Burn-through prediction and weld depth estimation by deep learning model monitoring the molten pool in gas metal arc welding with gap fluctuation
Kazufumi Nomura, Koki Fukushima, T. Matsumura, Satoru Asai
Abstract
In a single bevel GMAW (gas metal arc welding) with gap fluctuation, a deep learning model was constructed using the monitoring image during the welding to predict the welding quality. We utilized Python and the library Keras and created a CNN (Convolutional neural network) model using the top surface image including the molten pool as an input. The classification model was used to predict the burn-through, and the regression model was used to estimate the penetration depth. As a result, the excessive penetration and burn-through could be predicted in advance and more than 95 % of estimated results of penetration depth were less 1 mm error for stepped and tapered sample shapes.
Topics & Concepts
Materials scienceWeldingGas metal arc weldingConvolutional neural networkPenetration depthWeld poolPenetration (warfare)Gas tungsten arc weldingArtificial neural networkBevelMechanical engineeringArc weldingMetallurgyArtificial intelligenceComputer scienceOpticsEngineeringPhysicsOperations researchWelding Techniques and Residual StressesNon-Destructive Testing TechniquesThermography and Photoacoustic Techniques