Participants gain hands-on experience applying generative AI to accelerate and enhance MBSE workflows, equipping them with future-ready skills in system modeling, architecture, behavior analysis, and test generation using industry-standard tools.
Participants will learn to:
-
Model system structure, behavior, and requirements using SysML within an AI-enhanced MBSE workflow
-
Integrate software into systems models to support hardware/software co-design
-
Apply AI tools to accelerate model creation, analysis, and design decision-making
-
Leverage AI personas and agents to support collaborative and intelligent engineering processes
-
Use domain-driven modeling techniques to align architecture with problem-domain abstractions
-
Structure and refine requirements using AI to identify gaps, including for software systems
-
Generate and validate use case narratives with AI support, including user interface wireframes
-
Design scalable logical and physical architectures with AI-assisted trade studies and component selection
-
Develop behavioral models with state machines and use AI to generate diagrams and embedded code
-
Perform parametric simulations and constraint analyses with AI support for system optimization
-
Create AI-assisted test cases, including unit, behavioral, and integration tests
-
Utilize AI tools for code generation across embedded, interface, and database software components
-
Understand the capabilities and advancements of SysML v2 for future-ready system modeling
The course covers a comprehensive range of topics from SysML fundamentals to AI-assisted architecture, testing, and co-design—organized to reflect the full systems engineering lifecycle and demonstrate practical AI integration at each stage.
-
Introduction to AIM – AI’s role in enhancing MBSE workflows and engineering productivity
-
SysML Fundamentals – Modeling structure, behavior, and requirements using SysML, with object-oriented integration of systems and software
-
Hardware/Software Co-Design – Embedding software as a first-class element in system models
-
Leveraging AI in MBSE – Enhancing modeling, analysis, and decision-making with AI tools, including AI personas and agents
-
Domain Modeling Techniques – Defining architectures around core abstractions of the problem domain
-
Requirements Engineering – Structuring and refining requirements with AI-assisted gap analysis
-
Use Case Driven Development – Using AI to generate use case narratives and UI wireframes
-
Logical Architecture – Building scalable system structures using domain-driven design with AI insights
-
Physical Architecture – Conducting AI-assisted trade studies and evaluating commercial components
-
State Machines – Modeling system dynamics with AI-generated diagrams and embedded code
-
Parametric Modeling & Constraint Analysis – Applying AI to support simulations and performance trade-offs
-
AI-Assisted Testing – Generating test cases across unit, behavior, and integration levels with AI
-
Software & Systems Co-Design – Using AI for code generation across embedded, UI, and database software
-
Overview of SysML v2 – Exploring advancements in next-generation modeling languages
This course is ideal for systems engineers, MBSE practitioners, and technologists working across the systems engineering lifecycle, especially those integrating Gen AI into design, analysis, and operational workflows for complex, networked engineering systems.
Q1: What tools will I use in the course?
Participants will use Dassault Systèmes' Cameo Systems Modeler and Catia Magic Systems of Systems Architect with educational licenses provided for the duration of the course.
Q2: What kind of AI tools are covered?
Participants will use Dassault Systèmes' Cameo Systems Modeler and Catia Magic Systems of Systems Architect with educational licenses provided for the duration of the course. In addition, publicly available versions of ChatGPT from OpenAI will be used for demonstration purposes to showcase how generative AI can assist with tasks such as requirements generation, model analysis, and test case creation. These examples are illustrative and do not require integration with internal systems.
Q3: Is the course suitable for defense or sensitive environments?
Yes. While generative AI is explored through demonstration, care is taken to avoid requiring publicly hosted foundation models. Discussions include considerations for secure deployment and future tool integration in regulated environments.
Q4: Will I receive a certificate?
Yes. Participants who complete the course will receive a Caltech CTME Certificate and 4.0 Continuing Education Units (CEUs).
Q5: Is prior experience with AI required?
No prior AI experience is necessary. Familiarity with MBSE tools and systems engineering principles is expected, but AI concepts are introduced in a practical, engineering-focused context.
