Ultrasonic Impact Treatment (UIT) is an effective technique for surface refinement and residual stress reduction, which is widely used in welding. This study investigates UIT-assisted Wire and Arc Additive manufacturing (WAAM). The residual stress, grain morphology and mechanical properties of post-UIT and as-deposited samples are studied. The result demonstrates that the UIT has a significant influence on the decrease of the residual stress. Moreover, the residual stress of the post-UIT samples is much lower than that of the as-deposited samples. The samples fabricated by UIT-assisted WAAM have a novel, bamboo-like distribution of prior-β grains, an alternating distribution of short columnar grains and equiaxed grains. The grain size of this bamboo-like structure is much smaller than the coarsen columnar grains. In addition, the mechanical properties of the post-UIT and as-deposited samples are compared. The results indicate that the average tensile strength of the post-UIT samples is higher, while the average elongation of the post-UIT samples is lower.

Geometric characteristics provide an important means for characterization of the quality of direct laser deposition. Therefore, improving the accuracy of a prediction model is helpful for improving deposition efficiency and quality. The three main input variables are laser power, scanning speed, and powder-feeding rate, while the width and height of the melt track are used as outputs. By applying a multi-output support vector regression (M-SVR) model based on a radial basis function (RBF), a non-linear model for predicting the geometric features of the melt track is developed. An orthogonal experimental design is used to conduct the experiments, the results of which are chosen randomly as training and testing data sets. On the one hand, compared with single-output support vector regression (S-SVR) modeling, this method reduces the root mean square error of height prediction by 22%, with faster training speed and higher prediction accuracy. On the other hand, compared with a backpropagation (BP) neural network, the average absolute error in width is reduced by 5.5%, with smaller average absolute error and better generalization performance. Therefore, the established model can provide a reference to select direct laser deposition parameters precisely and can improve the deposition efficiency and quality.