Bead size and shape are important considerations for industry design and quality detection. It is hard to deduce an appropriate mathematical model for predicting the bead geometry in a continually changing welding process due to the complex interrelationship between different welding parameters and the actual bead. In this paper, an artificial neural network model for predicting the bead geometry with changing welding speed was developed. The experiment was performed by a welding robot in gas metal arc welding process. The welding speed was stochastically changed during the welding process. By transient response tests, it was indicated that the changing welding speed had a spatial influence on bead geometry, which ranged from 10 mm backward to 22 mm forward with certain welding parameters. For this study, the input parameters of model were the spatial welding speed sequence, and the output parameters were bead width and reinforcement. The bead geometry was recognized by polynomial fitting of the profile coordinates, as measured by a structured laser light sensor. The results showed that the model with the structure of 33-6-2 had achieved high accuracy in both the training dataset and test dataset, which were 99% and 96%, respectively.

As one of the widely used materials for hydro turbine runners, 13Cr4Ni martensitic stainless steels (13/4 MSS) manufactured by forging and wire arc additive manufacturing (WAAM), respectively, were selected for high-cycle fatigue tests, and the effects of microstructures and defect characteristics on fatigue mechanism were investigated. The results indicate that compared to the forged 13/4 MSS, the microstructure of the WAAM test piece is very fine, and the martensite units, consequently, are smaller in size. The yield strength and ultimate tensile strength are 685 MPa and 823 MPa for the forged specimen and 850 MPa and 927 MPa for the WAAM specimens, respectively. The fatigue strength of 10⁷ cycles at room temperature is 370 MPa for forged specimens and 468 MPa for WAAM specimens. The predominant defect of the forged 13/4 MSS specimen is inclusion, and the fatigue initiates mainly at the surface and subsurface. While for the WAAM specimen, the most commonly found defects are pores, and the fatigue initiation is internal and at the subsurface. In addition, the fine microstructure, as well as the high strength and hardness, enable the WAAM material to have higher fatigue strength. In order to assess the effect of defects on fatigue performance, the stress intensity factor and El-Haddad model were adopted in the present study. It was found that the forged specimens with fish-eye (FIE) zones and the WAAM specimens with granular bright facet (GBF) zones have longer fatigue life. The fatigue strengths of the forged 13/4 MSS were therefore predicted by defect size. In contrast, the fatigue strengths of the WAAM 13/4 MSS were predicted by both defect and GBF sizes.