Machine learning and vortex lattice method for surrogate modeling in multi-objective wing optimization

• Grant number: 24/07804-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: August 01, 2024
• Status: Discontinued
• Field of knowledge: Engineering - Aerospace Engineering - Aerodynamics
• Principal Investigator: Gabriel Pereira Gouveia da Silva
• Grantee: Gabriel Clemente Carrari
• Host Institution: Faculdade de Engenharia. Universidade Estadual Paulista (UNESP). Campus Experimental São João da Boa Vista. São João da Boa Vista , SP, Brazil
• Associated scholarship(s): 24/19943-7 - Optimizing effective perceived noise in distributed electric propulsion with neural networks and differential propeller rotation, BE.EP.IC

Abstract

Aircraft designs are inherently multidisciplinary and optimizing one technology individually can negatively affect other equally important technologies. In this way, aircraft designs benefit from multi-objective and multidisciplinary optimizations that can be carried out from the first phases of the project. However, such optimizations can become quite demanding on computational resources the more complex the technology models simulated in the optimization loop are. One solution to increase the efficiency of these optimizations is the use of surrogate models, especially models based on machine learning, which are capable of learning from examples and extracting patterns and behaviors that can be used for prediction and optimization. This work aims to implement surrogate models based on machine learning for optimizing subsonic wings from data obtained by vortex lattice method (VLM).