Automatised quality assessment in additive layer manufacturing using layer-by-layer surface measurements and deep learning

Roux LL, Liu C, Ji Z, Kerfriden P, Gage D, Feyer F, Körner C, Bigot S (2021)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2021

Journal

Procedia CIRP Curran

Publisher: Elsevier B.V.

Book Volume: 99

Pages Range: 342-347

Conference Proceedings Title: Procedia CIRP

Event location: Naples, ITA

DOI: 10.1016/j.procir.2021.03.050

Abstract

Additive manufacturing (AM) has gained high research interests in the past but comes with some drawbacks, such as the difficulty to do in-situ quality monitoring. In this paper, deep learning is used on electron-optical images taken during the Electron Beam Melting (EBM) process to classify the quality of AM layers to achieve automatized quality assessment. A comparative study of several mainstream Convolutional Neural Networks to classify the images has been conducted. The classification accuracy is up to 95 %, which demonstrates the great potential to support in-process layer quality control of EBM.And the error analysis has shown that some human misclassification were correctly classified by the Convolutional Neural Networks.

Authors with CRIS profile

Daniel Gage Lehrstuhl für Werkstoffwissenschaften (Werkstoffkunde und Technologie der Metalle) Felix Feyer Lehrstuhl für Werkstoffwissenschaften (Werkstoffkunde und Technologie der Metalle) Carolin Körner Lehrstuhl für Werkstoffwissenschaften (Werkstoffkunde und Technologie der Metalle)

Involved external institutions

Cardiff University GB United Kingdom (GB)

How to cite

APA:

Roux, L.L., Liu, C., Ji, Z., Kerfriden, P., Gage, D., Feyer, F.,... Bigot, S. (2021). Automatised quality assessment in additive layer manufacturing using layer-by-layer surface measurements and deep learning. In Roberto Teti, Doriana M. D'Addona (Eds.), Procedia CIRP (pp. 342-347). Naples, ITA: Elsevier B.V..

MLA:

Roux, Léopold Le, et al. "Automatised quality assessment in additive layer manufacturing using layer-by-layer surface measurements and deep learning." Proceedings of the 14th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2020, Naples, ITA Ed. Roberto Teti, Doriana M. D'Addona, Elsevier B.V., 2021. 342-347.

BibTeX: Download