Automating Model Based Systems Engineering with AI

Model Based Systems Engineering offers a robust approach to designing complex systems, but often involves significant manual effort and specialized expertise. The increasing complexity of engineering projects makes this challenge even more acute.

Today we'll discuss an AI-driven approach that automates the generation and validation of engineering models. Through the use of AI, organizations can now model their systems in detail and automatically verify design consistency.

Understanding AI-Driven MBSE

Traditional systems engineering approaches often struggle with the complexity of modern engineering projects. Manual creation of Systems Modeling Language models can be a daunting task, potentially requiring multiple man-years of effort. Ensuring traceability, consistency, and adherence to SysML standards throughout the model is also complex and time-consuming.

An AI-driven MBSE software approach can automate model generation and validation. By combining generative AI models, graph algorithms, and AI-powered verification, the software can automatically generate SysML graphs from technical documentation, stakeholder meeting notes, and regulatory documents.

As engineering projects become more complex, distributed, and impacted by interconnected requirements, the need for automation and intelligent tools increases. AI-driven MBSE provides an intuitive and efficient technique to accelerate model creation and ensure design consistency.

The Unique Advantages of AI for SysML Model Generation and Verification

The strengths of AI-driven MBSE hinge on its ability to encapsulate the complexity and dynamism of engineering projects. Unlike traditional frameworks, AI thrives on complexity and interdependencies.

AI-driven MBSE excels in:

• Automated model generation with traceability: Automatically generating SysML graphs from technical documentation and other sources.
• AI-powered verification: Validating design consistency against technical documentation and SysML standards.
• AI copilot workflows: Automating engineers' interactions with systems architecture modeling software.

This enables teams to assess system design resilience in a controlled, virtual environment under various conditions and focus their efforts on the highest-impact issues.

Key Components of the AI-Driven MBSE System

AI Graph Agent for SysML Model Generation

SysML v2 models are represented as directed acyclic graphs. The AI Graph Agent overcomes limitations of large language models by building the graph incrementally, one element or relationship at a time.

SysML Model Verification Using AI Graph Traversal

The AI system traverses the SysML graph using breadth-first search to identify and correct inconsistencies. This process includes:

• Checking each part for issues within its aggregated elements and relationships
• Verifying that fields trace back to source documentation and parent elements
• Ensuring self-consistency between element fields and neighboring elements
• Validating adherence to requirements related to part relationships, port connections, requirement traceability, constraint satisfaction, and action-state associations

SysML CoPilot for Enhanced User Interaction

The AI copilot simplifies user interaction with the SysML model by enabling natural language commands for modifications. The system identifies the relevant subgraph, performs the changes autonomously, verifies the changes for consistency, and lets users review the results.

Benefits of AI-Driven MBSE

• Automation: Automates the tedious effort of building SysML models.
• Robust traceability: Provides stronger traceability than manual methods.
• Automated verification: Verifies adherence to SysML standards and consistency with source documentation.
• Simplified training: Makes SysML-driven workflows easier for engineers to adopt.
• Reduced costs: Lowers the cost of adopting a robust MBSE approach.
• Improved collaboration: Gives engineers from different disciplines a more intuitive way to collaborate.

Conclusion

By leveraging AI to automate and enhance the MBSE process, ThunderGraph aims to make systems engineering more efficient, accessible, and accurate. These innovations have the potential to transform MBSE across multiple industries.