Ultrasonic monitoring and machine learning integration for layer-by-layer defect detection in PBF-LB/M
El Arbi HAJJIOUI, Foued ABROUG, Khanh NGUYEN, Maher BAILI, Kamal MEDJAHER, Lionel ARNAUD
Abstract. The quality of parts produced by PBF-LB/M processes, while promising, is often compromised by defects such as gas pores and lack of fusion. In response to the global push towards closed-loop systems for real-time defect detection and correction, in-situ correction during the PBF process is critical. Real-time monitoring enables the immediate detection and mitigation of defects, preventing the propagation of defective layers and preserving the integrity of the final component. The present study proposes a novel, cost-effective approach for real-time monitoring of the PBF process. Eight PBF samples, built in AlSi10Mg material and shaped as cylinders and cubes, contained intentionally created non-lased zones to induce lasing defects in the subsequent layers. In-situ monitoring is provided using an ultrasonic acoustic sensor installed inside the building chamber. The data collection is applied on all samples throughout the building process. The collected data is then processed via the application of Artificial Neural Networks (ANN) model, where temporal and frequency features of the ultrasonic signals are extracted and analyzed, in order to detect and identify the defects. The obtained results show that the ANN achieves a success rate of 92% in both accuracy and F1-score, highlighting its effectiveness in detecting the intentionally introduced defects.
Keywords
PBF-LB/M, In-situ Monitoring, Defects Detection, Artificial Intelligence
Published online 5/7/2025, 9 pages
Copyright © 2025 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: El Arbi HAJJIOUI, Foued ABROUG, Khanh NGUYEN, Maher BAILI, Kamal MEDJAHER, Lionel ARNAUD, Ultrasonic monitoring and machine learning integration for layer-by-layer defect detection in PBF-LB/M, Materials Research Proceedings, Vol. 54, pp 59-67, 2025
DOI: https://doi.org/10.21741/9781644903599-7
The article was published as article 7 of the book Material Forming
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] M. Zhang et al., « Fatigue and fracture behaviour of laser powder bed fusion stainless steel 316L: Influence of processing parameters », Materials Science and Engineering: A, vol. 703, p. 251‑261, août 2017. https://doi.org/10.1016/j.msea.2017.07.071
[2] H. Gong, K. Rafi, H. Gu, G. D. Janaki Ram, T. Starr, et B. Stucker, « Influence of defects on mechanical properties of Ti–6Al–4V components produced by selective laser melting and electron beam melting », Materials & Design, vol. 86, p. 545‑554, déc. 2015. https://doi.org/10.1016/j.matdes.2015.07.147
[3] J. V. Gordon et al., « Defect structure process maps for laser powder bed fusion additive manufacturing », Additive Manufacturing, vol. 36, p. 101552, déc. 2020. https://doi.org/10.1016/j.addma.2020.101552
[4] W. H. Kan et al., « A critical review on the effects of process-induced porosity on the mechanical properties of alloys fabricated by laser powder bed fusion », J Mater Sci, vol. 57, no 21, p. 9818‑9865, juin 2022. https://doi.org/10.1007/s10853-022-06990-7
[5] O. Ero, K. Taherkhani, et E. Toyserkani, « 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, vol. 78, p. 103894, sept. 2023. https://doi.org/10.1016/j.addma.2023.103894
[6] G. Zenzinger, J. Bamberg, A. Ladewig, T. Hess, B. Henkel, et W. Satzger, « Process monitoring of additive manufacturing by using optical tomography », présenté à 41ST ANNUAL REVIEW OF PROGRESS IN QUANTITATIVE NONDESTRUCTIVE EVALUATION: Volume 34, Boise, Idaho, 2015, p. 164‑170. doi: 10.1063/1.4914606
[7] F. G. Cunha, T. G. Santos, et J. Xavier, « In Situ Monitoring of Additive Manufacturing Using Digital Image Correlation: A Review », Materials, vol. 14, no 6, p. 1511, mars 2021. https://doi.org/10.3390/ma14061511
