Laser Powder Bed Fusion (LPBF) technology is one of the most promising additive manufacturing methods due to its capability to produce complex geometries with high precision and near-net shape. Its advantages, such as design flexibility and minimal material waste, have led to widespread adoption in aerospace, medical, and automotive industries. However, LPBF can be susceptible to various process-induced defects, including cracks, lack of fusion, and porosity. These defects compromise the mechanical integrity of finished parts, hindering broader implementation of this otherwise transformative technology. In response to this challenge, in-situ monitoring and early detection of defects such as cracks is essential to ensure part quality and reliability.

In this work, we introduce a novel approach to differentiate acoustic emission (AE) events through learned embedded representations, specifically targeting crack detection during LPBF. Our process begins by extracting short AE events from the continuous AE signal, which are then used to train an autoencoder. By learning low-dimensional latent representations of these signals, the model identifies subtle patterns indicative of defects. This latent space enables the clustering of AE events into meaningful groups, aiding in the detection of crack signatures. Furthermore, this system can support unsupervised data collection for subsequent training of classification models, enhancing real-time crack detection. Altogether, the proposed framework paves the way for robust in-situ quality assurance in LPBF, equipping manufacturers with an effective tool for defect mitigation and improved part reliability.