Penetration Depth Modeling and Process Parameter Maps for Laser Welds Using Machine Learning

Abstract

Penetration control is an important factor in determining the weld quality in keyhole mode laser welding, which enables deep penetration. In this study, machine learning models and neural network models were developed by using 380 published welding data which were constructed for steel base metals under the following welding conditions: a laser power of 0.3-16.7 kW, a welding speed of 0.3-20.0 m/min, and a bead diameter of 0.05-0.78 mm. A machine learning model SVM (supported vector machine) could accurately predict the penetration depth with a coefficient of determination, R2 of 0.95. A shallow neural network model with five nodes in only one hidden layer was developed with a slightly improved accuracy with R2 of 0.98. It was confirmed that neither model was overfitted, and process parameters (welding speed and beam diameter) maps with penetration depth contours were provided for a laser power of 2-8 kW.