Page 57 - MSAM-4-3

Materials Science in Additive Manufacturing AI-driven defect detection in metal AM

detection technique in FDM technology. Procedia Comput Defect detection in laser-based powder bed fusion process
Sci. 2024;231:119-128. using machine learning classification methods. IOP Conf Ser
doi: 10.1016/j.procs.2023.12.183 Mater Sci Eng. 2023;1296(1):012013.
29. Fu Y, Downey ARJ, Yuan L, Zhang T, Pratt A, Balogun Y. doi: 10.1088/1757-899X/1296/1/012013
Machine learning algorithms for defect detection in metal 42. Schmitt AM, Sauer C, Höfflin D, Schiffler A. Powder
laser-based additive manufacturing: A review. J Manuf bed monitoring using semantic image segmentation to
Process. 2022;75:693-710. detect failures during 3D metal printing. Sensors (Basel).
doi: 10.1016/j.jmapro.2021.12.061 2023;23(9):4183.
30. Han F, Zou J, Ai Y, Xu C, Liu S, Liu S. Image Classification doi: 10.3390/s23094183
and Analysis During the Additive Manufacturing Process 43. Kuriachen B, Jeyaraj R, Raphael D, Ashok P, Sundari PS,
Based on Deep Convolutional Neural Networks. United Paul A. Defect detection in fused deposition modelling
States: IEEE; 2019. p. 1-4.
using lightweight convolutional neural networks. Eng Appl
31. Khan IA, Birkhofer H, Kunz D, Lukas D, Ploshikhin V. Artif Intell. 2025;141:109802.
A random forest classifier for anomaly detection in laser-
powder bed fusion using optical monitoring. Materials doi: 10.1016/j.engappai.2024.109802
(Basel). 2023;16(19):6470. 44. Sousa J, Brandau B, Darabi R, et al. Artificial intelligence for
doi: 10.3390/ma16196470 control in laser-based additive manufacturing: A systematic
review. IEEE Access. 2025;13:30845-30860.
32. Abhilash PM, Ahmed A. Convolutional neural network-
based classification for improving the surface quality of doi: 10.1109/ACCESS.2025.3537859
metal additive manufactured components. Int J Adv Manuf 45. Soori M, Jough FKG, Dastres R, Arezoo B. Additive
Technol. 2023;126(9):3873-3885. manufacturing modification by artificial intelligence,
doi: 10.1007/s00170-023-11388-z machine learning, and deep learning: A review. Addit Manuf
Front. 2025;4(2):200198.
33. Lee KH, Lee HW, Yun GJ. A defect detection framework
using three-dimensional convolutional neural network (3D- doi: 10.1016/j.amf.2025.200198
CNN) with in-situ monitoring data in laser powder bed 46. Paraskevoudis K, Karayannis P, Koumoulos EP. Real-time 3D
fusion process. Optics Laser Technol. 2023;165:109571.
printing remote defect detection (stringing) with computer
doi: 10.1016/j.optlastec.2023.109571 vision and artificial intelligence. Processes. 2020;8(11):1464.
34. Wen H, Huang C, Guo S. The application of convolutional doi: 10.3390/pr8111464
neural networks (CNNs) to recognize defects in 3D-printed
parts. Materials (Basel). 2021;14(10):2575. 47. Wang Y, Wang Z, Liu W, et al. A novel depth-connected region-
based convolutional neural network for small defect detection
doi: 10.3390/ma14102575 in additive manufacturing. Cognit Comput. 2024;17(1):36.
35. Yin X, Akmal JS, Salmi M, Björkstrand R. Data From: Annotated doi: 10.1007/s12559-024-10397-8
Image Dataset for Defects Detection in Laser Powder Bed Fusion.
Geneva: Zenodo; 2025. 48. Dong K, Ni M, Liang C, et al. Automatic detection and
localization of internal defects in additively manufactured
doi: 10.5281/zenodo.14996806 aluminum alloy based on deep learning. Measurement.
36. He K, Zhang X, Ren S, Sun J. Deep Residual Learning for 2025;244:116383.
Image Recognition. United States: IEEE; 2016. p. 770-778.
doi: 10.1016/j.measurement.2024.116383
37. Tan M. Efficientnet: Rethinking Model Scaling for 49. Scime L, Siddel D, Baird S, Paquit V. Layer-wise anomaly
Convolutional Neural Networks. [arXiv Preprint]; 2019.
detection and classification for powder bed additive
38. Ren S. Faster R-CNN: Towards Real-Time Object Detection manufacturing processes: A machine-agnostic algorithm for
with Region Proposal Networks. [arXiv Preprint]; 2015. real-time pixel-wise semantic segmentation. Addit Manuf.
39. Redmon J. You Only Look Once: Unified, Real-Time Object 2020;36:101453.
Detection. United States: IEEE; 2016. doi: 10.1016/j.addma.2020.101453
40. Chen K, Zhang P, Yan H, et al. A review of machine learning 50. Ferguson M, Ak R, Lee YTT, Law KH. Detection and
in additive manufacturing: Design and process. Int J Adv segmentation of manufacturing defects with convolutional
Manuf Technol. 2024;135(3):1051-1087. neural networks and transfer learning. Smart Sustain Manuf
doi: 10.1007/s00170-024-14543-2 Syst. 2018;2(1):137-164.
41. Akmal J, Macarie M, Björkstrand R, Minet K, Salmi M. doi: 10.1520/SSMS20180033

Volume 4 Issue 3 (2025) 15 doi: 10.36922/MSAM025150022