Combined migration velocity model-building and its application in tunnel seismic prediction

We propose a combined migration velocity analysis and imaging method based on Kirchhoff integral migration and reverse time migration,using the residual curvature analysis and layer stripping strategy to build the velocity model.This method improves the image resolution of Kirchhoff integral migration and reduces the computations of the reverse time migration.It combines the advantages of efficiency and accuracy of the two migration methods.Its application in tunnel seismic prediction shows good results.Numerical experiments show that the imaging results of reverse time migration are better than the imaging results of Kirchhoff integral migration in many aspects of tunnel prediction.Field data show that this method has efficient computations and can establish a reasonable velocity model and a high quality imaging section.Combination with geological information can make an accurate prediction of the front of the tunnel geological structure.

Mach Number Prediction for a Wind Tunnel Based on the CNN-LSTM-Attention Method

The test section’s Mach number in wind tunnel testing is a significant metric for evaluating system performance.The quality of the flow field in the wind tunnel is contingent upon the system's capacity to maintain stability across various working conditions.The process flow in wind tunnel testing is inherently complex,resulting in a system characterized by nonlinearity,time lag,and multiple working conditions.To implement the predictive control algorithm,a precise Mach number prediction model must be created.Therefore,this report studies the method for Mach number prediction modelling in wind tunnel flow fields with various working conditions.Firstly,this paper introduces a continuous transonic wind tunnel.The key physical quantities affecting the flow field of the wind tunnel are determined by analyzing its structure and blowing process.Secondly,considering the nonlinear and time-lag characteristics of the wind tunnel system,a CNN-LSTM model is employed to establish the Mach number prediction model by combining the 1D-CNN algorithm with the LSTM model,which has long and short-term memory functions.Then,the attention mechanism is incorporated into the CNN-LSTM prediction model to enable the model to focus more on data with greater information importance,thereby enhancing the model's training effectiveness.The application results ultimately demonstrate the efficacy of the proposed approach.

Tunnel seismic tomography method for geological prediction and its application

Typical existing methods of tunnel geological prediction include negative apparent velocity, horizontal seismic profile, and the Tunnel Seismic Prediction （TSP） method as this technology is under development at home and abroad. Considering simpler observational methods and data processing, it is hard to accurately determine the seismic velocity of the wall rock in the front of the tunnel face. Therefore, applying these defective methods may result in inaccurate geological inferences which will not provide sufficient evidence for classifying the wall rock characteristics. This paper proposes the Tunnel Seismic Tomography （TST） method using a spatial observation arrangement and migration and travel time inversion image processing to solve the problem of analyzing the velocity structure of wall rock in the front of the tunnel face and realize accurate imaging of the geological framework of the tunnel wall rock. This method is very appropriate for geological prediction under complex geological conditions.

Predicting geological hazards during tunnel construction

The complicated geological conditions and geological hazards are challenging problems during tunnel construction,which will cause great losses of life and property.Therefore,reliable prediction of geological defective features,such as faults,karst caves and groundwater,has important practical significances and theoretical values.In this paper,we presented the criteria for detecting typical geological anomalies using the tunnel seismic prediction（TSP） method.The ground penetrating radar（GPR） signal response to water-bearing structures was used for theoretical derivations.And the 3D tomography of the transient electromagnetic method（TEM） was used to develop an equivalent conductance method.Based on the improvement of a single prediction technique,we developed a technical system for reliable prediction of geological defective features by analyzing the advantages and disadvantages of all prediction methods.The procedure of the application of this system was introduced in detail.For prediction,the selection of prediction methods is an important and challenging work.The analytic hierarchy process（AHP） was developed for prediction optimization.We applied the newly developed prediction system to several important projects in China,including Hurongxi highway,Jinping II hydropower station,and Kiaochow Bay subsea tunnel.The case studies show that the geological defective features can be successfully detected with good precision and efficiency,and the prediction system is proved to be an effective means to minimize the risks of geological hazards during tunnel construction.

Estimation of convergence of a high-speed railway tunnel in weak rocks using an adaptive neuro-fuzzy inference system(ANFIS) approach

Estimation of tunnel diameter convergence is a very important issue for tunneling construction,especially when the new Austrian tunneling method（NATM） is adopted.For this purpose,a systematic convergence measurement is usually implemented to adjust the design during the whole construction,and consequently deadly hazards can be prevented.In this study,a new fuzzy model capable of predicting the diameter convergences of a high-speed railway tunnel was developed on the basis of adaptive neuro-fuzzy inference system（ANFIS） approach.The proposed model used more than 1 000 datasets collected from two different tunnels,i.e.Daguan tunnel No.2 and Yaojia tunnel No.1,which are part of a tunnel located in Hunan Province,China.Six Takagi-Sugeno fuzzy inference systems were constructed by using subtractive clustering method.The data obtained from Daguan tunnel No.2 were used for model training,while the data from Yaojia tunnel No.1 were employed to evaluate the performance of the model.The input parameters include surrounding rock masses（SRM） rating index,ground engineering conditions（GEC） rating index,tunnel overburden（H）,rock density（？）,distance between monitoring station and working face（D）,and elapsed time（T）.The model’s performance was assessed by the variance account for（VAF）,root mean square error（RMSE）,mean absolute percentage error（MAPE） as well as the coefficient of determination（R2） between measured and predicted data as recommended by many researchers.The results showed excellent prediction accuracy and it was suggested that the proposed model can be used to estimate the tunnel convergence and convergence velocity.

