Date of Award
3-2025
Document Type
Thesis
Degree Name
Master of Science in Operations Research
Department
Department of Operational Sciences
First Advisor
Nathan B. Gaw, PhD
Abstract
Accurate sensors are critical for ensuring the safety of aircrew. However, detecting faulty sensors remains a significant challenge for the Test Pilot School at Edwards Air Force Base in California. Current methods rely on either student pilots identifying anomalies or waiting for sensors to fail completely before repairs are made—an approach that lacks reliability and consistency. This research aims to address these shortcomings by implementing machine learning techniques to detect sensor faults proactively. To date, applying machine learning to a dataset of this size, encompassing numerous sensors on the same aircraft, is unprecedented. The project focuses on establishing strong baseline models for the T-38 aircraft, with the ultimate goal of creating a scalable framework applicable to all relevant sensors. By leveraging advanced anomaly detection methods, this research paves the way for improved sensor reliability and enhanced operational safety.
AFIT Designator
AFIT-ENS-MS-25-M-195
Recommended Citation
Wekamp, Sydney M., "Machine Learning Techniques to Detect Anomalies in T-38 Flight Sensor Data" (2025). Theses and Dissertations. 8207.
https://scholar.afit.edu/etd/8207
Comments
An embargo was observed for posting this thesis on AFIT Scholar.
This work is marked as Distribution A - Approved for public release. Distribution Unlimited. PA clearance case number on file.