Text mining and natural language processing for the early stages of space mission design

Thesis

Download PDF

Creator

Rights statement

Awarding institution

Date of award

Thesis identifier

Person Identifier (Local)

Qualification Level

Qualification Name

Department, School or Faculty

Abstract

A considerable amount of data related to space mission design has been accumulated since artificial satellites started to venture into space in the 1950s. This data has today become an overwhelming volume of information, triggering a significant knowledge reuse bottleneck at the early stages of space mission design. Meanwhile, virtual assistants, text mining and Natural Language Processing techniques have become pervasive to our daily life. The work presented in this thesis is one of the first attempts to bridge the gap between the worlds of space systems engineering and text mining. Several novel models are thus developed and implemented here, targeting the structuring of accumulated data through an ontology, but also tasks commonly performed by systems engineers such as requirement management and heritage analysis. A first collection of documents related to space systems is gathered for the training of these methods. Eventually, this work aims to pave the way towards the development of a Design Engineering Assistant (DEA) for the early stages of space mission design. It is also hoped that this work will actively contribute to the integration of text mining and Natural Language Processing methods in the field of space mission design, enhancing current design processes.

Advisor / supervisor