Utilizing partial least square and support vector machine for TBM penetration rate prediction in hard rock conditions

Rate of penetration(ROP) of a tunnel boring machine(TBM) in a rock environment is generally a key parameter for the successful accomplishment of a tunneling project. The objectives of this work are to compare the accuracy of prediction models employing partial least squares(PLS) regression and support vector machine(SVM) regression technique for modeling the penetration rate of TBM. To develop the proposed models, the database that is composed of intact rock properties including uniaxial compressive strength(UCS), Brazilian tensile strength(BTS), and peak slope index(PSI), and also rock mass properties including distance between planes of weakness(DPW) and the alpha angle(α) are input as dependent variables and the measured ROP is chosen as an independent variable. Two hundred sets of data are collected from Queens Water Tunnel and Karaj-Tehran water transfer tunnel TBM project. The accuracy of the prediction models is measured by the coefficient of determination(R2) and root mean squares error(RMSE) between predicted and observed yield employing 10-fold cross-validation schemes. The R2 and RMSE of prediction are 0.8183 and 0.1807 for SVMR method, and 0.9999 and 0.0011 for PLS method, respectively. Comparison between the values of statistical parameters reveals the superiority of the PLSR model over SVMR one.

Reverse time migration imaging of tunnels via the finite element method using an unstructured mesh

Wavefield extrapolation is critical in reverse time migration(RTM).The finite diff erence method is primarily used to achieve wavefi eld extrapolation in case of the RTM imaging of tunnels.However,complex tunnel models,including those for karsts and fault fracture zones,are constructed using regular grids with straight curves,which can cause numerical dispersion and reduce the imaging accuracy.In this study,wavefi eld extrapolation was conducted for tunnel RTM using the finite element method,wherein an unstructured mesh was considered to be the body-fi tted partition in a complex model.Further,a Poynting vector calculation equation suitable for the unstructured mesh considered in the fi nite element method was established to suppress the interference owing to low-frequency noise.The tunnel space was considered during wavefi eld extrapolation to suppress the mirror artifacts based on the fl exibility of mesh generation.Finally,the infl uence of the survey layouts(one and two sidewalls)on the tunnel imaging results was investigated.The RTM results obtained for a simple tunnel model with an inclined interface demonstrate that the method based on unstructured meshes can effectively suppress the low-frequency noise and mirror artifacts,obtaining clear imaging results.Furthermore,the two-sidewall tunnel survey layout can be used to accurately obtain the real position of the inclined interface ahead of the tunnel face.The complex tunnel numerical modeling and actual data migration results denote the eff ectiveness of the fi nite element method in which an unstructured mesh is used.

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.

Realtime prediction of hard rock TBM advance rate using temporal convolutional network(TCN)with tunnel construction big data

Real-time dynamic adjustment of the tunnel bore machine(TBM)advance rate according to the rockmachine interaction parameters is of great significance to the adaptability of TBM and its efficiency in construction.This paper proposes a real-time predictive model of TBM advance rate using the temporal convolutional network(TCN),based on TBM construction big data.The prediction model was built using an experimental database,containing 235 data sets,established from the construction data from the Jilin Water-Diversion Tunnel Project in China.The TBM operating parameters,including total thrust,cutterhead rotation,cutterhead torque and penetration rate,are selected as the input parameters of the model.The TCN model is found outperforming the recurrent neural network(RNN)and long short-term memory(LSTM)model in predicting the TBM advance rate with much smaller values of mean absolute percentage error than the latter two.The penetration rate and cutterhead torque of the current moment have significant influence on the TBM advance rate of the next moment.On the contrary,the influence of the cutterhead rotation and total thrust is moderate.The work provides a new concept of real-time prediction of the TBM performance for highly efficient tunnel construction.

An improved artificial bee colony-random forest(IABC-RF)model for predicting the tunnel deformation due to an adjacent foundation pit excavation

An improved artificial bee colony-random forest(IABC-RF)model is proposed for predicting the tunnel deformation due to the excavation of an adjacent foundation pit.A new search strategy of the artificial bee colony(ABC)algorithm is herein developed and incorporated,with the results showing that a much higher computational efficiency can be achieved with the new model,while high computational accuracy can also be maintained.The improved ABC algorithm is thereafter utilised and combined with the random forest(RF)model,where four important hyper-parameters are optimized,for a tunnel deformation prediction.Results are thoroughly compared with those of other prediction methods based on machine learning(ML),as well as the monitored data on the site.Via the comparisons,the validity and effectiveness of the proposed model are fully demonstrated,and a more promising perspective can be seen of the method for its potential wide applications in geotechnical engineering.