Robust model for tunnel squeezing using Bayesian optimized classifiers with partially missing database

Accurately predicting and estimating the squeezing and ground response to tunneling remains challenging.Moreover,tunnel-squeezing hazards are much more likely to occur in deeply buried long tunnels with complex engineering-geological environments.There-fore,a high-performance predictive model for tunnel squeezing is necessary.A superior ensemble classifier is put forward in this study,which is composed of four individual classifiers(gradient boosting classifier,extra-trees classifier,AdaBoost classifier,and Logistic regression classifier)and two optimization algorithms(Bayesian optimization(BO)and sparrow search algorithm(SSA)).The training database covers five parameters:tunnel depth(H),rock tunneling quality index(Q),tunnel diameter(D),support stiffness(K),and strength stress ratio(SSR),about which the basic information is accessible at the early design phases.However,the dataset compiled from the literature is insufficient.Thus,the ten proposed methods are used to replace the missing values.During the model training pro-cess,BO shows its strong ability to optimize seventeen hyperparameters.When applied to tune the classifiers’weights,SSA achieves a fast and efficient performance.The novel Shapley Additive Explanations–LightGBM method indicates that the K is the most important input feature,followed by SSR,Q,H,and D,respectively.The ensemble classifier is then validated using the test set and additional his-torical case projects.The validation shows that the model can achieve an accuracy of 98%(i.e.,the error rate is 2%)on the test set,higher than those achieved by previous prediction models.Moreover,the predicted probability could provide warning information for timely support measures.Finally,the application results are illustrated through tests on the tunnel sections that have not yet been excavated in the line of the Sichuan–Tibet railway project.The applied predictive tendencies and laws are in line with the practical experience.In sum-mary,the proposed model’s prediction results are reasonable,and its prediction will be more accurate as more data is collected and trained for prewarning the tunnel squeezing hazard.

Supporting structure failure caused by the squeezing tunnel creep and its reinforcement measure

Tunnels deeply buried have high crustal stress and are prone to large deformation disasters when encountering soft rock.The large deformation phenomenon during the construction process of the Maoxian Tunnel on the Chengdu-Lanzhou Railway is particularly evident.This article focuses on the large deformation problem of the No.1 inclined shaft of the Maoxian Tunnel,and uses on-site monitoring methods to explore the reasons for tunnel structure failure,and analyzes the mechanical behavior of the tunnel structure.By using numerical simulation methods,the effectiveness of the second-layer support in resisting creep loads in tunnels was studied,and the influence of the construction time of the secondlayer support on the mechanical properties of the tunnel was discussed.The results indicate that the first-layer support in the tunnel is a structural failure caused by asymmetric deformation caused by creep,while the second-layer support has a good effect on resisting creep loads.The research results can provide a technical reference for deformation control of squeezing tunnels.

Design of the yielding support used highly deformable elements for a tunnel excavated in squeezing rock

Yielding support is often used in the squeezing tunnel to prevent damage to the lining induced by large deformation of the surrounding rock.Highly Deformable Elements(HDE)which is often installed along the circumferential direction of the shotcrete lining is a common type of yielding support.To determine the yield parameters of HDE,the support characteristic of the lining using HDE and the ground pressure considering strain-softening of soft rock were analyzed by an analytical method.The analytical solution showed that when considering the strain-softening of squeezing ground,the ground pressure has a non-zero minimum value.The minimum value of ground stress can be used to determine the constant yield stress of the HDE,and the corresponding deformation of the minimum ground pressure can be used to determine the deformation capacity of the HDE.Based on the variation in the design constant yield stress and yield displacement of HDE with the in-situ stress and the mechanical parameters of the soft rock,equations were proposed for determining of the yield parameters of the HDE.

