PSI - Issue 77

Available online at www.sciencedirect.com Available online at www.sciencedirect.com ScienceDirect Structural Integrity Procedia 00 (2026) 000 – 000

www.elsevier.com/locate/procedia

ScienceDirect

Procedia Structural Integrity 77 (2026) 529–536

© 2026 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of ICSI organizers Abstract The use of neural networks has the potential to significantly enhance additive manufacturing based on the Selective Laser Melting (SLM) method. They enable automated analysis of image data collected during the printing process, which could contribute to early defect detection and overall improvement in part quality. This, in turn, could lead to increased reliability and efficiency of the entire manufacturing process. The work focuses on exploring the potential of convolutional neural networks for monitoring and optimizing SLM printing.Click here and insert your abstract text. © 2026 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of ICSI organizers Keywords: Selective laser melting, Machine learning, CNN, Powder bed International Conference on Structural Integrity Using machine learning for quality control in additive manufacturing A. Polanský a , I. Zetková a , I. Gruber b,c , Y. Bakir a a Regional Technological Institute, Faculty of Mechanical Engineering, University of West Bohemia, Univerzitní 8, 306 14 Pilsen, Czech Republic b Faculty of Applied Sciences, New Technologies for the Information Society , University of West Bohemia, Plzeň, Czech Republic c Amitia s.r.o, Riegrova 206/1, Pilsen, Czech Republic

* Adam Polanský. Tel.: +420 774 278 953 E-mail address: apola@fst.zcu.cz 1. Introduction

Selective laser melting (SLM) is a subtype of Laser powder bed fusion (LPBF) technology. A thin layer of powder is deposited on the substrate, and the laser selectively melts the current cross-section of the part, and again, a new layer of powder is spread. This process repeats until the final part is built. It allows the creation of highly complex geometry that could not be manufactured with conventional technology. However, this “layer -by- layer” process might be a source of defects in the printed part. Therefore, the quality of each layer is essential for ensuring the

2452-3216 © 2026 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of ICSI organizers

2452-3216 © 2026 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of ICSI organizers 10.1016/j.prostr.2026.01.066