Artificial Intelligence and Machine Learning in Materials Engineering

Indian Institute of Technology Kanpur and NPTEL via Swayam

Overview

ABOUT THE COURSE:Artificial intelligence (AI) has taken the center-stage of material development due to rapid increase of the computational power and speed. The use of AI is rapidly picking up for high throughput screening and decision making for materials chemistry, property estimation and optimization of properties. As the need of new materials with improved properties is felt across the discipline, the accelerated design and development has become a key aspect of material science and engineering. The the need for use of AI and machine learning has widely been felt to design new materials with better properties The course is intended to provide this some basics aspects of use of AI and ML in materials science and engineering. Starting with processing -structure-property correlation, the basic computational tools will be deliberated with application of machine learning and deep learning. The application of AI-ML will be discussed with some case studies and examples.INTENDED AUDIENCE: UG, PG from Academic Institutes and Industry Professionals from various IndustriesPREREQUISITES: Basic concept on Materials ScienceINDUSTRY SUPPORT: YES, Tata Steels, TRDDC, Jindal, Hidulco

Syllabus

Week 1 :

Introduction to the course: This will provide basic aspects of the course: why AI/ML in Materials Engineering.
Basics of Materials Science-I: Structure of Materials
Basics of Materials Science-II: Microstructure –property correlation

Week 2 :

Basics of Materials Science-III: Processing of materials
Basics of Materials Science-IV: Correlation between processing with materials structure-I
Basics of Materials Science-V: Correlation between processing with materials structure-II

Week 3 :

Materialsdesign at different length scale - I: Basic Design Principles
Materialsdesign at different length scale - II: Component level to atomic level aspects of material design
Materialsdesign at different length scale - III: CALPHAD;

Week 4 :

Materialsdesign at different length scale - IV: Ab initio, Density Functional Theory (DFT),
Materialsdesign at different length scale - V: Monte Carlo (MC) or Molecular Dynamic (MD) followed Phase Field Simulations (PFM) for microstructural evolution.
Machine Learning Approaches for Materials Design-I: Statistical Tools, Machine Learning-I

Week 5 :

Machine Learning Approaches for Materials Design-II: Statistical Tools, Machine Learning,-II
Machine Learning Approaches for Materials Design-III: Statistical Tools, Machine Learning-III
Machine Learning Approaches for Materials Design-IV: Computer vision-I
Machine Learning Approaches for Materials Design-V: Computer vision-II

Week 6 :

Machine Learning Approaches for Materials Design-VI: Microstructural evolution-I
Machine Learning Approaches for Materials Design-VII: Microstructural evolution-II
Machine Learning Approaches for Materials Design-VIII: Microstructure property correlation-I

Week 7 :

Machine Learning Approaches for Materials Design-IX: Microstructure property correlation-II
Machine Learning Approaches for Materials Design-X: Microstructure property correlation-III
Accelerating Materials Development and Deployment-I: Microstructure property correlation-IV

Week 8 :

Accelerating Materials Development and Deployment-II: Deep Learning-I
Accelerating Materials Development and Deployment-III: Deep Learning-II
Accelerating Materials Development and Deployment-IV: Deep Learning-III

Week 9 :

Accelerating Materials Development and Deployment-V: Inverse design using AI/ML – from evolutionary algorithms to deep learning-I
Materials Knowledge and Materials Data Science-I: Inverse design using AI/ML – from evolutionary algorithms to deep learning-II
Materials Knowledge and Materials Data Science-II: Inverse design using AI/ML – from evolutionary algorithms to deep learning-III

Week 10 :

Materials Knowledge and Materials Data Science-III: Advanced Deep Learning-I
Materials Knowledge and Materials Data Science-IV: Advanced Deep Learning-I
Materials Knowledge and Materials Data Science-V: AI/ML for materials characterization-I
Materials Knowledge and Materials Data Science-VI: AI/ML for materials characterization-II

Week 11 :

Materials Knowledge and Materials Data Science-VII: AI/ML for materials characterization-III
Materials Knowledge and Materials Data Science-VIII: AI/ML for materials characterization-IV
Materials Knowledge and Materials Data Science-VIII: AI/ML for autonomous experiments-I
Materials Knowledge and Materials Data Science-VIII: AI/ML for autonomous experiments-II

Week 12 :

Materials Knowledge and Materials Data Science-IX: Materials Informatics and Data Science-I
Materials Knowledge and Materials Data Science-IX: Materials Informatics and Data Science-II
Materials Knowledge and Materials Data Science-IX: Materials Informatics and Data Science-III
Materials Knowledge and Materials Data Science-X: Summary and Way forward