exponential kernels to handle mixedcategorical variables. The proposed kernel leads to a new GP surrogate that generalizes both the continuous relaxation and the Gower distance based GP models. We demonstrate, on both analytical and engineering problems, that our proposed GP model gives a higher likelihood and a smaller residual error than the other kernel-based state-of-the-art models. Our method is available in the open-source software SMT.

show abstract