Stock price prediction is an important and challenging problem for studying financial markets. Existing studies are mainly based on the time series of stock price or the operation performance of listed company. In this paper, we propose to predict stock price based on investors' trading behavior. For each stock, we characterize the daily trading relationship among its investors using a trading network. We then classify the nodes of trading network into three roles according to their connectivity pattern. Strong Granger causality is found between stock price and trading relationship indices, i.e., the fraction of trading relationship among nodes with different roles. We further predict stock price by incorporating these trading relationship indices into a neural network based on time series of stock price. Experimental results on 51 stocks in two Chinese Stock Exchanges demonstrate the accuracy of stock price prediction is significantly improved by the inclusion of trading relationship indices.

Heat dissipation and working efficiency of transport air in rolling bearing under oil-air lubrication are closely related to the flowing state of oil-air in bearing chamber. For cylindrical roller bearing NF211, numerical simulation model of oil-air flow field in bearing chamber was established combining with the practical structure features of rolling bearing and ignoring the effect caused by roller rotation. Combining with flow field numerical simulation functions of Fluent software, simulation analysis of the flow state in bearing chamber were carried out. Based on k-ε turbulent model, three-dimensional flow field in the bearing chamber and main feature parameters of inner flow were got analyzed carefully considering the effect of twirling. Comparing with the numerical simulation of simplified flow field, it showed that energy dissipation and axial velocity of the air were influenced by the effect of twirling distinctly. Simulation results were expected to give useful references for the optimization design of the oil-air lubrication system in rolling bearing.

A dynamic finite element analysis model for cylindrical roller bearing is developed, and the complex stress distribution and dynamic contacting nature of the bearing are investigated carefully based on ANSYS/LS-DYNA. Numerical simulation results show that the stress would be bigger when the element contacting with the inner or outer ring than at other times, and the biggest stress would appear near the area that roller contacting with the inner ring. Phenomenon of stress concentration on the roller is found to be very obvious during the operating process of the bearing system. The stress distributions of different elements are uneven on the same side surface of roller in its axis direction. Numerical simulation results can give useful references for the design and analysis of rolling bearing.

The utilization of the stone material in Chinese official buildings in early Ming Dynasty was mature, and the characteristics performed at the tremendous volume in scale, the flowing lines and the plain style in decoration. This paper took the stone material used in the official buildings in the three capitals (Fengyang, Nanjing and Beijing) as the research object, analyzing the stone’s characteristics, categories and related the transport ability in early Ming Dynasty.