Predictive analysis of stress regime and possible squeezing deformation for super-long water conveyance tunnels in Pakistan

The prediction of the stress field of deep-buried tunnels is a fundamental problem for scientists and engineers. In this study, the authors put forward a systematic solution for this problem. Databases from the World Stress Map and the Crustal Stress of China, and previous research findings can offer prediction of stress orientations in an engineering area. At the same time, the Andersonian theory can be used to analyze the possible stress orientation of a region. With limited in-situ stress measurements, the Hock-Brown Criterion can be used to estimate the strength of rock mass in an area of interest by utilizing the geotechnical investigation data, and the modified Sheorey＇s model can subsequently be employed to predict the areas＇ stress profile, without stress data, by taking the existing in-situ stress measurements as input parameters. In this paper, a case study was used to demonstrate the application of this systematic solution. The planned Kohala hydropower plant is located on the western edge of Qinghai-Tibet Plateau. Three hydro-fracturing stress measurement campaigns indicated that the stress state of the area is SH - Sh 〉 Sv or SH 〉Sv 〉 Sh. The measured orientation of Sn is NEE （N70.3°-89°E）, and the regional orientation of SH from WSM is NE, which implies that the stress orientation of shallow crust may be affected by landforms. The modified Sheorey model was utilized to predict the stress profile along the water sewage tunnel for the plant. Prediction results show that the maximum and minimum horizontal principal stres- ses of the points with the greatest burial depth were up to 56.70 and 40.14 MPa, respectively, and the stresses of areas with a burial depth of greater than 500 m were higher. Based on the predicted stress data, large deformations of the rock mass surrounding water conveyance tunnels were analyzed. Results showed that the large deformations will occur when the burial depth exceeds 300 m. When the burial depth is beyond 800 m, serious squeezing deformations will occur in the surrounding rock masses, thus requiring more attention in the design and construction. Based on the application efficiency in this case study, this prediction method proposed in this paper functions accurately.

Tunnelling through weak and fragile rocks of Himalayas

A considerable amount of tunnelling has been going on in India for various projects such as hydroelectric power, irrigation, roads and railways. Most of these projects are located in Himalayas, far away from the urban areas. Tunnelling through weak and jointed rock masses such as the one in the Himalayas is a challenging task for the planners, designers, engineers and geologists because of high overburden, thickly vegetated surface, weak, poor and fragile rocks and highly varying geology with the presence of numerous small and big shear zones, faults, etc. Due to these reasons, various tunnelling problems have been faced in the past and are still being encountered. Failures and the problems may be regarded as challenges and opportunities for generating new knowledge base and thereby increasing self-reliance in tunnelling. The experiences of Himalayan tunnelling through weak and fragile rocks covering varying and mixed geology, understanding on tunnelling in squeezing ground conditions and applicability of TBM in Himalayas are presented. It has also been highlighted that the probe holes planning, drilling and monitoring shall be followed seriously to reduce the geological surprises.

Rock creep modeling based on discontinuous deformation analysis

Creep is one of the major problems of deep underground mining that must be studied theoretically,experimentally,and numerically over a long period.Experiments and feld tests are methods which can directly and more accurately describe the engineering practices as compared with others.However,these approaches are also time-consuming because creep problem of rock engineering,such as the roadway/tunnel squeezing phenomenon,usually lasts from several months to a few years.A numerical method can be employed to overcome this time-consuming problem.The discontinuous deformation analysis(DDA)method was originated in 1984 and received considerable attention from geo-engineers and researchers.The current paper discusses the creep calculation methods using the continuous and the discontinuous methods,and proposes a creep analysis method based on DDA.The method proposed in this paper can directly change the stiffness matrix while inheriting the advantages of the original DDA.Applying this method does not require any changes in the contact part of DDA.Thus,this method does not have any effect on the open–close iteration and convergence and can solve the creep problem,while maintaining the advantages of the original DDA.We theorized that creep problems are static problems,and based on this,the work using DDA in this study was divided into two parts:(1)addition of a new loop for the original DDA to‘‘discredited’’the total creep time into several time elements,thereby changing the material properties in each time element;and(2)division of each of the time elements by the time steps,similar to the original DDA.In this manner,one creep problem can be solved via assembling of static problems.Afterwards,the method mentioned above is employed to modeling a tunnel case.The evolution of the displacement fled and stress feld during creep are analyzed and discussed.