Please join us in welcoming Davis Macgregor, a senior manufacturing scientist at Fast Radius, as he discusses machine learning algorithms.
Metrology Automation and Geometric Analysis for Additive Manufacturing
Additive manufacturing (AM) presents unique technical challenges to monitor and control the geometry of parts made in production. AM part geometry can differ from the designed dimensions depending on the part size and shape, as well as manufacturing parameters such as the machine used or the location of the part within the printer. The relationships between part design, manufacturing parameters, and geometric accuracy are not well understood for AM, and there is a need to develop methods that identify and predict dimensional defects. This talk describes research that develops metrology automation to measure and analyze parts made with AM and machine learning methods to predict geometric accuracy. We use optical scanning and computer vision methods to measure part dimensions. Scalable measurement automation enables us to collect many measurements and create insights about the production environment. We then leverage the measurements and insights to develop machine learning models that predict the manufactured dimensions of parts produced with AM.
Davis J. McGregor, Ph.D. is a Senior Manufacturing Scientist at Fast Radius, where he leads the development of manufacturing intelligence algorithms, including costing and design for manufacturability. He developed the company’s framework for continuous feedback and improvement of machine learning models and has integrated automation and technology solutions into the manufacturing process. Dr. McGregor received his Ph.D. in Mechanical Engineering from the University of Illinois Urbana-Champaign, co-advised by Dr. William P. King and Dr. Sameh Tawfick. His graduate research investigated the quality of additively manufactured parts using advanced computational and statistical tools, including computer vision and machine learning.
