Training a Neural-Network-Based Surrogate Model for Aerodynamic Optimisation Using a Gaussian Process

DOI10.1080/10618562.2022.2138863OpenAlexW4319981052MaRDI QIDQ5880409

Charbel Farhat, Nahla Alhazmi, Radek Tezaur, Unnamed Author

Publication date: 2 March 2023

Published in: International Journal of Computational Fluid Dynamics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/10618562.2022.2138863

zbMATH Keywords

Gaussian processsupervised learningcross-validationactive learningadaptive samplingpressure coefficientneural network regressioncambered NACA airfoil

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Flow control and optimization for compressible fluids and gas dynamics (76N25) Basic methods in fluid mechanics (76M99)

Uses Software

• L-BFGS
• SPACE
• Scikit
• PyTorch

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the limited memory BFGS method for large scale optimization
• Many regression algorithms, one unified model: a review
• Application of a three-field nonlinear fluid-structure formulation to the prediction of the aeroelastic parameters of an F-16 fighter
• Bayesian learning for neural networks
• Applying Bayesian optimization with Gaussian process regression to computational fluid dynamics problems
• Universality of deep convolutional neural networks
• Random sampling with a reservoir
• Advanced Lectures on Machine Learning
• Wide neural networks of any depth evolve as linear models under gradient descent ^*
• The origins of kriging

This page was built for publication: Training a Neural-Network-Based Surrogate Model for Aerodynamic Optimisation Using a Gaussian Process