[8] P. Yadav, O. Rigo, C. Arvieu, V. K. Singh, et E. Lacoste, « Data processing techniques for in-situ monitoring in PBF-LB/M process », Journal of Manufacturing Processes, vol. 81, p. 155‑165, sept. 2022. https://doi.org/10.1016/j.jmapro.2022.06.062
[9] P. Yadav, O. Rigo, C. Arvieu, E. Le Guen, et E. Lacoste, « In Situ Monitoring Systems of The SLM Process: On the Need to Develop Machine Learning Models for Data Processing », Crystals, vol. 10, no 6, p. 524, juin 2020. https://doi.org/10.3390/cryst10060524
[10] R. McCann et al., « In-situ sensing, process monitoring and machine control in Laser Powder Bed Fusion: A review », Additive Manufacturing, vol. 45, p. 102058, sept. 2021. https://doi.org/10.1016/j.addma.2021.102058
[11] S. K. Everton, M. Hirsch, P. Stravroulakis, R. K. Leach, et A. T. Clare, « Review of in-situ process monitoring and in-situ metrology for metal additive manufacturing », Materials & Design, vol. 95, p. 431‑445, avr. 2016. https://doi.org/10.1016/j.matdes.2016.01.099
[12] J. R. Tempelman et al., « Detection of keyhole pore formations in laser powder-bed fusion using acoustic process monitoring measurements », Additive Manufacturing, vol. 55, p. 102735, juill. 2022. https://doi.org/10.1016/j.addma.2022.102735
[13] I. Zhirnov et D. Kouprianoff, « Acoustic Diagnostic of Laser Powder Bed Fusion Processes », in Advances in Transdisciplinary Engineering, A. H. C. Ng, A. Syberfeldt, D. Högberg, et M. Holm, Éd., IOS Press, 2022. doi: 10.3233/ATDE220173
[14] D. Ye, G. S. Hong, Y. Zhang, K. Zhu, et J. Y. H. Fuh, « Defect detection in selective laser melting technology by acoustic signals with deep belief networks », Int J Adv Manuf Technol, vol. 96, no 5‑8, p. 2791‑2801, mai 2018. https://doi.org/10.1007/s00170-018-1728-0
[15] M. Seleznev et al., « In situ detection of cracks during laser powder bed fusion using acoustic emission monitoring », Additive Manufacturing Letters, vol. 3, p. 100099, déc. 2022. https://doi.org/10.1016/j.addlet.2022.100099
[16] T. Wuest, D. Weimer, C. Irgens, et K.-D. Thoben, « Machine learning in manufacturing: advantages, challenges, and applications », Production & Manufacturing Research, vol. 4, no 1, p. 23‑45, janv. 2016. https://doi.org/10.1080/21693277.2016.1192517
[17] K. Taherkhani, O. Ero, F. Liravi, S. Toorandaz, et E. Toyserkani, « On the application of in-situ monitoring systems and machine learning algorithms for developing quality assurance platforms in laser powder bed fusion: A review », Journal of Manufacturing Processes, vol. 99, p. 848‑897, août 2023. https://doi.org/10.1016/j.jmapro.2023.05.048
[18] V. Pandiyan, R. Drissi-Daoudi, S. Shevchik, G. Masinelli, R. Logé, et K. Wasmer, « Analysis of time, frequency and time-frequency domain features from acoustic emissions during Laser Powder-Bed fusion process », Procedia CIRP, vol. 94, p. 392‑397, 2020. https://doi.org/10.1016/j.procir.2020.09.152
[19] F. Imani, A. Gaikwad, M. Montazeri, P. Rao, H. Yang, et E. Reutzel, « Layerwise In-Process Quality Monitoring in Laser Powder Bed Fusion », in Volume 1: Additive Manufacturing; Bio and Sustainable Manufacturing, College Station, Texas, USA: American Society of Mechanical Engineers, juin 2018, p. V001T01A038. doi: 10.1115/MSEC2018-6477
[20] K. Thameur, T. Marc, G. Raynald, et E. B. Mohamed, « Comparison between the efficiency of L.M.D and E.M.D algorithms for early detection of gear defects », Mechanics & Industry, vol. 14, no 2, p. 121‑127, 2013. https://doi.org/10.1051/meca/2012037
[21] S. Agatonovic-Kustrin et R. Beresford, « Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research », Journal of Pharmaceutical and Biomedical Analysis, vol. 22, no 5, p. 717‑727, juin 2000. https://doi.org/10.1016/S0731-7085(99)00272-1
