Shear velocity is an important parameter in pre-stack seismic reservoir description. However, in the real study, the high cost of array acoustic logging leads to lacking a shear velocity curve. Thus, it is crucial to use conventional well-logging data to predict shear velocity. The shear velocity prediction methods mainly include empirical formulas and theoretical rock physics models. When using the empirical formula method, calibration should be performed to fit the local data, and its accuracy is low. When using rock physics modeling, many parameters about the pure mineral must be optimized simultaneously. We present a deep learning method to predict shear velocity from several conventional logging curves in tight sandstone of the Sichuan Basin. The XGBoost algorithm has been used to automatically select the feature curves as the model’s input after quality control and cleaning of the input data. Then, we construct a deep-feed neuro network model (DFNN) and decompose the whole model training process into detailed steps. During the training process, parallel training and testing methods were used to control the reliability of the trained model. It was found that the prediction accuracy is higher than the empirical formula and the rock physics modeling method by well validation.

Induced by coal mining, the fractures constantly occur in geologic strata until failure occurs, which provide channels for water flow. Therefore, it is essential to investigate the permeability evolution of rocks under load. Borehole sampling was conducted in a bedrock layer beneath an aquifer, and the permeability evolution of sandstone specimens under different confining pressures was tested in rock mechanics testing laboratories. The results indicated that the permeability gradually decreases with the increasing confining pressures, while the peak strength increases with the increase of confining pressures. The minimum and maximum permeabilities occurred in the sandstone specimens that were subjected to elastic deformation and strain-softening stages, respectively. The failure, and maximum permeability, of these sandstone specimens did not occur simultaneously. To prevent the flow channel being formed due to the development and failure of rock fractures, a method of backfill gob was proposed and also the influence of backfill on fracture development was discussed.

The traditional way to evaluate pedestrian safety is a reactive approach using the data at an aggregate level. The objective of this study is to develop real-time safety models for pedestrian red-light running using the signal cycle level traffic data. Traffic data for 464 signal cycles during 16 h were collected at eight crosswalks on two intersections in the city of Nanjing, China. Various real-time safety models of pedestrian red-light running were developed based on the different combination of explanatory variables using the Bayesian Poisson-lognormal (PLN) model. The Bayesian estimation approach based on Markov chain Monte Carlo simulation is utilized for the real-time safety models estimates. The models’ comparison results show that the model incorporated exposure, pedestrians’ characteristics and crossing maneuver, and traffic control and crosswalk design outperforms the model incorporated exposure and the model incorporated exposure, pedestrians’ characteristics, and crossing maneuver. The result indicates that including more variables in the real-time safety model could improve the model fit. The model estimation results show that pedestrian volume, ratio of males, ratio of pedestrians on phone talking, pedestrian waiting time, green ratio, signal type, and length of crosswalk are statistically significantly associated with the pedestrians’ red-light running. The findings from this study could be useful in real-time pedestrian safety evaluation as well as in crosswalk design and pedestrian signal optimization.

In order to solve the problem of solid waste soda residue (SR) environmental pollution and resourceful utilization, lime soil modified by high content soda residue (LSMHCSR) is prepared by solid waste SR, lime and soil. In this paper, the basic characteristics of SR and the mechanical properties of LSMHCSR were tested, and the enhancement mechanism of LSMHCSR was analyzed. The test results showed that: (1) SR is mainly composed of CaCO₃, Ca(OH)₂ and CaCl₂, with high natural moisture content, which is not recommended as a separate engineering filler; (2) As the SR content gradually increased, the optimum moisture content of LSMHCSR gradually increased, with the maximum dry density first increasing and then decreasing; (3) With SR content in the range of 10% to 30%, both 7d and 28d UCS of LSMHCSR increased first and then decreased, reaching the maximum under 15% SR, with the increase as high as 36.9% and 37.2%, respectively. The optimal material mix ratio was SR:lime:soil = 15%:6%:85%; (4) An appropriate amount of SR could effectively promote the physical filling, cementation, crystallization and carbonization, and pozzolanic reactions of the material, and the resulting cementing substances, such as CaCO₃ crystals, C-H-S and N-A-S-H, could improve the material strength. However, under excessive SR amounts, the excess SR did not react, with the material strength reduced. Based on the engineering benefit analysis of the test section, lime soil modified by high content SR can effectively alleviate the road material supply shortage, soil erosion and solid waste pollution problems, demonstrating remarkable technical, economic and social benefits and enjoying a good prospect of application and promotion.

In the reuse stage of a gob-side entry retaining, failure of the structure and stability of the main roof have a significant effect on the safety of the advanced support and ventilation space at the working face. In this study, field investigation, theoretical analysis, and industrial experimentation were performed to analyse the fracture characteristics and formation process of the gob-side entry retaining roof during the reuse period. A dynamic-equilibrium mechanical model of the main roof structure is presented and the formation mechanisms of different types of short cantilever rock beam structures are clarified. The following major conclusions are drawn: (1) Three types of short cantilever rock beam structures occur in the main roof of a gob-side entry retaining during the reuse period, namely, the short cantilever-articulated rock beam structure, short cantilever step rock beam (type I) structure, and short cantilever step rock beam (type II) structure. (2) The stability criterion for these three short cantilever rock beam structures was also determined; that is, when the sliding instability coefficient K1, the short cantilever-articulated rock beam structure will form, and when the sliding instability coefficient K<1, the short cantilever step rock beam (type I or II) will form. (3) The governing law for the thicknesses of the main roof, immediate roof, and coal seam of the short cantilever rock beam structure was clarified; namely, the K-value gradually increases with increases in the thickness of the coal seam, drops sharply and then decreases gradually with increases in the thickness of the main roof, and decreases slowly with increases in the thickness of the immediate roof. The research results were validated at the gob-side entry retaining project in the Huainan mining area and have theoretical significance and reference value for roadway support projects with similar conditions.