ABSTRACT: This paper presents the MBSE-Graph-RAG framework to address key challenges in Model-Based Systems Engineering (MBSE). Traditional MBSE tools suffer from usability barriers, limited accessibility, and integration challenges. By combining knowledge graphs with Retrieval-Augmented Generation (RAG), the proposed framework enables AI-Augmented engineering through natural language interactions and automated system architecture generation. A systematic literature review establishes a solid research foundation, identifying gaps in AI-assisted MBSE. Key contributions include a structured MBSE-Graph interface, improved usability via Large Language Models (LLMs), and automated graph construction aligned with SysML. A proof-of-concept demonstrates the potential of this approach to enhance MBSE by reducing complexity, improving data accessibility, and supporting engineering collaboration.
Hanke et al. (Fri,) studied this question.