Prediction of surrounding rock parameters and optimization of support in tunnel crossing fault fracture zones

ABSTRACT: This study investigates the performance of yielding bolt in a weak rock mass tunnel with high in-situ stress conditions. The genetic algorithm and the Komamura-Huang rheological model are combined to perform an inversion analysis of the mechanical parameters of the weak surrounding rock mass before and after implementing the anchoring system. The results based on an actual tunnel project suggest that the mechanical properties all enhanced in the anchoring tunnel section The elastic modulus of the surrounding rock increased by 45.7%, the cohesive force increased by 18.1%, and the friction angle increased by 2.92%. Hence, the yielding bolt anchor can effectively prevent the squeezing deformation of the surrounding rock mass and improve the structural integrity of the tunnel lining. The performance of the anchoring system and the inversion process of the mechanical parameters can guide the design and construction of similar tunnel projects in weak rock mass configurations. 1. INTRODUCTION During the excavation progress in a rock tunnel under high in-situ stress, the problem of large squeezing deformation is often encountered in unfavoured geological conditions consisting of weak surrounding rock mass (Liu and Jiang 2021). There is no good treatment to deal with the large squeezing deformation of the tunnel during construction progress, which continuously leads to disasters in tunnel construction. In tunnel squeezing conditions, the supporting structure of the tunnel is complicated to construct, and the rework after the squeezing incident is time-consuming and labour-intensive. Many scholars tried numerical simulations to grasp the actual squeezing deformation characteristics of the surrounding rock during excavation. Nevertheless, most numerical methods cannot match the field monitoring data due to the subjectivity of the selection of rock mechanics parameters, the uncertainty of surrounding geological conditions, the variability of the construction process, and the limitation of mesh distorting in numerical calculation. Therefore, it is practically essential to capture the mechanical parameters of the surrounding rock mass in tunnel construction based on the field measurement data.

Different geological conditions are often encountered in the excavation of coal mine roadways, with fault-fracture zone being the most commonly seen complex geological conditions. Fault-fracture zone is characterized by complex lithologic property and joint development and can easily cause safety accidents when excavation burrows through the fault. Therefore, grouting reinforcement of fault-fracture zone is often implemented to ensure coal mine safety production. Based on the tunnel excavation case of −530 - −650 m belt conveyor inclined roadway at Huainan Pan’er Coal Mine, borehole optical fiber and electrical testing technologies were applied to monitor and analyze the dynamics of the surrounding rock stability when roadway excavation passed through the F1 fault, and evaluate the effect of grouting reinforcement on fault-fracture zone. According to the results of optical fiber and electrical methods, the distributional characteristics and evolution patterns of strain and electric resistivity were analyzed. The research pointed out the distinct difference in variation characteristics of strain and electrical fields between grouted reinforced fault-fracture zone and normal rock strata sections. This indicates that the grouting reinforcement effectively improve physical properties of rock strata in the fractured section, the stability of the rock strata at the fault-fracture zone was effectively increased, the degree of fault activation and deformation was relatively small, and roadway surrounding rock basically retained its original properties, pointing to high stability.

Based on the geological conditions of the fully weathered sandstone stratum in the expressway of the mountainous area, the Huizhou-Qingyuan section of the Yuzhan Expressway is used to analyze the mechanical parameters and creep characteristics of the surrounding rock of the tunnel through the indoor model test. It is concluded that: 1) The uniaxial compression deformation test measured the structural parameters of the fully weathered sandstone stratum structure, and obtained that the elastic modulus and internal friction angle φ of the fully weathered sandstone was 14.20°, and the cohesion c was 0.343Mpa. 2) The failure mode of fully weathered sandstone specimens was obtained by triaxial creep test. The creep curves of different weathered loads were analyzed and the Xiyuan rheological model was established. 3) The creep data was analyzed by MATLAB software, and the surrounding rock parameters under different surrounding rock were obtained.

To realize parameter feedback optimization of tunnel construction in water-rich areas, a feedback analysis method for tunnel parameters under fluid–solid coupling conditions was established based on an intelligent optimization algorithm. Firstly, the numerical calculation model was established and solved using the fluid–solid coupling model. In orthogonal design analysis, the displacement of surrounding rock and pore water pressure distribution in different rock mass parameter combinations were obtained, and the learning samples needed for machine learning were established. The input group was surrounding rock displacement and pore water pressure, and the output was rock mass parameters. Then, the Gaussian process algorithm was used to obtain the nonlinear mapping relationship contained in the learning samples. A differential evolution algorithm was used to optimize the critical parameters involved in this process. Furthermore, according to the established regression model and the measured displacement and pore water pressure in the research area, differential evolution was used again to optimize the rock mass parameters and obtain the parameter feedback analysis results. Finally, the inversion values were compared with the actual measured values, and the reliability of the surrounding rock parameters obtained from the feedback analysis was verified, providing an effective method for obtaining surrounding rock parameters for similar projects.

