About This Offering

Participants will learn the basics of key generative AI methods, such as generative adversarial networks, diffusion, and transformer methods. In addition, this course will showcase how the generative AI methods advance the field of engineering designs in practical setups.  

Registration

Browse our catalog

Check out all of our short course and bootcamp offerings! see all offerings

Portrait of Dr. Xiaosong Du

Xiaosong Du

Dr. Xiaosong Du is an Assistant Professor in the Department of Mechanical and Aerospace Engineering at Missouri University of Science and Technology (Missouri S&T). Prior to joining Missouri S&T, he was a postdoctoral research fellow at the University of Michigan. He earned his Ph.D. in Aerospace Engineering from the Iowa State University and accumulated more than 10 years of experience in artificial intelligence (AI) and engineering design optimization, especially engineering design empowered by generative AI and physics-based AI.

Dr. Du specializes in developing novel AI algorithms and engineering design architectures. A key focus of his research is the coupling between generative AI and engineering design for advanced optimization architectures. He has published over 60 papers with over 1,200 citations and was recognized as a Top 2% most cited scientist according to a Stanford report. His publications won the ASME Best Paper Award and were posted as Editor’s Choice Article and Title Story. Since joining Missouri S&T in Fall 2022, he has received two federal grants (one as a single PI and the other one as a Co-PI) and multiple institutional seed grants. He has been serving as guest editors for journals, session chairs for international conferences, etc. His recent research, physically constrained generative AI-based rapid engineering design, is under the funding support by the National Science Foundation.
  • Registration: Open until June 18, 2026
  • Course Dates: June 25 & 26, 2026
  • PDH: 16
  • Price: $1,499
  • Location: 2127 Innerbelt Business Center Drive, St. Louis, MO 63114
    • Directions 
    • Also delivered live online via Zoom

This introductory workshop provides a comprehensive overview of generative AI fundamentals and relevant engineering applications (especially in engineering design optimization). Participants will learn the basics of key generative AI methods, such as generative adversarial networks, diffusion, and transformer methods. In addition, this course will showcase how the generative AI methods advance the field of engineering designs in practical setups.

The course establishes the foundational principles of three‑dimensional mapping using Structure‑from‑Motion (SfM) photogrammetry and LiDAR, with emphasis on the role of Global Navigation Satellite Systems (GNSS) in achieving engineering‑grade accuracy. Building on conceptual understanding, the workshop moves into practical skills such as mission planning, field operations, and core data‑processing workflows.

Participants will also examine the range of 2D and 3D survey products generated through drone mapping, focusing on their use in engineering design and assessment. The course concludes with discussions on accuracy and precision, change detection, and best practices for long‑term data management and archival.

By the end of the course students should be able to:

  • Describe key engineering applications of drone‑based mapping.
  • Support the planning and design of a complete drone mapping campaign.
  • Explain the fundamental concepts underlying LiDAR and SfM photogrammetry.
  • Evaluate the advantages and limitations of LiDAR and SfM for site survey and assessment tasks.
  • Plan, specify, and interpret the range of mapping products generated through drone workflows.

Day 1 — Introduction + Foundations

1. Welcome, Objectives & Context
  • Introduction to generative AI
  • State-of-the-art generative AI methods and applications
  • Coupling between generative AI and engineering design optimization
2. Variational Autoencoder
  • Overview and theory
  • Model setup within python
  • Test examples on industry data/cases
3. Generative Adversarial Networks
  • Overview and advantages
  • Adversarial mechanism and limitations
  • Test examples on industry data/cases
4. Diffusion Models
  • Conceptual foundation and physics analogy
  • The two-phase mechanism and technical components
  • Test examples on industry data/cases
5. Transformer Models
  • Introduction and core innovation
  • The attention mechanism and key architectural components
  • Test examples on industry data/cases
6. Summary of Generative AI Models
  • Advantages and disadvantages of each method
  • Representative engineering applications

Day 2 — Generative AI-Driven Engineering Design

1. Introduction to Generative AI in Engineering Design
  • Overview and motivation
  • State of the art and aircraft design
2. Engineering Design Optimization
  • Analytical methods
  • Derivative-based optimization and gradient-free optimization
  • Key challenges
3. AI-Enabled Optimization Architectures
  • Surrogate-based optimization in aerodynamic and system design
  • Inverse mapping in aircraft design and trajectory design
  • Reinforcement learning applications in air traffic
  • Existing gaps
4. Generative AI-Driven Engineering Design (1/2)
  • Intelligent parametrization for aircraft shapes and trajectories
  • Predictive modeling for optimal design discovery
  • Test examples on industry data/cases
5. Generative AI-Driven Engineering Design (2/2)
  • Training facilitation for optimal control
  • Constraint handling for rapid engineering decision-making
  • Test examples on industry data/cases
6. Summary and Outlook
  • Existing issues and potential risks
  • Recommendation and guidance on industry applications