Ontology Learning for Systems Engineering Body of Knowledge
Lan Yang, Kathryn Cormican, Ming Yu
Abstract
Extant 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 article, we propose an ontology learning methodology 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 system 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.