Utilizing AI to Overcome Barriers to MBSE Adoption

The increasing complexity of systems has necessitated a modernized model-centric approach to design them. Becoming fully model-centric has introduced a new set of challenges that need to be overcome in order to realize the full potential from this new approach. This paper presents a plugin for Cameo System Modeler 2022x that automates the extraction of SysML Block Definition Diagram data from an entire model or a selected diagram. The extracted data is formatted into JSON and processed via a Java-based API client, which sends it to Mistral AI for interpretation. The AI-generated textual summary provides insights into system components and relationships, streamlining model comprehension and decision-making. By integrating AI-driven interpretation into the Cameo environment, this approach enhances model-based systems engineering (MBSE) workflows, reducing the manual effort required to analyze complex architectures. The paper discusses the plugin’s implementation, its benefits in model analysis, and potential applications in complex system development, such as those in the defense sector. This work demonstrates how AI can augment MBSE tools to improve efficiency and accessibility in system modeling.