Date of Award

Summer 7-10-2023

Access Type

Thesis - Open Access

Degree Name

Master of Science in Aerospace Engineering

Department

Aerospace Engineering

Committee Chair

Hever Moncayo

Committee Advisor

Hever Moncayo

First Committee Member

Richard Prazenica

Second Committee Member

Richard Stansbury

College Dean

James Gregory

Abstract

Flight test data is a valuable resource used in many aerospace applications. However, procuring a sufficiently large database of flight test data poses several challenges. Nominal flight tests can be expensive and time-consuming and require much post-processing depending on the availability of sensors and the quality of the sensor output. Flight test performed outside of nominal flight conditions, or flight tests in which failures are introduced, add to the inherent risk and danger associated with flight tests. The most popular alternative to flight test, numerical simulations, may fail to fully capture all non-linear behavior. While flight tests will always be required, a method for augmenting an existing database of flight test data with synthetically generated data could help alleviate some of the aforementioned challenges. Over the past few decades, generative machine learning has a emerged as a popular tool for data augmentation. In this thesis, several neural network architectures were investigated as methods of generating synthetic flight data that is consistent with the aircraft dynamics.

Share

COinS