A Methodology for Knowledge Integration and Acquisition in Model-Based Systems Engineering

In Model-Based System Engineering (MBSE) systems are represented as models using a predefined metalanguage such as SysML that hides some of the complexity behind the specification of a system, and provides experts with a rich syntax to define, share and constrain these models.Even though current MBSE design tools are sophisticated and support expressive meta-languages, these tools have limited capabilities on the detection of semantic errors, the integration of expert knowledge, or the ability to formalize the knowledge from the expert's design.Our work addresses these limitations by annotating the SysML models with domain-specific ontologies.Enabling this interaction not only makes the ontology's semantics available to the tooling environment, but the UML model specified by the designer can be translated into Ontology Web Language format (OWL), generating a system specification in terms of the ontology.These "annotated models" are suitable for reasoning tasks, like consistency check and instance checking.We particularly ensure the annotated model is a consistent extension of the domain-specific ontology, thus formalizing the expert's knowledge as a subontology.This extended ontology can be re-used and shared to evaluate and constrain further models, or be itself evaluated by semantic-compatible tools.In this article we present our approach for an OWL-MBSE integration, and show its feasibility via an implementation in the UAVs domain.