No abstract

The accurate prediction of surface settlement caused by large-diameter shield tunneling is crucial for the safety of the tunnel environment. However, due to the complexity and uncertainty of the rock-machine interaction and groundwater variation, it is difficult to predict the settlement by developing traditional theoretical methods. Recently, a big number of data obtained from the Chunfeng shield tunnel in China provides the possibility to predict the settlement using machine-learning methods. In this study, the equipment parameters, the geological parameters, and the monitored settlements are used to establish the models. Three machine-learning algorithms (i.e., long-short-term memory (LSTM), random forest (RF), and gated recurrent unit (GRU)) are used to predict the surface settlement. Three indicators, mean absolute error (MAE), accuracy (ACC), and coefficient of determination ( R 2 ), are selected to evaluate the prediction performance. Results demonstrated that the filtering and selection of model parameters is vitally important to the accuracy of model prediction. Among the three machine-learning algorithms, the LSTM algorithm gives the best accuracy in predicting the maximum surface settlement and can effectively predict the settlement development in different strata.

This paper investigates the stress transferring mechanism of a pressure tunnel strengthened with CFRP. A simplified mechanical model of the internal water pressure transfer from the CFRP to the lining concrete is established, and the key parameters that influence the internal water pressure transfer between the CFRP and lining concrete are identified. A solid-spring-solid three-dimensional finite element model is established. Using the numerical model, the influences of the above key parameters on the ratios of the internal water pressure borne by the concrete and CFRP are investigated. Based on the above results, a reinforcement scheme of the Yellow River Crossing Tunnel is studied and optimized as a case study. This reveals that the elastic modulus and thickness of the CFRP are the two most important factors that affect the ratios of the internal water pressure borne by the concrete and CFRP, and increasing the elastic modulus and thickness of the CFRP can decrease the ratio of the internal water pressure borne by the concrete and improve the stress state of the lining concrete.

Understanding the response law and mechanism of weak currents stimulated from coal under an impact load is significant for the prediction of coal bumps in deep coal mines. In this paper, the system for the weak current measurement of coal under an impact load is established and the response characteristics of weak currents induced by the deformation of coal under an impact load are investigated. Physical models are established to describe the process of charge transfer and explain the generation mechanism of those currents. The results show that a transient current is stimulated from the coal sample when an impact load is applied, and then, the current decays slowly, tending to be a stable value that is slightly greater than the background current. The weak current flows from the loaded volume to the unloaded volume of the coal and increases with the impact velocity in a negative exponential form. Analysis of weak currents using non-extensive entropy shows that the attenuation of the weak current obeys non-extensive statistical mechanics and the non-extensive parameter q is greater than 2. The carriers are mainly electrons, of which the distribution obeys the tip effect that electrons tend to enrich towards the tip of a crack. The generation mechanism of those weak currents induced by coal deformation is the instantaneous movement of electrons under a density difference caused by the tip effect. Research results can provide a new perspective to understand the electric phenomena of coal under an impact load as well as a new method for coal bump prediction.

This paper introduces an engineering case history of the prevention and remediation of sinkholes induced by limestone quarrying in Longmen county, Huizhou city, China, through karst groundwater-air pressure monitoring, the design and construction of a grouting curtain, and grouting effect detection. Based on hydrogeological surveys, the location of the main karst development zones and faults can be accurately delineated by combining geophysical exploration with drilling, providing a basis for curtain setting. According to the interpretation results of geophysical exploration, the monitoring boreholes of groundwater-air pressure were set up, which provided support for mine construction, optimization of prevention and remediation of the sinkhole scheme, and reduction of sinkhole risk. In order to prevent the further expansion of sinkhole hazards, grouting curtain technology was used for engineering treatment of the water inflow points of the quarry. After construction of the grouting curtain was completed, comprehensive detection methods were used to evaluate the grouting effect of the curtain. The results showed that the inflow rate reduced from 3500 to approximately 500 m3/day, the water plugging effect was significant, and the occurrence of sinkhole hazards was effectively reduced. The monitoring boreholes can capture the changes of groundwater-air pressure within karst conduit systems, and the purpose of monitoring and warning of sinkholes can be achieved by setting an appropriate warning threshold.