Real Time Monitoring in L-PBF Using a Machine Learning Approach

Abstract Laser powder bed fusion (L-PBF) is an additive manufacturing process whereby a heat source (laser) is used to consolidate material in powder form to build three-dimensional parts. This paper uses real-time monitoring in L-PBF for quality control. Acoustic Emission (AE) is used to detect various defects like pores and cracks during the powder bed selective laser melting process via the machine learning approach. Data collection is performed under various process parameters, using an AE sensor. Several time and frequency-domain features are extracted from the AE signals during data mining. K-means clustering is employed during the unsupervised learning, and a neural network approach is employed for the supervised machine learning on the dataset. Data labelling is conducted for different laser powers, clustering results and signal time durations. The results show the potential of real-time quality monitoring using AE during the L-PBF process.