Aim

This course is designed to equip participants with both the theoretical knowledge and practical skills required to design, model, and manufacture smart polymer composites using AI. Participants will bridge the gap between material science fundamentals, machine-learning-based property prediction, inverse design, and Industry 4.0 workflows (including simulation, additive manufacturing, IoT-enabled monitoring, and quality control).

Course Objectives

• Define smart polymer composites and their key functional properties.
• Contrast traditional workflows with AI-enabled design benefits.
• Acquire and clean materials datasets from open sources.
• Engineer descriptors (composition, process, microstructure).
• Train and benchmark ML models for property prediction.
• Validate models using cross-validation (CV) and metrics (MAE, R²), along with basic uncertainty checks.
• Apply inverse design to meet target property specifications.
• Integrate AI-driven results with simulations (ANSYS/COMSOL) and outline Industry 4.0 integration.

Course Structure

Course Outcomes

• Curate and clean composite datasets from open sources.
• Engineer features such as composition, process, and microstructure.
• Train and evaluate ML models (RF/NN/SVM) to predict key material properties.
• Validate models with cross-validation (CV) and metrics (MAE, R²), assessing uncertainty.
• Perform basic inverse design to meet target property specifications.
• Feed AI outputs into ANSYS/COMSOL simulations.
• Outline Industry 4.0 workflows (3D printing, IoT QC, defect prediction).
• Deliver a capstone project showcasing the data → model → simulation pipeline, with accompanying slides.

Who Should Enrol?

• Background: UG/PG students, researchers, and professionals in materials science, polymer engineering, mechanical engineering, chemical engineering, or applied physics.
• Roles: R&D engineers, data scientists/ML engineers entering the field of materials informatics, faculty, and industry practitioners.
• Sectors: Aerospace, automotive, biomedical, energy, advanced manufacturing.
• Skill level: Beginner–intermediate (no prior AI-in-materials knowledge required).
• Recommended prep: Basic knowledge of materials science/mechanics and introductory Python (starter notebooks provided).
• Logistics: Participants should bring a laptop for Jupyter notebooks and be ready to use provided datasets and simulation demos (ANSYS/COMSOL).