Xi'an University of Science and Technology

About: Xi'an University of Science and Technology is a education organization based out in Xi'an, China. It is known for research contribution in the topics: Coal & Coal mining. The organization has 10023 authors who have published 7317 publications receiving 51897 citations.

Web2Vec: Phishing Webpage Detection Method Based on Multidimensional Features Driven by Deep Learning

Abstract: Phishing is a kind of online attack that attempts to defraud sensitive information of network users. Current phishing webpage detection methods mainly use manual feature collection, and there are problems that feature extraction is complicated and the possible correlation between features cannot be avoided. To solve the problems, a new phishing webpage detection model is proposed, among which the main components are automatic learning representations from multi-aspects features through representation learning and extracting features by hybrid deep learning network. Firstly, the model treats URL, HTML page content, and DOM (Document Object Model) structure of webpages as character sequences respectively, and uses representation learning technology to automatically learn the representation of the webpages; then, sends multiple representations to a hybrid deep learning network composed of a convolutional neural network and a bidirectional long and short-term memory network through different channels to extract local and global features, and use the attention mechanism to strengthen the influence of important features; finally, the output of multiple channels is fused to realize classification prediction. Through four sets of experiments to verify the detection effect of the model, the results show that the overall classification effect of the model is better than the existing classic phishing webpage detection methods, the accuracy reaches 99.05%, and the false positive rate is only 0.25%. It is proved that the strategies of extracting webpage features from all aspects through representation learning and hybrid deep learning network can effectively improve the detection effect of phishing webpages.

Quantitative Estimation of the Growth of Environmentally Assisted Cracks at Flaws in Light Water Reactor Components

Abstract: Since environmentally assisted cracking (EAC) is an important degradation mechanism affecting the structural materials of nuclear power plants, numerous EAC experiments have been performed in the past three decades using standard specimens in simulated high temperature water environments to evaluate the various core materials used in light water reactors (LWRs). However, the environment, the condition of the material, and the mechanical properties near flaws in LWR components are not absolutely equivalent to those near the crack tip in standard specimens; thus, more research needs to be done before EAC growth in an actual LWR component can be accurately estimated using existing experimental EAC data. By combining the film slip-dissolution/oxidation model with the elastic-plastic finite element method and existing experimental EAC data, we have derived a method by which an estimation of EAC growth at flaws in actual LWR components can be made. In this paper we propose and discuss the use of this method. The results show that this new method basically concurs with the Fracture Research Institute (FRI) model in evaluating EAC growth across a semi-elliptic crack front under a simple tensile load and is also in approximate agreement with the experimental results obtained in evaluating EAC growth along a semi-elliptic crack front under complex loading conditions. The approach is expected to form a bridge between predicting EAC growth rate in core materials and evaluating EAC growth in key structural components in LWRs, and it is also expected that it can be used as a pre-analytical tool for EAC experiments using nonstandard specimens.

Effects of high-temperature thermal treatment on the porosity of red sandstone: an NMR analysis

Abstract: High temperatures affect the physical properties of red sandstone seriously, especially the pores. Understanding its mechanism is of great significance in coal mining following underground gasification, geothermal energy utilization, and the deep burial of nuclear waste. Nuclear magnetic resonance (NMR) was used to detect pore structure characteristics, and scanning electron microscopy (SEM) and polarizing light microscopy (PLM) were used to mechanism of change. The transverse relaxation time (T2) and signal strengths of red sandstone treated at various temperatures were observed by NMR, and then, the pore situation can be obtained, and finally, the influence of temperature on the pore structure of red sandstone can be obtained. Microscopic photographs of the pores of red sandstone were obtained by SEM and PLM to assist in explaining the process of microstructural change, especially the influences of temperature on pore characteristics and grain morphology and distribution. The researches indicate that after the heat treatment of red sandstone at 25–1300 °C, the pore and strength characteristics change in well-defined stages. Before 500 °C, the pore diameters and distribution range increase, but the porosity and internal grain structure do not change significantly. At 500–1000 °C, red sandstone micropores contract, mesopores and macropores develop, and strength decreases. After 1000 °C, the grains that comprise sandstone melt and fill many of the pores, decreasing porosity. The proportion of micropores decreases, while mesopores and macropores increase. In addition, a large number of bubbly holes appear in and on the sandstone, presumably caused by gases such as CO2, and water vapor from dehydrating grains. The changes in pore and cementation states with temperature are the main factors affecting the tensile strength of red sandstone.