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

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