Multi-objective optimization of process parameters for ultra-narrow gap welding based on Universal Kriging and NSGA II

The successful confinement of the arc by the flux band depends on the welding process parameters for achieving single-pass, multi-layer, and ultra-narrow gap welding. The sidewall fusion depth, the width of the heat-affected zone, and the line energy are utilized as comprehensive indications of the quality of the welded joint. In order to achieve well fusion and reduce the heat input to the base metal. Three welding process characteristics were chosen as the primary determinants, including welding voltage, welding speed, and wire feeding speed. The metamodel of the welding quality index was built by the orthogonal experiments. The metamodel and NSGA-II (Non-dominated sorting genetic algorithm II) were combined to develop a multi-objective optimization model of ultra-narrow gap welding process parameters. The results showed that the optimized welding process parameters can increase the sidewall fusion depth, reduce the width of the heat-affected zone and the line energy, and to some extent improve the overall quality of the ultra-narrow gap welding process.