Machine Learning Modeling and Hyper-Parameter Optimization for Weld Nugget Formation and Failure Behavior of Resistance Spot Welds

The welding process parameters of resistance spot are determined by quality indicators, such as nugget diameter, and tensile shear test behavior, failure load location. In this study, deep-learning models were investigated to predict the indicators from base materials parameter information. For each model, hyperparameters, number hidden layers, nodes in layer, learning rate optimizer, epochs, optimized based on model performance. regression for diameter showed coefficients determination 0.90 0.95, respectively. Two developed classify location: a 1-step that estimates location material information parameters, 2-step predicted model. classification similar accuracies approximately 90%.