 This research focused on developing a statistical design technique and a deep learning neural network to predict the Weld-B geometry parameters of shielded metal arc welding, SMAW, metal inert gas, MIG, and tungsten inert gas, TIG, welding processes. Experimental research was conducted to generate regression models which showed the relationship between welding process parameters and Weld-B sizes. Additionally, a deep learning neural network was used to develop an artificial intelligence-based system for predicting complicated relations between the welding process parameters and the Weld-B geometry. Both the regression model and the deep learning model resulted in a good correlation between the welding process parameters and the Weld-B geometry. This article was authored by Nakien Tran, Van Hung Bui, and Van Thong Hong.