A multi-start aerodynamic shape optimisation approach via multi-fidelity neural networks
Authors:
- Tao ZhangTZTao Zhang
- Mark WoodgateMWMark Woodgate
- George BarakosGBGeorge Barakos
- Yu LuoYLYu Luo
Open Access
- 1 October 2025
- journal article
- Published by Elsevier in Aerospace Science and Technology
- Vol. 168
Abstract
No abstract availableThis publication has 17 references indexed in Scilit:
- High-fidelity aero-acoustic evaluations of a heavy-lift eVTOL in hoverJournal of Sound and Vibration, 2024
- On the aerodynamic performance of redundant propellers for multi-rotor eVTOL in cruiseAerospace Science and Technology, 2023
- Multi-fidelity aerodynamic design and analysis of propellers for a heavy-lift eVTOLAerospace Science and Technology, 2023
- JAXA-ONERA-DLR cooperation: results from rotor optimization in hoverCEAS Aeronautical Journal, 2022
- High-fidelity numerical analysis and optimisation of ducted propeller aerodynamics and acousticsAerospace Science and Technology, 2021
- A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problemsJournal of Computational Physics, 2020
- Application of deep learning based multi-fidelity surrogate model to robust aerodynamic design optimizationAerospace Science and Technology, 2019
- Robust aerodynamic shape optimization—From a circle to an airfoilAerospace Science and Technology, 2019
- Optimisation of Ducted Propellers for Hybrid Air Vehicles Using High-Fidelity CFDThe Aeronautical Journal, 2016
- Matrix formulation of co-krigingMathematical Geology, 1982