Date of Award

4-6-2021

Publication Type

Master Thesis

Degree Name

M.A.Sc.

Department

Electrical and Computer Engineering

First Advisor

Afshin Rahimi

Rights

info:eu-repo/semantics/openAccess

Abstract

A satellite can only complete its mission successfully when all its subsystems, including the attitude control subsystem, are in healthy condition and work properly. Control moment gyroscope is a type of actuator used in the attitude control subsystems of satellites. Any fault in the control moment gyroscope can cause the satellite mission failure if it is not detected, isolated and resolved in-time. Fault isolation provides an opportunity to detect and isolate the occurring faults and, if accompanied by proactive remedial actions, can avoid failure and improve the satellite reliability. It is also necessary to know the fault severity for better maintenance planning and prioritize the corrective actions. This way, the more severe faults can be corrected first. In this work, an enhanced data-driven fault diagnosis scheme is introduced for fault isolation and identification of multiple in-phase faults of satellite control moment gyroscopes that is not addressed in the literature before with high accuracy. The proposed method is based on an optimized support vector machine and an optimized support vector regressor. The results yield fault predictions with up to 95.6% accuracy for isolation and 94.9% accuracy for identification, on average. In addition, a sensitivity analysis with regards to noise, missing values, and missing sensors is done where the results show that the proposed model is robust enough to be used in real applications.

Share

COinS