Artificial Intelligence-Aided Materials Design: AI-Algorithms and Case Studies on Alloys and Metallurgical Processes

This book provides an introduction to the application of artificial intelligence and machine learning concepts to develop predictive models for designing alloy materials. It covers various AI/ML algorithms, their implementation in MATLAB® and Python, and case studies in materials science. It is written for materials scientists and metallurgists interested in applying AI/ML to develop new materials.

Format: Hardback
Length: 334 pages
Publication date: 16 March 2022
Publisher: Taylor & Francis Ltd

This comprehensive book delves into the realm of artificial intelligence (AI)/machine learning (ML) concepts, presenting a comprehensive guide on how to develop predictive models for designing alloy materials. Spanning a wide range of alloys, including hard and soft magnetic alloys, nickel-base superalloys, titanium-base alloys, and aluminum-base alloys, this text serves as a valuable resource for both newcomers to AI/ML algorithms and experienced researchers seeking to explore new approaches.

The book begins by offering an insightful overview of various AI concepts and their appropriate implementation in diverse data types derived from experiments, computer simulations, and real-world industries. It helps readers grasp the advantages and limitations of these algorithms and provides practical guidance on how to apply them effectively.

To facilitate the development of predictive models, the book offers comprehensive coverage of AI/ML algorithms, including MATLAB® and Python implementations, through detailed case studies. These case studies serve as practical examples that illustrate the application of these algorithms in real-world scenarios, making it easier for readers to understand and apply the concepts.

Furthermore, the book includes downloadable resources such as MATLAB GUI/APP and Python implementation, making it accessible to readers on common mobile devices. This accessibility enhances the convenience and practicality of the material, enabling readers to explore and apply AI/ML algorithms in their research and professional endeavors.

In addition to covering AI/ML algorithms, the book delves into the CALPHAD approach, a widely used method in materials science for predicting phase diagrams and thermodynamic properties. It provides a comprehensive explanation of the CALPHAD approach and discusses how data generated from it can be utilized to enhance the accuracy and reliability of AI/ML models.

Furthermore, the book includes a chapter on metallurgical/materials concepts, which serves as a foundation for understanding the case studies and implementing AI/ML algorithms within the framework of data-driven materials science. By examining the importance of using unsupervised machine learning algorithms in determining patterns in datasets, the book underscores the significance of leveraging AI/ML in advancing the field of materials science.

Ultimately, this book is written for materials scientists and metallurgists who are interested in harnessing the power of AI, ML, and data science to develop new materials. It provides a comprehensive and practical guide that covers the essential concepts, algorithms, and applications, enabling readers to stay at the forefront of this rapidly evolving field.

Weight: 680g
Dimension: 161 x 243 x 27 (mm)
ISBN-13: 9780367765279