Modeling of Laser Welds Using Machine Learning Algorithm Part I: Penetration Depth for Laser Overlap Al/Cu Dissimilar Metal Welds

Thin sheets of Al/Cu dissimilar materials are overlap welded for the electrical connection secondary battery electrodes by laser welding. The weld penetration depth is an important joint quality to ensure strength and conductance. It difficult predict using analytical methods because high reflection small thickness base materials. Several machine learning algorithms were investigated develop regression models depth. included linear regression, decision tree, supported vector Gaussian process tree ensemble model groups. with degrees freedom showed excellent mean absolute percentage errors (MAPE) coefficients determination (R2). In particular, exponential kernels had MAPE 0.2% R2 unity. Key words: Machine learning, Laser welding, Penetration depth, Aluminum, Copper, Overlap