Gabriel Achour
(Advisor: Prof. Dimitri Mavris]

will propose a doctoral thesis entitled,

A Multi-Objective Deep Learning Methodology for Morphing Wings

On

Wednesday, June 8 at 2:00 p.m.
Collaborative Visualization Environment (CoVE)
Weber Space Science and Technology Building (SST II)

And

https://bluejeans.com/327559285/7025

Abstract
Conventional aircraft are currently unable to achieve maximum aerodynamic performance when operating under varying missions and weather conditions due to design constraints. One of these constraints is the traditional approach of optimizing aircraft wings to achieve the best average aerodynamic performance for a specific mission while maintaining structural integrity. Previous studies have however shown that changing the shape of wings at different points of a mission profile improves the aerodynamic performance of aircraft. As such, efforts have been made by stakeholders to explore the viability and feasibility of changing or morphing the shape of aircraft wings to enable aircraft to adapt to varying missions and/or weather conditions. However, as with any other aspect of aircraft design, there are challenges that currently exist which hinder the development of conventional aircraft with morphing wings.

First, it is computationally expensive to compute the optimal shapes of aircraft wings for every possible flow condition of a flight a priori as aerodynamic shape optimization requires computationally expensive flow solvers. Furthermore, even though changing the shape of an aircraft’s wing at each segment of a mission profile is the most efficient approach to maximize the benefits of morphing wings, this is not feasible as flight and weather conditions are not constant throughout the flight segment. As such, a framework that can adapt the wing shapes to varying flow conditions during the flight is needed. Second, morphing can lead to a high variation of wing shapes, which can generate high aerodynamic loads and minimize the aerodynamic benefits of morphing wings. As such, a multi-objective framework capable of optimizing morphing wings to increase aerodynamic efficiency while addressing aeroelastic constraints is needed. Finally, a methodology to benchmark the performance of morphing wing aircraft and traditional non-morphing aircraft to identify the more economically viable configuration across different mission profiles is lacking.

Consequently, this thesis aims to address these gaps by 1) developing a Conditional Generative Adversarial Network capable of generating optimal wing shapes and structures of a morphing wing vehicle for each segment of a given mission profile, 2) implementing a Meta Reinforcement Learning agent to make the aircraft wing adapt its shape to any flow condition variation during each mission segment and 3) implementing the notion of shape variation into a mission analysis tool and implement a design of experiment on mission profiles to identify the minimum mission requirements that make morphing vehicles more economically viable than traditional fixed-wing vehicles.

Committee

• Dr. Dimitri Mavris – School of Aerospace Engineering (advisor)
• Dr. Graeme Kennedy – School of Aerospace Engineering
• Dr. Daniel Schrage – School of Aerospace Engineering
• Dr. Woong Je Sung – School of Aerospace Engineering
• Mr. Dino Roman – Chief Aerodynamicist, Advanced Concepts, Boeing Commercial Aircraft