Satellites Health Monitoring System using Inductive Monitoring Approach
Mohamed Ali Mohamed Abo Arais;
Abstract
Nowadays, satellites are included in our daily activities for several purposes. Once the satellite is launched and enters its orbit, it operates independently, and during orbital flight, the satellites are exposed to a variety of dangers that threaten their mission. Therefore, monitoring the health of satellite systems during missions is essential for the success of satellite missions.
The Thesis discusses traditional satellite health monitoring systems and the new trend of data-driven techniques and proposes an enhancement to the learning module to a data-driven technique called IMS "Inductive monitoring system."
The Thesis is divided into five chapters in addition to lists of contents, tables, figures, and a list of references
Chapter One: Introduces the thesis research topic and gives an overview of the research problem, its motivation, and our research objectives.
Chapter Two: discusses the theoretical background of this Thesis and present the required essential concepts for this research understanding like an introduction to satellites, their design, systems for monitoring their health, and the categories of satellites, introduction to techniques for machine learning, data mining, and comparison, and the algorithms used in each technique, and an explanation of the inductive satellite monitoring system, it is working theory
Chapter Three: discuss the proposed improvement to the learning process of the inductive monitoring system for satellites by comparing the algorithm used for learning which K-means is and proposing a new algorithm, which is One class SVM and Suggested dataset to validate the results by applying it on IRAZU CubeSat telemetry data
Chapter Four: This chapter will explain the practical steps for applying the comparison between learning using the Kmeans algorithm and learning with the One-Class SVM algorithm.
Chapter Five: In this chapter, we will conclude the results, discuss them, and suggest other areas for improvement for future studies to improve the inductive monitoring system.
The Thesis discusses traditional satellite health monitoring systems and the new trend of data-driven techniques and proposes an enhancement to the learning module to a data-driven technique called IMS "Inductive monitoring system."
The Thesis is divided into five chapters in addition to lists of contents, tables, figures, and a list of references
Chapter One: Introduces the thesis research topic and gives an overview of the research problem, its motivation, and our research objectives.
Chapter Two: discusses the theoretical background of this Thesis and present the required essential concepts for this research understanding like an introduction to satellites, their design, systems for monitoring their health, and the categories of satellites, introduction to techniques for machine learning, data mining, and comparison, and the algorithms used in each technique, and an explanation of the inductive satellite monitoring system, it is working theory
Chapter Three: discuss the proposed improvement to the learning process of the inductive monitoring system for satellites by comparing the algorithm used for learning which K-means is and proposing a new algorithm, which is One class SVM and Suggested dataset to validate the results by applying it on IRAZU CubeSat telemetry data
Chapter Four: This chapter will explain the practical steps for applying the comparison between learning using the Kmeans algorithm and learning with the One-Class SVM algorithm.
Chapter Five: In this chapter, we will conclude the results, discuss them, and suggest other areas for improvement for future studies to improve the inductive monitoring system.
Other data
| Title | Satellites Health Monitoring System using Inductive Monitoring Approach | Other Titles | نظام مراقبة صحة عمل الاقمار الصناعية باستخدام نهج المراقبة الاستقرائية | Authors | Mohamed Ali Mohamed Abo Arais | Issue Date | 2021 |
Attached Files
| File | Size | Format | |
|---|---|---|---|
| BB9888.pdf | 1.15 MB | Adobe PDF | View/Open |
Similar Items from Core Recommender Database
Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.