Blasting is a widely employed technique for tunnel construction in mountainous regions; however, it often causes damage to the surrounding rock mass, particularly in fault fracture zones, which can lead to hazards such as rockfalls and collapses. This study examines the characteristics of damage to surrounding rock due to tunnel blasting through fault fracture zones. Based on an actual tunnel blasting construction project, we conducted a finite element analysis using the JH-2 material model, taking into account the width of the fault fracture zone. Results indicate that as the width of the fault fracture zone increases, the disturbance effect of tunnel blasting on the surrounding rock becomes more pronounced. Compared to the arch bottom and arch waist of the tunnel, the tunnel vault primarily absorbs the slip deformation and compressive forces resulting from blasting disturbances in the fault fracture zone. The findings of this paper contribute a valuable methodology for analyzing the mechanical mechanisms in mountain tunnel blasting and provide essential theoretical parameters to inform the design and construction of tunnel blasting projects.

We aim at the problem of the large deformation and difficult control of surrounding rock when passing through a fault fracture zone in the centralized rail transportation lane along the south wing of Xinyi Coal Mine; the stress environment and failure mechanism of surrounding rock are analyzed through field investigation, numerical simulation, and field industrial test. The instability of the surrounding rock in the fault fracture zone was considered to be the result of the joint effect of the surrounding rock fracture development, lithology differences, water gushing occurrences, low strength of the original support, high in situ stress, and fault‐related tectonic stress. Rock blocks are collected on site at the fracture zone, and the remoulded samples are prepared for mechanical experiments in the laboratory. The basic mechanical parameters of the roadway passing through silty mudstone, sand‐mudstone interlayer, and fine sandstone were analyzed. A three‐dimensional model is established to analyze the distributions of the stress, deformation, and plastic area in the surrounding rock mass after the tunnel passes through, considering both a single‐rock mass and a multilayer‐rock mass. Based on the above analysis, the “closed support + shotcrete + grouting + anchor mesh cable coupling support” is proposed. Three stations were arranged on site to observe the mine pressure, and the field industrial test shows that, within the 100 days of observation, the maximum roof‐to‐floor convergence is 38 mm, while the maximum horizontal convergence is 56 mm. The overall reinforcement effect of the roadway is good, the surface is smooth, and there is no phenomenon of concrete cracking and bolt fracture.

The Collapse Deformation Control of Granite Residual Soil in Tunnel Surrounding Rock: A Case Study

ABSTRACTTo solve the problem of grouting reinforcement of low permeability argillaceous surrounding rocks of deep roadway, the zonal failure characteristics of the surrounding rock and the mechanism and technology of hierarchical grouting reinforcement were studied by means of rock mechanics test, numerical simulation, and field test. Based on the stress environment of the surrounding rock of deep roadway, the uniaxial and triaxial compression mechanical properties of mudstone were tested. The results showed that the shallow surrounding rock of the roadway was in a state of uniaxial compression or low confining pressure, and the strength of the surrounding rock was low with splitting failure, whose fracture opening was large. The deep surrounding rock was in the state of triaxial compression, and the strength of the surrounding rock was high with shear failure, whose fracture opening was small. The rock mechanics test and drilling peep results showed that the surrounding rock was divided into the fracture development zone, micro‐fracture zone, and fracture closure zone from shallow to deep of roadway. Based on the zonal failure characteristics of the surrounding rock in the deep roadway, the mechanism of hierarchical grouting reinforcement was put forward: Through the implementation of “ordinary cement, low pressure grouting” in the fracture development zone and the “superfine cement, high pressure grouting” in the micro‐fracture zone, the groutability and strength of the surrounding rock have significantly improved, and the anchoring structure of the surrounding rock could be improved. According to the failure characteristics of the surrounding rock of the 1103 roadway, the slurry diffusion characteristics under different grouting pressures and grouting hole spacing were simulated, and the grouting parameters were determined. The field practice of hierarchical grouting reinforcement with “3 MPa pressure grouting for fracture development zone” and “12–15 MPa pressure grouting for micro‐fracture zone” was successfully carried out, and the deformation of the 1103 roadway was effectively controlled.

