Deep learning for anomaly detection in wire-arc additive manufacturing

Abstract Wire-arc additive manufacturing (WAAM) is becoming the most important metal additive manufacturing process in many industries. In this paper, one of the common problems of irregularity in the metal deposition in WAAM has been addressed and solved using machine learning (ML). A deep learning-based convolutional neural network (CNN) was used to classify the two classes of deposited beads, i.e. ‘regular bead’ and ‘irregular bead’. A digital camera was installed with a WAAM setup to obtain the images of beads after deposition. A single layer of deposition was conducted on a substrate using aluminium 5356 alloy filler wire using robotic-controlled gas-metal arc welding (GMAW) setup. The performance of the ML model was validated using classification accuracy and processing time. The developed CNN model was checked with three types of proposed datasets. The dataset containing the training and testing ratio of 60:40 achieved an accuracy of 86.53% and 88.08% with 30 and 60 epochs respectively for testing. The proposed ML model was successful in anomaly detection in the deposited bead of WAAM and hence it helps in improving the quality of deposited layers and mechanical properties of fabricated parts.