Simurgh: A Framework for Cad-Driven Deep Learning Based X-Ray CT Reconstruction

Abstract

High-resolution X-ray computed tomography (XCT) is an important technique for the inspection of additively manufactured (AM) parts. While XCT is typically used off-line to inspect a subset of manufactured parts, significantly accelerating measurement speed while retaining accuracy would enable use of XCT for in-line inspection to rapidly identify defects in each part as it is manufactured. Here, we propose a deep learning (DL) based approach that uses computer aided design (CAD) models of the AM parts and physicsbased information to rapidly produce high-quality reconstructions from sparse XCT measurements without high quality ground truth data. Our approach uses a generative adversarial neural network (GAN) to produced realistic training data from the CAD-based simulations and a deep neural network that is trained using data from the first stage to produce accurate 3D reconstructions. Using experimental XCT data of metal parts, we demonstrate enhanced defect detection capabilities while dramatically reducing the scan time.

Machine Learning Enabled Sensor Fusion for In-Situ Defect Detection in Laser Powder Bed Fusion

“…The time required to develop and implement the DMSCNN, as well as complications related to analyzing the XCT data, prevented ablation studies from being completed during the program's period of performance, but such analyses are still of interest to the program participants and will be the subject of future collaborations. Additional exploratory reconstructions were performed for some of the samples using the Simurgh algorithm [13], and preliminary inspection of the Simurgh reconstructions showed promise for generating high-quality reconstructions (see Figure 18). Finally, the ORNL-developed DL reconstructions were evaluated for the IRC printed during Phase II.…”