Study on process parameters of coaxial powder feeding argon arc cladding based on RSM and NSGA-II algorithm

In order to improve the quality and performance of the cladding layer on the surface of the re-repaired workpiece, the argon arc cladding experiment of Nano-SiC reinforced wear-resistant coating was carried out on the surface of 316 L stainless steel by using the self-developed coaxial powder feeding tungsten argon arc cladding system. Aiming at the problem that the process parameters are difficult to optimize under the interaction of multiple factors, a multi-objective optimization method of process parameters integrated with RSM and NSGA-II algorithm is proposed. In this method, the welding unit heat input, powder feeding amount and SiC quality fraction were taken as input factors, and the microhardness, penetration depth and dilution rate were taken as response indexes. The regression model between the quality of cladding layer and process parameters was established by response surface method, and the interaction effect of process parameters on the quality of cladding layer was explored. Then, the NSGA-II algorithm was used to find the optimal combination of process parameters. Finally, the quality comparison and microstructure observation of cladding layer were carried out on the samples prepared under the optimal process parameters. The results show that the optimal parameter combination is unit heat input is 17.82 W/mm/min, powder feeding amount 8g/mm and SiC quality fraction 2%. The microhardness of the specimens under these conditions increased by 9.9%, the depth of fusion decreased by 31.9%, the dilution rate decreased by 22.4%. The morphology of the cladding layer is good without defects, and the top area is uniform and fine equiaxed grains.