Read more
This book introduces the state-of-the-art understanding on domain-informed machine learning (DIML) for advanced manufacturing. Methods and case studies presented in this volume show how complicated engineering phenomena and mechanisms are integrated into machine learning problem formulation and methodology development. Ultimately, these methodologies contribute to quality control for smart personalized manufacturing. The topics include domain-informed feature representation, dimension reduction for personalized manufacturing, fabrication-aware modeling of additive manufacturing processes, small-sample machine learning for 3D printing quality, optimal compensation of 3D shape deviation in 3D printing, engineering-informed transfer learning for smart manufacturing, and domain-informed predictive modeling for nanomanufacturing quality. Demonstrating systematically how the various aspects of domain-informed machine learning methods are developed for advanced manufacturing such as additive manufacturing and nanomanufacturing, the book is ideal for researchers, professionals, and students in manufacturing and related engineering fields.
List of contents
Introduction.- Domain-informed Feature Engineering for Smart Manufacturing.- Domain-informed.- Dimension Reduction for Smart Manufacturing.- Fabrication-Aware Machine.- Learning Models for Additive Manufacturing.- Domain-Informed Machine Learning.- Models for Nanomanufacturing.- Engineering-Informed Transfer Learning.- Engineering-Informed.- Process Compensation and Adjustment.- Domain-informed Data Pre-Processing in Additive Manufacturing.- Future Perspective for Domain-informed Machine.- Learning for Smart Manufacturing.
About the author
Dr. Qiang S. Huang is a Professor in the Epstein Department of Industrial and Systems Engineering at the University of Southern California, Los Angeles, CA.
Summary
This book introduces the state-of-the-art understanding on domain-informed machine learning (DIML) for advanced manufacturing. Methods and case studies presented in this volume show how complicated engineering phenomena and mechanisms are integrated into machine learning problem formulation and methodology development. Ultimately, these methodologies contribute to quality control for smart personalized manufacturing. The topics include domain-informed feature representation, dimension reduction for personalized manufacturing, fabrication-aware modeling of additive manufacturing processes, small-sample machine learning for 3D printing quality, optimal compensation of 3D shape deviation in 3D printing, engineering-informed transfer learning for smart manufacturing, and domain-informed predictive modeling for nanomanufacturing quality. Demonstrating systematically how the various aspects of domain-informed machine learning methods are developed for advanced manufacturing such as additive manufacturing and nanomanufacturing, the book is ideal for researchers, professionals, and students in manufacturing and related engineering fields.
