________________________________ From: Khaled Khasawneh <[log in to unmask]> The distinguished seminar has been postponed. The new date for the distinguished seminar will be shared when it is available. Sorry for the inconvenience. Best, Khaled -- Khaled N. Khasawneh, Assistant Professor Electrical and Computer Engineering Department Volgenau School of Engineering George Mason University (GMU) Office: ENGR 3223 Phone: (703) 993-5430 Web: http://mason.gmu.edu/~kkhasawn/ -- ________________________________ From: Jammie Chang <[log in to unmask]> Sent: Thursday, April 7, 2022 2:38 PM To: [log in to unmask] <[log in to unmask]> Subject: ECE Distinguished Seminar: Apr 15, 10:00 am, Physics- and Deep Learning based Computational Imaging to enhance Characterization of Metal Additive Manufactured Parts Using X-ray Computed Tomography ECE Distinguished Seminar Physics- and Deep Learning based Computational Imaging to enhance Characterization of Metal Additive Manufactured Parts Using X-ray Computed Tomography Amir Koushyar Ziabari, Ph.D. R&D Staff Scientist, Multimodal Sensor Analytics Group, Oak Ridge National Laboratory (ORNL) April 15, 2022, 10:00 am-11:00 am ENGR 4201 https://gmu.zoom.us/j/93962077526 Note for people joining in-person only: Participants are encouraged to complete Mason COVID Health✓™<https://www.gmu.edu/mason-covid-health-check> and receive a “green light” status on the day of the event. Please send your RSVP request to [log in to unmask] with the info of seminar date, seminar title, your name. Abstract: Metal Additive Manufacturing (AM), also known as 3D printing, is the process of printing 3D metal parts layer by layer based on corresponding computer aided design (CAD) models input to the printer. X-ray computed tomography (CT) has been used as the key tool for non-destructive characterization (NDC) of metal AM parts. In recent years, and along with the fourth industrial revolution (industry 4.0), there has been efforts for integrating the X-ray CT in-line with the printing process so that it can characterize several parts quickly and provide user with feedback on the quality of the printed parts. This in turn requires a faster X-ray CT scans either through sparse measurement, reducing the scan integration time per view, using less than full-scan data etc. Such requirement for X-ray CT scanning will introduce new challenges and artifacts to the existing challenges associated with X-ray CT scans of metal parts, such as noise, beam hardening and metal artifacts. In this talk, I will present our efforts in development of Deep Learning based Image Reconstruction algorithms leveraging CAD model of the parts along with the physics based information to enhance the quality of X-ray CT reconstruction of metal AM parts, while reducing the scan time by 3-4x. I will present case studies showing how this approach has resulted in fast process parameter optimization for novel materials in metal AM, as well as at least 3X improvement in flaw detection capability without compromising the scanning speed. I will also discuss some of the future work. Bio: Dr. Amir Koushyar Ziabari is an R&D staff scientist in the Multimodal Sensor Analytics group at Oak Ridge National Laboratory (ORNL). Before joining ORNL, Dr. Ziabari was a Postdoc at Integrated Imaging group at the Department of Electrical and Computer Engineering (ECE) at the Purdue University. He also received his PhD from the department of ECE at Purdue University in August 2016. In his research on data science for science, he develops physics, signal processing and machine/deep learning algorithms to process and analyze multiscale scientific imaging data. This includes his research on data analytic, data driven and physics-based image reconstruction and segmentation algorithms for advanced manufacturing (AM) in order to improve non-destructive characterization (NDC) and the state-of-the-art in real time monitoring of the AM process.