This paper describes the method of public opinion trends prediction based on back-propagation (BP) neural networks. This paper compares two measures which are used to optimize shortcomings of the BP neural network: genetic algorithms and simulated annealing algorithm. To improve both genetic algorithms and simulated annealing, we combine these two algorithms to optimize the BP neural network. It can not only solve the dependence on the initial sample values of the BP neural network, but also prevent its falling into local minimum. It is this dual optimization on the BP neural network that will enhance the accuracy of public opinion trends prediction significantly.

He, X.; Zhou, X.; Xu, Y.; Ma, W., and Wu, T., 2020. Study on the influence of nonlinear seepage and grouting reinforcement on surrounding rock in subsea tunnel. In: Liu, X. and Zhao, L. (eds.), Today's Modern Coastal Society: Technical and Sociological Aspects of Coastal Research. Journal of Coastal Research, Special Issue No. 111, pp. 162–167. Coconut Creek (Florida), ISSN 0749-0208.Seepage is an important problem of tunneling engineering, which shows nonlinear characteristics in the low permeability media. Particularly in the seabed environment, Darcy's law is not accurate when considering the design of grouted subsea tunnels. Therefore, in this article, an analytical model considering nonlinear seepage and grouting reinforcement is established. Under a series of conditions, the analytical solutions of seepage fields and stress fields are derived and verified by numerical calculation. Then the influence of nonlinear seepage and grouting reinforcement on the pore pressure and effective stress of surrounding rock is investigated, and tunnel drainage is also discussed. The results indicate that tunnel excavation under nonlinear seepage is safer than that under linear Darcy's seepage, and grouting is a significant support that can not only improve the bearing capacity of surrounding rock, but also effectively reduce tunnel drainage.

Test optimization selection is a set cover problem, and heuristic algorithm for set covering problem is effective method. A genetic simulated annealing neural network fused algorithm was proposed by fusing the genetic algorithm, BP neural network and the simulated annealing algorithm, the genetic algorithm global search ability, strong ability of BP neural network training algorithm and fast search ability of simulated annealing algorithm were made full use of in this algorithm, the phenomenon falling into local optimum was avoided, and also the search efficiency and accuracy wad improved, the algorithm is applied to solve the test optimization selection problem. Example proves that this algorithm can effectively and quickly obtain test the optimal solution of optimization problems. Introduction In order to optimize the selection, the optimal combination test is chose in all possible combination of tests in the system, and the testability index can be met, while the minimum cost, include test time and test expense[1][2]. Perspective of mathematics, optimization selection is a test set covering problem, but we know set cover problem is a NP problem, when the system is on a big scale, to obtain the optimal solution is very difficult[3][4]. At present there are many more effective to solve the set covering problem of heuristic algorithm, such as genetic algorithm (GA) and simulated annealing algorithm (SA), neural network (ANN), tabu search (TS), ant colony system (ACO), etc., but these algorithms have their own advantages and defects, the effect is not ideal to solve alone, to complement each other mutual fusion has become the focus of future research[5][6][7]. This article is based on this idea, BP neural network and simulated annealing algorithm and introduced on the basis of traditional genetic algorithm, and a genetic simulated annealing neural network fusion algorithm has been formed, optimization selection can be solved faster and more accurate. Fusion algorithm Operation process of fusion algorithm The operation process of fusion algorithm is shown in Figure 1. Extreme value and dead zone analysis of algorithm In the process of solving the traditional heuristic algorithm, the maximum and minimum values appear easily. These extreme values are very close to the optimal value of algorithm, but the fusion algorithm is based on genetic algorithm, and the advantages of genetic algorithm is strong global search capability, which can avoid the occurrence of extreme value in the whole search space[8][9]. Therefore, the occurrence of extreme value can be avoided in the fusion algorithm can the occurrence of extreme value. Similarly, the genetic algorithm is good at global search, which can search to every corner of the space in the process of search, and the dead zone can be avoided in the fusion algorithm. Because of strong global search ability of the genetic algorithm, extreme value and dead zone can be avoided, but the disadvantage of slow speed is also caused in the genetic algorithm. Moreover, International Conference on Advances in Mechanical Engineering and Industrial Informatics (AMEII 2015) © 2015. The authors Published by Atlantis Press 402 The BP neural network and simulated annealing algorithm are introduced in the fusion algorithm, the search speed can be improved, and the optimal solution can solved quickly and effectively[10][11].

