Volumetric Anomaly Detection in LPBF by Segmentation and Classification of Exposure Optical Tomography (EOT) Image Stacks

Abstract:

In Laser Powder Bed Fusion (LPBF), ensuring reproducible part quality remains a ma-jor challenge despite the availability of high-resolution in-situ monitoring systems, such as ExposureOptical Tomography (EOT). While EOT provides detailed layer-wise optical information, most exist-ing approaches focus on single-layer analysis or real-time process control and do not exploit the fullvolumetric information contained in the acquired data.This work presents a modular framework for the volumetric reconstruction and post-process anal-ysis of EOT image data. Sequential EOT images are processed using volumetric component segmen-tation (VCS) and fused into a three-dimensional OT Image Cube, forming a central volumetric datastructure called LPBF Cube. Each voxel encodes spatial and radiometric information and can option-ally be augmented with additional process metadata.Based on this representation, high-resolution two-dimensional slices are rendered along arbitraryorientations using profile-based slicing strategies for planar, cylindrical, and complex geometries.These slices enable intuitive, part-level inspection of laser exposure history and spatial process vari-ations. The framework is validated using geometric and radiometric analyzes, demonstrating goodagreement with nominal CAD geometry and a clear correlation between EOT-derived emission val-ues, laser energy input, and local cross-sectional area.The proposed approach extends the use of EOT data beyond layer-wise monitoring toward com-prehensive, volumetric part inspection and provides a practical basis for geometry-aware quality as-sessment in LPBF, particularly for prototyping and post-build evaluation.

• Periodical: Key Engineering Materials (Volume 1047)
• Pages: 191-204
• Online since: April 2026
• Authors: Karsten Scheibe*, Johann Albers, Felix Jensch, Chukwuemeka Okolo, Sebastian Härtel
• Keywords: Anomaly Detection, Exposure OT, Image Segmentation, LPBF, Machine Learning

References

[1] E. Duong: Laser Powder Bed Fusion Process Monitoring Using Multisensory: PhD thesis, RWTH Aachen (2023).

[2] Mohr, G.; Altenburg, S.J.; Ulbricht, A.; Heinrich, P.; Baum, D.; Maierhofer, C.; Hilgenberg, K.: In-Situ Defect Detection in Laser Powder Bed Fusion by Using Thermography and Optical Tomography-Comparison to Computed Tomography. Metals (2020), 10, 103

DOI: 10.3390/met10010103

[3] Breese, P., Becker, T., Oster, S., Altenburg, S., Metz, C., Maierhofer, C.: Aktive Laserthermografie im L-PBF-Prozess zur in-situ Detektion von Defekten. DGZfP Jahrestagung (2022), Kassel, May, Germany. https://www.ndt.net/?id=27067

[4] Aydogan, B.; Chou, K.: Review of In Situ Detection and Ex Situ Characterization of Porosity in Laser Powder Bed Fusion Metal Additive Manufacturing. Metals (2024), 14, 669

DOI: 10.3390/met14060669

[5] Herzog, T., Brandt, M., Trinchi, A. et al.: Process monitoring and machine learning for defect detection in laser-based metal additive manufacturing. J Intell Manuf 35, 1407-1437 (2024)

DOI: 10.1007/s10845-023-02119-y

[6] Osazee E., Katayoon T., Ehsan T.: Optical tomography and machine learning for in-situ defects detection in laser powder bed fusion: A self-organizing map and U-Net based approach Additive Manufacturing, V78 (2023).

DOI: 10.1016/j.addma.2023.103894

[7] Atwya, M., Panoutsos, G.: In-situ porosity prediction in metal powder bed fusion additive manufacturing using spectral emissions: a prior-guided machine learning approach. J Intell Manuf 35, 2719-2742 (2024)

DOI: 10.1007/s10845-023-02170-9

[8] Lim, Y., Wong and Tan: Correlation of In-Process Monitoring Data and Defects in X-Ray CT for AM Swirler Whitepaper EOS. https://www.eos.info/

[9] A. Kirillov, N. Ravi, D. Xu, S. Azadi, H. Xu, T. Darrell, K. He, R. Girshick, and P. Dollár: Segment Anything Model 2 (SAM2). Meta AI Research, 2024. Available at: https://github. com/facebookresearch/segment-anything-2.

[10] T. Y. Zhang and C. Y. Suen: A fast parallel algorithm for thinning digital patterns. Communications of the ACM, Volume 27, Number 3 (March 1984).

[11] T.-C. Lee, R.L. Kashyap and C.-N. Chu: textitBuilding skeleton models via 3-D medial surface/axis thinning algorithms. Computer Vision, Graphics, and Image Processing, 56(6):462-478, (1994).

DOI: 10.1006/cgip.1994.1042

[12] L. Fuchs, C. Eischer: In-process monitoring systems. Whitepaper EOS. https://www.eos. info/