Semester

Fall

Date of Graduation

2019

Document Type

Thesis

Degree Type

MS

College

Statler College of Engineering and Mineral Resources

Department

Mechanical and Aerospace Engineering

Committee Chair

Mario Perhinschi

Committee Member

Peter Gall

Committee Member

Patrick Browning

Abstract

A detection and identification scheme for abnormal conditions was developed for an unmanned aerial vehicle (UAV) based on the artificial immune system (AIS) paradigm. This technique involves establishing a body of data to represent normal conditions referred to as “self” and differentiating these conditions from abnormal conditions, referred to as “non-self”. Data collected from simulation of the UAV attempting to autonomously fly a pre-decided trajectory were used to develop and test a scheme that was able to detect and identify aircraft sensor and actuator faults. These faults included aerodynamic control surface locks and damages and angular rate sensor biases. The method used to create the AIS is known as the partition of the universe approach. This approach differs from standard clustering approaches because the universe is divided into uniform partition clusters rather than clustering data using some clustering algorithm. It is simpler and requires less computational resources. This will be the first time that this approach has been applied for use in aerospace engineering. Data collected from nominal flights were used to define self partitions, and the non-self partitions were defined implicitly. The creation scheme is also discussed, involving all software used for simulation, as well as the process of creating the self and the logic behind the detection and identification schemes. The detection scheme was evaluated based on detection rate, detection time, and false alarms for flights under both normal and abnormal conditions. The failure identification scheme was assessed in terms of identification rate and time. Investigation of the proposed technique showed promising results for the cases explored with comparable performance with respect to clustering-based approaches and motivates further research and extension of the proposed methodology toward a more complete health management system.

Download

Share

COinS