||Additive manufacturing is a continuously growing field with the potential to revolutionize the manufacture of critical engineering components. Developing an understanding of the complex parameter space involved to reliably produce high quality parts is particularly challenging due to the large variable space that must be considered including machine, material, and part geometry specific settings. To improve part quality, large amounts of data are collected in-situ utilizing nondestructive methods such as thermal, acoustic, ultrasonic, and visual inspection. Further, manufactured components are investigated postproduction using a range of characterization methods to quantify the grain structure, texture, porosity, and secondary phase content of the materials. Organizing and analyzing this volume of data has proved difficult, especially as it relates to identifying quantifiable and actionable processing improvements on an industrially relevant scale.
This symposium aims to examine collection, management, and analysis of data that can be used to expedite and improve the additive manufacturing process. Academic analysis is of interest, however this symposium is particularly interested in identifying methods that can be introduced into the growing additive industry and digital manufacturing framework.
Specific topics of interest include artificial intelligence and machine learning approaches focused on leveraging process and inspection data to improve additive manufacturing, including but not limited to digital twins, nondestructive evaluation, data management, and accelerated material and/or part qualification.