Show simple item record

dc.contributor.advisorCormican, Kathryn
dc.contributor.advisorYu, Ming
dc.contributor.authorYang, Lan
dc.description.abstractSystems engineering (SE) is a multidisciplinary and integrative approach that enables the successful realization of engineered systems. It encompasses fundamentals, principles, and models of foundational systems science, and associated scientific, technological, and management methods for the entire system life cycle. However, the SE body of knowledge is fragmented, as seen from the various guidelines, handbooks, and standards existing in this domain. The lack of a cohesive body of knowledge and shared conceptual framework hinders the mutual understanding of the nature of SE, the practical application of SE approaches, and the sustainable development of the SE discipline. Therefore, the establishment of a common knowledge representation for the entire SE body of knowledge and a shared SE ontology is urgently called for and strongly advocated. This thesis presents a study on the development of a formal ontology for the entire SE body of knowledge using a novel and emerging ontology learning approach. The study was completed using a well-defined scientific process. First, a systematic literature review on relevant cognate studies was carried out to understand the state of the art of ontology development and its application in SE. The literature relating to ontology-based systems engineering (OBSE) was synthesized and analyzed. Then, based on the literature, the gaps and limitations were identified and used to define the research questions and goals. This analysis revealed that manual codification is used to develop SE ontologies, which is tedious, time-consuming, and error-prone. There is a clear need for a formal ontology that depicts the entire body of knowledge. Therefore, to address this gap, this research proposes an ontology learning methodology that takes advantage of natural language processing and machine learning techniques and makes use of existing SE standards to learn an SE ontology derived from available SE knowledge assets. In terms of the development of the SE ontology, three ontology models were developed to portray the conceptual, logical, and data facets. Regarding the validation of the research method, a comprehensive case study was conducted to apply the proposed ontology learning methodology along with the ontology models. From the case study, a formal ontology for the SE body of knowledge was obtained, with a controlled vocabulary of SE terminologies, a concept hierarchy with nine top-level classes, and relations between concepts. To further demonstrate the application scenarios of the ontology, the concepts and relations in the system life cycle processes were separately studied and used for restructuring the life cycle processes more robustly and dynamically. Finally, the thesis incorporates vital learnings and insights to help both academic researchers and practitioners implement a comprehensive and generalizable strategy to create SE ontologies for other application domains or use cases.en_IE
dc.publisherNUI Galway
dc.subjectontology learningen_IE
dc.subjectontology engineeringen_IE
dc.subjectsystems engineeringen_IE
dc.subjectknowledge acquisitionen_IE
dc.subjectknowledge representationen_IE
dc.subjectsystem life cycle processesen_IE
dc.subjectIndustrial Engineeringen_IE
dc.titleOntology learning for systems engineering body of knowledgeen_IE
dc.contributor.funderHardiman Research Scholarship, National University of Ireland Galwayen_IE
dc.local.noteExtant systems engineering standards are so fragmented that the conceptualization of a cohesive body of knowledge is not easy. The discrepancies between different standards lead to misunderstanding and misinterpretation, making communication between stakeholders increasingly difficult. Moreover, these standards remain document centric, whereas systems engineering is transforming from paper-based to a model-based discipline. This requires the use of advanced information exchange schema and digital artifacts to enhance interoperability. Ontologies have been advocated as a mechanism to address these problems, as they can support the model-based transition and formalize the domain knowledge. However, manually creating ontologies is a time-consuming, error-prone, and tedious process. Little has been known about how to automate the development and little work has been conducted for building systems engineering ontologies. Therefore, in this study, an ontology learning methodology is proposed to extract a systems engineering ontology from the extant standards. This methodology employs natural language processing techniques to carry out the lexical and morphological analyses on the standard documents. From the learning process, important terminologies, synonyms, concepts, and relations constructing the systems engineering body of knowledge are automatically recognized and classified. A formal and sophisticated systems engineering ontology is achieved which can be used to harmonize the extant standards, unify the languages, and improve the interoperability of the model-based systems engineering approach.en_IE

Files in this item

Attribution-NonCommercial-NoDerivs 3.0 Ireland
This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. Please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.

The following license files are associated with this item:


This item appears in the following Collection(s)

Show simple item record