1st Edition

Steel Informatics Analysing Data of a Complex Materials System

By Shubhabrata Datta, Subhas Ganguly Copyright 2025
    264 Pages 108 B/W Illustrations
    by CRC Press

    Steel Informatics aims to review the application of data-driven computing techniques related to design of steel including phase transformation, composition-process-property correlation, and different processing techniques, particularly deformation and joining. The book initiates with fundamentals of informatics followed by description of applications of statistical analyses in defining different attributes of steel. The proceeding chapters of the book cover recent applications of statistical, machine learning, expert systems and optimizations algorithms in the domains of iron and steel making, casting, deformation, phase transformation and heat treatment, microstructure analysis, and design of steel.


    • Exclusive title focussing on informatics in steel design.
    • Covers related statistics as well as Artificial Intelligence and Machine Learning aspects.
    • Explains metallurgical aspects lucidly for the data scientists, steel researchers and industries.
    • Discusses all aspects of steel technology.
    • Describes pertinent tools used for related computations.

    The book is useful for researchers, professionals and graduate students in Metallurgy, Materials Science, Steel and Welding and Computational Materials Science.

    Chapter 1. Introduction to Informatics and Data Analytics. 1.1. Informatics. 1.2. Data Analytics. 1.3. Statistical Tools for Data Analytics. 1.4. Artificial Intelligence and Machine Learning. 1.5. Fuzzy and Expert Systems. 1.6. Metaheuristic Algorithms for Optimization. 1.7. Summary. Chapter 2. Materials Informatics and Steel Data. 2.1. Concept of Materials Informatics. 2.2. Applications of Materials Informatics. 2.3. Source of Steel Data. 2.4. Data Digitization. 2.5. Steel Microstructure. 2.6. Summary. Chapter 3. Ironmaking and Steelmaking. 3.1. Overview of Ironmaking and Steelmaking Processes. 3.2. Informatics in Ironmaking and Steelmaking processes. 3.3. Preprocessing of Ironmaking and Steelmaking Data. 3.4. Analysis of Ironmaking Data. 3.5. Analysis of Steelmaking Process Data. 3.6. Summary. Chapter 4. Prediction of Phase Transformation in Steel. 4.1. Why Informatics-based Predictions for Phase Transformation. 4.2. Linear Regression Models for Transformation Temperatures. 4.3. Neural Network Models for Phase Transformation. 4.4. Predictive Models for CCT and TTT Diagrams. 4.5. Summary. Chapter 5. Steel Welding. 5.1. Measurables in Welding Process. 5.2. MLR for Carbon Equivalent and Other Outcomes. 5.3. Neural Networks for Weld Bead and HAZ Geometry. 5.4. Neural Network Modelling of Welded Steel Properties. 5.5. Data-driven Approaches for Stainless Steel Welding. 5.6. Summary. Chapter 6. Data-driven Modelling of Mechanical Properties of Steel. 6.1. Mechanical Properties of Steel. 6.2. Linear Regression Models for Mechanical Properties of Steel. 6.3. Neural Network Models for Mechanical properties. 6.4. Genetic Programming Models. 6.5. Incorporating imprecise knowledge - Fuzzy Inference Systems in Property Predictions. 6.6. Feature Selection from mechanical property data using rough set theory. 6.7. Summary. Chapter 7. Microstructure and Machine Learning. 7.1. Quantification of Microstructural Features. 7.2. Image Analysis Techniques. 7.3. Feature Extraction and Classification of Microstructure. 7.4. MLR for Predicting Microstructural Features. 7.5. Neural Network for Prediction of Microstructural Features. 7.6. Deep Learning for Microstructure Classification. 7.7. Defect Root Cause Analysis. 7.8. Summary. Chapter 8. Optimization for Design. 8.1. Prescriptive Analytics and Optimization in Steel Design. 8.2. Properties, Performance and Multi-objective Optimization. 8.3. Process Optimization using Metaheuristic Algorithms. 8.4. Microstructure Design. 8.5. Summary. Chapter 9. Possibilities and Opportunities. 9.1. Future of Data Science. 9.2. Where Are the Gaps in Steel Informatics?. 9.3. Will There Be More Steel Data to Analyze?. 9.4. Will Deep Learning Make It More Effective?. 9.5. Is It Really Important for the Industry?. 9.6. Summary.


    Shubhabrata Datta is presently working as Research Professor in the Department of Mechanical Engineering, and Coordinator of the Centre for Composites and Advanced Materials at SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India. His research interests are in the domain of Materials Informatics, Alloy Design, Composites and Biomaterials.

    Subhas Ganguly is an Associate Professor in the Department of Metallurgical and Materials Engineering, National Institute of Technology, Raipur, India. His research interests include Artificial Intelligence and Machine learning in Materials Engineering, Computational Optimization and Data Science for Metallurgical problems, Advance Steel and Alloy Design, Phase Transformation and Friction Stir Welding.