Deep learning based workflow for accelerated industrial X-ray Computed Tomography (2309.14371v1)
Abstract: X-ray computed tomography (XCT) is an important tool for high-resolution non-destructive characterization of additively-manufactured metal components. XCT reconstructions of metal components may have beam hardening artifacts such as cupping and streaking which makes reliable detection of flaws and defects challenging. Furthermore, traditional workflows based on using analytic reconstruction algorithms require a large number of projections for accurate characterization - leading to longer measurement times and hindering the adoption of XCT for in-line inspections. In this paper, we introduce a new workflow based on the use of two neural networks to obtain high-quality accelerated reconstructions from sparse-view XCT scans of single material metal parts. The first network, implemented using fully-connected layers, helps reduce the impact of BH in the projection data without the need of any calibration or knowledge of the component material. The second network, a convolutional neural network, maps a low-quality analytic 3D reconstruction to a high-quality reconstruction. Using experimental data, we demonstrate that our method robustly generalizes across several alloys, and for a range of sparsity levels without any need for retraining the networks thereby enabling accurate and fast industrial XCT inspections.
- “Defects in metal additive manufacturing processes,” Journal of Materials Engineering and Performance, vol. 30, no. 7, pp. 4808–4818, 2021.
- “Directed energy deposition (DED) additive manufacturing: Physical characteristics, defects, challenges and applications,” Materials Today, vol. 49, pp. 271–295, 2021.
- “Practical cone-beam algorithm,” JOSA A, vol. 1, no. 6, pp. 612–619, 1984.
- “Enabling rapid X-ray CT characterisation for additive manufacturing using CAD models and deep learning-based reconstruction,” npj Computational Materials, vol. 9, no. 1, pp. 91, 2023.
- “Beam hardening artifact reduction in X-ray CT reconstruction of 3D printed metal parts leveraging deep learning and CAD models,” in ASME International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 2020, vol. 84492, p. V02BT02A043.
- “Simurgh: A Framework for CAD-Driven Deep Learning Based X-Ray CT Reconstruction,” in 2022 IEEE International Conference on Image Processing (ICIP). IEEE, 2022, pp. 3836–3867.
- “High Throughput Deep Learning-Based X-ray CT Characterization for Process Optimization in Metal Additive Manufacturing,” ASPE and euspen Summer Topical Meeting, vol. 77, pp. 160–164, 2022.
- “Robust and interpretable blind image denoising via bias-free convolutional neural networks,” International Conference on Learning Representations (ICLR), 2020.
- “2.5 D deep learning for CT image reconstruction using a multi-GPU implementation,” in 2018 52nd Asilomar Conference on Signals, Systems, and Computers. IEEE, 2018, pp. 2044–2049.
- “MBIR Training for a 2.5D DL network in X-ray CT,” in 16th International Meeting on Fully 3D Image Reconstruction in Radiology and Nuclear Medicine, Leuven, Belgium, 2021, pp. 19–23.
- “Neural Network-based Single-material Beam Hardening Correction for X-ray CT in Additive Manufacturing ,” in (to appear) 17th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine, Stony Brook, NY, USA, July 16-21, 2023.
- “An energy-based beam hardening model in tomography,” Physics in Medicine & Biology, vol. 47, no. 23, pp. 4181, 2002.
- Nobuyuki Otsu, “A threshold selection method from gray-level histograms,” IEEE transactions on systems, man, and cybernetics, vol. 9, no. 1, pp. 62–66, 1979.
- “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical image computing and computer-assisted intervention. Springer, 2015, pp. 234–241.
- “Observation of spatter-induced stochastic lack-of-fusion in laser powder bed fusion using in situ process monitoring,” Additive Manufacturing, vol. 61, pp. 103298, 2023.
- “Image quality assessment: From error visibility to structural similarity.,” IEEE Transactions on image processing, vol. 13, no. 1, pp. 600–612, 2004.