Development of an Artificial Intelligence-Based System for Predicting Weld Bead Geometry

The prediction of the weld bead geometry parameters is an important aspect welding processes due to it related strength welded joint. This research focuses on using statistical design techniques and a deep learning neural network predict shape shielded metal arc (SMAW), inert gas (MIG), tungsten (TIG) processes. With techniques, experiments were carried out obtain data for generating regression models. Establishing mathematical models that shows relationship between process size significant practical applications. model enables determination when setting specific parameters. In this research, experimental results obtained build showing geometries SMAW, MIG, TIG serve as basis establishing predictive systems or optimizing we developed artificial intelligence-based system predicting complicated relations size. Both result in good correlation geometry.