In order to analyse the reinforcement effect of tunnels with different surrounding rock grades in Tiger Leaping Gorge, a three-dimensional tunnel model was established. The effects of surrounding rock parameters and bolt supporting on the displacement and tension strain disturbance zone of surrounding rock were explored. The numerical results of tension strain and displacement show that the improvement of surrounding rock stability is limited by reinforcement measures, and the change of tension strain disturbance zone is also small when the rock is intact. However, when the surrounding rock is relatively fragmented, the range of tension-strain disturbance zone and displacement of the cave are very large. After strengthening, the range of tension-strain disturbance zone is reduced by 61.5%. Comparing the displacement of vault and arch waist, it can be seen that the displacement of cave in grade V surrounding rock is larger, the vertical displacement of vault is 3.5 times higher than that of grade IV surrounding rock, and the horizontal displacement of large section in arch waist is 58.63 mm, and it has great influence on the stability of tunnel. The displacement value of vault and arch waist reinforced in grade V rock is similar to that of tunnel without reinforcement in grade IV rock.

Zonal disintegration refers to the special phenomenon whereby fractured zones and intact zones appear alternately in deep‐buried surrounding rocks under high stress conditions, which are different from that of the shallow rock mass. Because the divisional rupture law in engineering practice is closely related to the force characteristics of the bolt body, this paper analyzed stress distribution rules of the same bolt body at different times and that of different bolt bodies at the same time in the case of zonal disintegration based on coordination deformation between the bolt body and surrounding rock. The nonlinear rheological mechanics model of rock mass on the elastic‐plastic interface under the maximum support pressure was established. It puts forward the theoretical calculation formula about the mechanics criterion and breakdown moment of the zonal disintegration. Using the mechanics model of interaction between a bolt and the surrounding rock, the distribution locations along the bolt body of the anchor neutral points and its maximum axial forces were discussed with the multiple theoretical neutral points. Furthermore, the location and width of each fracture zone were back analyzed. The results show that the rock mass on the elastic‐plastic interface of the surrounding rock has a significant creep effect after the excavation of the deep underground cave. While maximum deviator stress of the rock mass is more than its long‐term strength, the rock mass will fracture along a radial direction and come into the fractured zone. The multiple redistribution of the surrounding rock stress will generate alternate distribution phenomena of the fractured zone and intact zone. Meanwhile, the distribution regularity of the peaks and troughs interval of the displacement of surrounding rock leads to multiple neutral points along the anchor length direction. The computed results of zonal disintegration through the back analysis can reflect the actual space‐time evolution laws of zonal disintegration in deep underground caves.

The geological conditions in tunnel construction are unpredictable. However, unfavorable geological conditions such as fault fracture zones, weak surrounding rocks, and karst caves often appear during the construction process (especially in the karst areas of southwest China). Rush construction is very easy to cause landslides, water inrush, and other unfavorable geological diseases, especially in karst and fault fracture zone areas with high incidence and high risk of water inrush, which is a major key problem in tunnel construction. Therefore, more and more experts, scholars, and technicians pay attention to advanced water exploration in tunnel. The advanced geological prediction of tunnel geological structure has been described in detail in Chap. 3. The advanced geological prediction methods widely used in the detection of the hidden water hazards of the surrounding rock in tunnel include the ground penetrating radar method and the electrical method. High-density resistivity method is the most commonly used method. The author and his team have improved the high-density resistivity method in terms of power supply, cables, and terrain correction, forming a set of high-power electrical sounding 3D imaging technology suitable for deep buried long tunnels.

Due to the generality and particularity of Internet financial risks, it is imperative for the institutions involved to establish a sound risk prevention, control, monitoring, and management system and timely identify and alert potential risks. Firstly, the importance of Internet financial risk monitoring and evaluation is expounded. Secondly, the basic principles of backpropagation (BP) neural network, genetic algorithm (GA), and GABP algorithms are discussed. Thirdly, the weight and threshold of the BP algorithm are optimized by using the GA, and the GABP model is established. The financial risks are monitored and evaluated by the Internet financial system as the research object. Finally, GABP is further optimized by the simulated annealing (SA) algorithm. The results show that, compared with the calculation results of the BP model, the GABP algorithm can reduce the number of BP training, has high prediction accuracy, and realizes the complementary advantages of GA and BP neural network. The GABP network optimized by simulated annealing method has better global convergence, higher learning efficiency, and prediction accuracy than the traditional BP and GABP neural network, achieves better prediction effect, effectively solves the problem that the enterprise financial risk cannot be quantitatively evaluated, more accurately assesses the size of Internet financial risk, and has certain popularization value in the application of Internet financial risk prediction.