Engineering of Additive Manufacturing Features for Data-Driven Solutions: Sources, Techniques, Pipelines, and Applications

ISBN-13: 9783031321535 / Angielski

Mutahar Safdar; Guy Lamouche; Padma Polash Paul

Spis treści

Introduction.- Feature Engineering in AM.- Applications in Data-driven AM.- Analyzing AM Feature Spaces.- Challenges and Opportunities in AM Data Preparation.- Summary.

O autorze

Mutahar Safdar is a PhD candidate in Additive Design and Manufacturing Laboratory (ADML) at the Department of Mechanical Engineering in McGill University, in Montreal, Quebec, Canada. Before joining ADML at McGill, Mutahar obtained a master’s degree in mechanical engineering from Korea Advanced Institute of Science and Technology (KAIST), in Daejeon, South Korea. At KAIST, he was part of the Intelligent Computer-Aided Design (iCAD) laboratory where he researched solutions to interoperability issues in design data exchange. He completed his bachelor’s degree in mechanical engineering from University of Engineering and Technology (UET), in Lahore, Pakistan. His research interests include engineering informatics, additive manufacturing, engineering design, digital twin, and sustainability in design and manufacturing. He is interested in the application of machine learning to transform additive manufacturing into a reliable and high-volume production technology. As part of his PhD research, he is developing machine learning based solutions to expedite process development of directed energy deposition additive manufacturing process at the industrial scale.

 

Guy Lamouche received the M.Sc.A degree from the École Polytechnique, Montréal, Canada, in 1989, and the Ph.D. degree from the Université de Montréal, Montréal, Canada, in 1996, performing research on guide-wave optics and optical properties of semiconductors and quantum structures. He has been a Natural Science and Engineering Research Council of Canada (NSERC) Post-Doctoral Fellow, from 1996 to 1998, both at Université Paris VII, Paris, France, and Université Joseph Fourier, Grenoble, France. He is now a Principal Research Officer at the National Research Council (NRC) Canada where he has been working since 1998 on the development of optical characterization techniques for both biomedical and industrial applications. As a member of the Computer Vision and Graphics team in the Numerical Technologies research center at NRC, his mot recent work focused on inline monitoring of manufacturing processes.

 

Padma Polash Paul is an esteemed machine learning researcher, published author, former professor and entrepreneur. As the Co-CEO and CTO of Braintoy, Canada’s first machine learning platform, he is dedicated to helping organizations build and deploy their own machine learning solutions to enhance business performance. Originally from Bangladesh, Paul has a Masters Degree in computer Science from the University of Hong Kong and a PhD in computer science from the University of Calgary. He completed his Postdoctoral Fellowship at the University of Oxford in computational neuroscience and continues to be actively involved in neural implant. Paul has published in excess of 80 research papers, 50 of those while attaining his PhD. Paul was the Principal Machine Learning Architect at the Calgary headquarters of GE, which later became Baker Hughes, between 2016-2019. In addition to his role as co-CEO and Chief Technology Officer with Braintoy, Padma is a course curriculum designer for the Applied AI and ML bootcamp at the Southern Alberta Institute of Technology (SAIT) and Mount Royal University.

 

Gentry Wood is a Senior Research and Development Engineer for Apollo-Clad Laser Cladding, a division of Apollo Machine & Welding Ltd. in Leduc, Alberta, Canada. Gentry completed his undergraduate degree in Materials Engineering in 2012 from the University of Alberta and a PhD in 2017 from the Canadian Centre for Welding and Joining. His work has focused on modelling the geometry of laser-welding based overlays, optimizing process efficiency, and maximizing performance of corrosion and wear resistant coatings for a variety of applications. He has led Apollo-Clad efforts to pivot from laser coatings towards industrial-scale, directed energy deposition based additive manufacturing of metallic components. In 2022, Gentry was inducted as a fellow of the Canadian Welding Bureau Association (CWBA).

 

Yaoyao Fiona Zhao is an Associate Professor and William Dawson Scholar at the Department of Mechanical Engineering in McGill University, in Montreal, Canada. She is the director of the Additive Design and Manufacturing Laboratory (ADML) in McGill University which is one of the leading research laboratories in additive manufacturing field. She has expertise in Design for Additive Manufacturing (DfAM), digital manufacturing, sustainable manufacturing, artificial intelligence, and machine learning. Her team has successfully conducted projects on a number of ML applications to assist manufacturability prediction, predictive analysis of product performance, microstructure simulation, hybrid energy system modeling, cutting tool life prediction. Her team is leading the research in DfAM with the development of new design methods to achieve multi-functionalities, less part count, better functional and sustainability performance. Her team is also leading the efforts on developing methods and guidelines for manufacturing industry to adopt machine learning and AI as an effective tool for global competition.

 

 

 

Blurb

This book is a comprehensive guide to the latest developments in data-driven additive manufacturing (AM). From data mining and pre-processing to signal processing, computer vision, and more, the book covers all the essential techniques for preparing AM data. Readers willl explore the key physical and synthetic sources of AM data throughout the life cycle of the process and learn about feature engineering techniques, pipelines, and resulting features, as well as their applications at each life cycle phase. With a focus on featurization efforts from reviewed literature, this book offers tabular summaries for major data sources and analyzes feature spaces at the design, process, and structure phases of AM to uncover trends and insights specific to feature engineering techniques. Finally, the book discusses current challenges and future directions, including AI/ML/DL readiness of AM data.

Whether you're an expert or newcomer to the field, this book provides a broader summary of the status and future of data-driven AM technology.