Automatic fault detection for laser powder-bed fusion using semi-supervised machine learning

Risk-averse areas such as the medical, aerospace and energy sectors have been somewhat slow towards accepting and applying Additive Manufacturing (AM) in many of their value chains. This is partly because there are still significant uncertainties concerning the quality of AM builds. This paper introduces a machine learning algorithm for the automatic detection of faults in AM products. The approach is semi-supervised in that, during training, it is able to use data from both builds where the resulting components were certified and builds where the quality of the resulting components is unknown. This makes the approach cost efficient, particularly in scenarios where part certification is costly and time consuming. The study specifically analyses Laser Powder-Bed Fusion (L-PBF) builds. Key features are extracted from large sets of photodiode data, obtained during the building of 49 tensile test bars. Ultimate tensile strength (UTS) tests were then used to categorise each bar as 'faulty' or 'acceptable'. Using a variety of approaches (Receiver Operating Characteristic (ROC) curves and 2-fold cross-validation), it is shown that, despite utilising a fraction of the available certification data, the semi-supervised approach can achieve results comparable to a benchmark case where all data points are labelled. The results show that semi-supervised learning is a promising approach for the automatic certification of AM builds that can be implemented at a fraction of the cost currently required.