AI-Assisted Composite Materials Design

“AI-Assisted Composite Materials Design” is an international, hands-on workshop that explores how AI is transforming traditional materials science workflows. Participants will learn to use data-driven models, surrogate optimization, and deep learning algorithms to predict material properties, simulate behavior, and discover new composite formulations with tailored mechanical, thermal, or electrical properties.

The workshop emphasizes real-world datasets, multi-scale modeling, and AI-powered tools like Bayesian optimization, Neural Networks, Graph Neural Networks (GNNs), and AutoML platforms applied to composite design and simulation.

• Bridge the gap between materials science and artificial intelligence

• Train participants to use AI for faster, cost-effective materials discovery

• Foster cross-disciplinary collaboration for smart, sustainable material development

• Introduce scalable digital tools for next-generation composite design

• Promote reproducibility, transparency, and innovation in AI-assisted materials research

Day 1: Generative Models for Microstructure Design

• Fundamentals of microstructure design and its impact on material properties

• Traditional vs. data-driven design approaches

• Overview of generative models: GANs, VAEs, and diffusion models

• Conditioning generative models on target properties

• Learning inverse design: mapping structure to desired properties

• Case studies in 2D/3D material generation using machine learning

Day 2: Bayesian Optimization for Stiffness/Weight Trade-Off

• Multi-objective design problems in engineering

• Stiffness vs. weight trade-offs in materials and components

• Constraints in mechanical and aerospace design

• Principles of Bayesian optimization: Gaussian processes, surrogate models, acquisition functions

• Pareto frontiers and uncertainty quantification

Day 3: Digital Twin Validation in Finite Element Analysis (FEA)

• Introduction to digital twins in predictive engineering

• Integrating simulation data with real-world observations

• FEA model setup and validation for structural behavior

• Techniques for model calibration using experimental or sensor data

• AI-assisted model updates to enhance simulation fidelity and performance feedback

• Materials and mechanical engineers

• Polymer scientists and nanocomposite researchers

• AI/ML engineers in manufacturing or R&D

• Aerospace, automotive, and biomedical materials developers

• UG/PG/PhD students in materials science, physics, or applied AI