Layer-Wise Profile Monitoring of Laser-Based Additive Manufacturing
Abstract
Additive manufacturing (AM) is a novel fabrication technique capable of producing highly
complex parts. Nevertheless, a major challenge is improving the quality of fabricated parts. While
there are a number of ways of approaching this problem, developing data-driven methods that use
AM process signatures to identify these part anomalies can be rapidly applied to improve overall
part quality during build. The objective of this study is to build a new layer-wise process signature
model to create the thermal-microstructure relationship. In this study, we derive novel key process
signatures for each layer (from melt pool thermal images), which are reduced using multilinear
principal component analysis (MPCA) and are directly correlated with layer-wise quality of the
part. Using these key process signatures, a Gaussian SVM classifier model is trained to detect the
existence of anomalies inside a layer. The proposed models are validated through a case study of
real-world direct laser deposition experiment where the layer-wise quality of the part is predicted
on the fly. The accuracy of the predictions is calculated using three measures (recall, precision,
and f-score), showing reasonable success of the proposed methodology in predicting layer-wise
quality. The ability to predict layer-wise quality enables process correction to eliminate anomalies
and to ultimately improve the quality of the fabricated part.