An unsupervised machine learning algorithm for in-situ defect-detection in laser powder-bed fusion

This research studies the development of a machine-learning algorithm to detect porosity induced during laser powder bed fusion (LPBF) due to the lack of fusion (LoF) phenomenon. The detection algorithm is based on analyzing in-situ light intensity data emitted from the melt pool during LPBF. A Self-Organizing Map (SOM), an unsupervised machine learning algorithm, is thoroughly customized to classify disturbances in the light intensity signal, where the clustered disturbances are mapped with the geometrical feature and position of defects. The defects' position and size are correlated with the actual geometrical feature and position of defects identified through a post-processing computed tomography (CT) scanning. To this end, two sets of samples are designed, including 1) samples with intentional micro-voids to mimic the lack of fusion in the printed parts for assessing the sensor response and calibrating/optimizing the SOM algorithm, and 2) samples with randomized pores induced normally during the process to evaluate the proposed SOM algorithm at different process parameters. Along with the SOM approach, a volumetric segmentation method and confusion matrix are incorporated into the SOM-based algorithm to examine the sensitivity (true positive rates) and specificity (true negative rates) of defect prediction. The comparison between the outcome of the prediction algorithm and experimental CT data indicates that the sensitivity and specificity are from 61 % to 94 % and 69 % to 93 %, respectively, where the prediction percentage is highly dependent on the process parameters. In comparison with conventional prediction algorithms (e.g., Absolute Limits), the proposed SOM algorithm has a higher prediction rate when it is faster and can rapidly identify the location of defects that may open up an opportunity to develop intermittent controllers for LPBF.