The academic society is stepping into the age of scholarly big data, where finding suitable scholars for collaboration has become ever difficult. Scholarly recommendation approaches are designed to overcome the information overload problems. However, previous methods mainly consider network topology without considering scholars academic information and the manually designed similarity measurements may not have a good performance when applying to large-scale sparse networks. This paper designs a scholarly friend recommendation system using network embedding and scholar attributes. We first construct an attributed social network by extracting scholars academic attributes from digital libraries. Then, we perform an attributed random walk which can jointly model network structure and scholar attributes. Finally, a novel graph recurrent neural framework is adopted to embed attributed scholar interactions within the model for recommendations. Experimental results on two real-world scholarly datasets demonstrate the effectiveness of our proposed method.

The machining of Ti-6Al-4V thin-walled parts is characterized by high cutting temperatures, significant force fluctuations, and complex thermomechanical coupling. Cryogenic Minimum Quantity Lubrication Technology (CMQL) uses bio-lubricant as the lubrication carrier, combined with the cooling characteristics of cryogenic temperature medium, showing good cooling and lubrication performance and environmental friendliness. However, the cooling and lubrication mechanism of different cryogenic media in synergy with bio-lubricants is still unclear. This paper establishes convective heat transfer coefficient and penetration models for cryogenic media in the cutting zone, based on the jet core theory and the continuum medium assumption. The model results show that cryogenic air has a higher heat transfer coefficient, while cryogenic CO₂ exhibits a better penetration ability in the cutting zone. Further milling experiments show that compared with cryogenic air, the average temperature rise, average cutting force and surface roughness of workpiece surface with cryogenic CO₂ as cryogenic medium are reduced by 23.6%, 32.8%, and 11.8%, respectively. It is considered that excellent permeability is the key to realize efficient cooling and lubrication in the cutting zone by Cryogenic CO₂ Minimum Quantity Lubrication Technology. This study provides a theoretical basis and technical reference for efficient precision machining of titanium alloy thin-walled parts.

Aiming at the problems that the simulation accuracy which is reduced due to the simplification of the model, a three-dimensional simulation method based on solid modeling is being proposed. By analyzing the motion relationship and positional relationship between the caries knife and the workpiece, the coordinate system of the caries machining was established. With the MATLAB software, the cutting edge model and the blade sweeping surface model of the boring cutter are sequentially established. Boolean operation is performed on the blade swept surface formed by the tooth cutter teeth with time t and the workpiece tooth geometry as well as the undeformed three-dimensional chip geometry model and the instantaneous cogging geometry model are obtained at different times. Through the compare between gear end face simulation tooth profile and the theoretical inner arc tooth profile, we verified the accuracy and rationality of the proposed method.