Search

The welding parameters optimization of TC4 titanium alloys/304 stainless steel (TC4/304 SS) by friction stir lap welding (FSLW) based on orthogonal test was researched. The results show that when the rotating speed was constant, the area of the high temperature zone and the peak temperature decreased with the increase of the traversing speed; when the traversing speed was constant, the area of the high temperature zone and the peak temperature increased with the increasing rotating speed. Among them, under the condition of low heat input, the interface temperature was about 912 °C, the material at the interface cannot fully react, and there was no formation of a large amount of brittle and hard intermetallic compounds; under the condition of medium heat input, the interface temperature was about 930 °C, this temperature caused a large amount of brittle and hard intermetallic compounds at the interface; under high heat input, the interface temperature was about 975 °C, a large number of intermetallic compounds were not formed at the interface.

The multi-pass fillet welds of casing pipe were welded onto the in-service pipeline, which is widely used in pipeline repairs. However, the residual stress of repairing welded joints is larger, and it is easy to cause cracks in the heat-affected zone. In this paper, the local heat treatment was used to adjust the residual stress of the repaired welded joint of the in-service pipeline. The results show that the local heat treatment is very useful for reducing the residual stress of the repair welding joint of the in-service pipeline.

The optimization of friction stir processing (FSP) parameters of magnesium alloy composite (AZ31B–SiC) based on orthogonal test was researched. The results show that the distribution of silicon carbide (SiC) particles, microhardness, tensile property, and fracture mode are greatly affected by the change in process parameters. The results show that the composite was made with a rotating speed of 750 rev·min−1, a traversing speed of 30 mm·min−1, and a processing time of three; the distribution of SiC particles is even, the microhardness difference of composite is small, the tensile property is better, and the ductile fracture is the main fracture mode. Besides, the existence of SiC and the number of FSP have a certain influence on the corrosion performance of the magnesium alloy composite (AZ31B–SiC), and the corrosion resistance of the FSP sample is obviously better than that of the AZ31B magnesium alloy.

Collaborative filtering is one of most important technologies in the field of recommender systems, the process of making predictions about user preferences for products or services by learning known user-item relationships. In this paper, slope one and item-based nearest neighbor collaborative filtering algorithms are analyzed on the Movie Lens dataset. In order to obtain better accuracy and rationality, a new combined approach is proposed that takes advantages of slope one and item-based nearest neighbor model. In addition, simple gradient descent and bias effects are used further to improve performance. Finally, some experiments are implemented on the dataset, and the experimental results show that the proposed final solution achieves great improvement of prediction accuracy when compared to the method of using slope one or item-based nearest neighbor model alone.