Master Thesis – AI in MBSE

Tasks

The master thesis will focus on applying, evaluating, and improving an existing MBSE Copilot solution within a real-world engineering context. The tasks are:

• Analyze Copilot capabilities for supporting MBSE workflows, including requirement handling and model generation
• Conduct a case study using representative MBSE artifacts (e.g., SysML models, requirement documents) to assess tool performance
• Perform user testing to evaluate usability, efficiency gains, and acceptance among engineers
• Investigate input quality and segmentation strategies for large-scale requirements (e.g., 600+ pages) to ensure meaningful Copilot output
• Benchmark Copilot performance against traditional manual MBSE processes to determine effectiveness and identify improvement areas
• Document findings and propose enhancements for better integration of AI copilots in MBSE lifecycles

Qualification

• Strong MBSE knowledge: Familiarity with model-based systems engineering principles and SysML (ideally SysML v2)
• AI/ML understanding: Basic concepts of artificial intelligence and machine learning, especially in engineering applications
• Analytical and evaluation skills: Ability to assess tool performance, identify improvement areas, and interpret user feedback
• Technical proficiency: Basic programming skills for data analysis and automation tasks
• Tool familiarity: Experience with MBSE tools such as Cameo or Capella is advantageous but not mandatory
• Communication and documentation: Ability to clearly document findings and present results to technical and non-technical stakeholders
• Research capability: Competence in conducting literature reviews and synthesizing insights from academic and industrial sources

nice to have:

• Experience with SysML v2
• Familiarity with MBSE tools (Cameo, Capella)
• Knowledge of Python or AI frameworks
• Prior experience in user studies or usability testing