Predicting triaxial compressive strength of high-temperature treated rock using machine learning techniques

The accurate prediction of the strength of rocks after high-temperature treatment is important for the safety maintenance of rock in deep underground engineering.Five machine learning(ML)techniques were adopted in this study,i.e.back propagation neural network(BPNN),AdaBoost-based classification and regression tree(AdaBoost-CART),support vector machine(SVM),K-nearest neighbor(KNN),and radial basis function neural network(RBFNN).A total of 351 data points with seven input parameters(i.e.diameter and height of specimen,density,temperature,confining pressure,crack damage stress and elastic modulus)and one output parameter(triaxial compressive strength)were utilized.The root mean square error(RMSE),mean absolute error(MAE)and correlation coefficient(R)were used to evaluate the prediction performance of the five ML models.The results demonstrated that the BPNN shows a better prediction performance than the other models with RMSE,MAE and R values on the testing dataset of 15.4 MPa,11.03 MPa and 0.9921,respectively.The results indicated that the ML techniques are effective for accurately predicting the triaxial compressive strength of rocks after different high-temperature treatments.

Non-mechanical behaviors of soft clay in two-dimensional electro-osmotic consolidation

To investigate the soil behaviors in a direct current field on both spatial and temporal scales, a 1: 5 scale model test was conducted in laboratory to simulate the two-dimensional (2D) electro-osmotic consolidation of soft clay foundation. Volume of drainage, intensity, voltage, water content and pH value of water collected in the cathodes were monitored. The pH values of soil and the mass of anodes were measured before and after the test. The test results indicate that the unsaturated state, resultant from fissures induced by the differences in water contents, is favorable to dynamic compaction of soil during electro-osmotic drainage. The results also demonstrate that water content, degree of saturation and electric potential distributions can be used to deduce the electro-osmotic drainage process. Water content of soil decreases first near electrodes, while keeps nearly constant in the center of the model. The area with constant water content is larger than half of the sample surface. Moving anodes towards cathodes by about one third of the electrode spacing is effective to improve the treatment effect after electro-osmosis stops due to the large resistance. Moreover, it is observed that during electro-osmosis, the corrosion rate of anodes becomes smaller, while the variation in pH values of soil near anodes becomes larger.

A Frost Heaving Prediction Approach for Ground Uplift Simulation Due to Freeze-Sealing Pipe Roof Method

Freeze-sealing pipe roof method is applied in the Gongbei tunnel,which causes the ground surface uplift induced by frost heave.A frost heaving prediction approach based on the coefficient of cold expansion is proposed to simulate the ground deformation of the Gongbei tunnel.The coefficient of cold expansion in the model and the frost heaving rate from the frost heave test under the hydration condition can achieve a good correspondence making the calculation result closer to the actual engineering.The ground surface uplift along the lateral and longitudinal direction are respectively analyzed and compared with the field measured data to validate the model.The results show that a good agreement between the frost heaving prediction model and the field measured data verifies the rationality and applicability of the proposed model.The maximum uplift of the Gongbei tunnel appears at the center of the model,gradually decreasing along with the lateral and longitudinal directions.The curve in the lateral direction presents a normal distribution due to the influence of the constraint of two sides,while the one along the lateral direction shapes like a parabola with the opening downward due to the temperature field distribution.The model provides a reference for frost heaving engineering calculation.

Predicting the strut forces of the steel supporting structure of deep excavation considering various factors by machine learning methods

The application of steel strut force servo systems in deep excavation engineering is not widespread,and there is a notable scarcity of in-situ measured datasets.This presents a significant research gap in the field.Addressing this,our study introduces a valuable dataset and application scenarios,serving as a reference point for future research.The main objective of this study is to use machine learning(ML)methods for accurately predicting strut forces in steel supporting structures,a crucial aspect for the safety and stability of deep excavation projects.We employed five different ML methods:radial basis function neural network(RBFNN),back propagation neural network(BPNN),K-Nearest Neighbor(KNN),support vector machine(SVM),and random forest(RF),utilizing a dataset of 2208 measured points.These points included one output parameter(strut forces)and seven input parameters(vertical position of strut,plane position of strut,time,temperature,unit weight,cohesion,and internal frictional angle).The effectiveness of these methods was assessed using root mean square error(RMSE),correlation coefficient(R),and mean absolute error(MAE).Our findings indicate that the BPNN method outperforms others,with RMSE,R,and MAE values of 72.1 kN,0.9931,and 57.4 kN,respectively,on the testing dataset.This study underscores the potential of ML methods in precisely predicting strut forces in deep excavation engineering,contributing to enhanced safety measures and project planning.

Displacement and force analyses of piles in the pile-caisson composite structure under eccentric inclined loading considering different stratum features

A novel anchorage for long-span suspension bridges,called pile-caisson composite structures,was recently proposed by the authors in an attempt to reduce the construction period and costs.This study aims to investigate the displacement and force behavior of piles in a pile-caisson composite structure under eccentric inclined loading considering different stratum features.To this end,both 1g model tests and three-dimensional numerical simulations were performed.Two groups of 1g model tests were used to validate the finite-element(FE)method.Parametric studies were then performed to investigate the effects of groundwater level,burial depth of the pile-caisson composite structure,and distribution of soil layers on the performance of the pile-caisson composite structure.The numerical analyses indicated that the influence of the groundwater level on the stability of the caisson was much greater than that of the piles.In addition,increasing the burial depth of the pile-caisson composite structure can assist in reducing the displacements and improving the stability of the pile-caisson composite structure.In addition,the distribution of soil layers can significantly affect the stability of the pile-caisson composite structure,especially the soil layer around the caisson.

Response of operating metro tunnels to compensation grouting of an underlying large-diameter shield tunnel:A case study in Hangzhou

Due to the shield tunneling underneath,long-term settlements may develop in the existing metro tunnels.The compensation grouting is applied worldwide to stabilize the settlement of ground and existing structures.Few field studies concerning large-diameter shield pass-ing tunnel from below have analyzed the interaction between the compensation grouting and the existing tunnel.This paper presents a case study on the response of the operating metro tunnels to the compensation grouting of an underlying large-diameter tunnel in muddy clay stratum.The tunnel deformations before,during,and after the compensation grouting were monitored and analyzed.The long-term tunnel settlements were mitigated and stabilized by the timely compensation grouting.Smaller settlement rates were observed during the grouting treatment,and the settlement was gradually stabilized three months after the grouting.The grouting holes at the tunnel invert were used initially for better grouting efficiency.The horizontal displacement and convergence developed during the grouting construc-tion and remained stable after the grouting process.Moreover,some limitations of the grouting treatment were discussed.The tunnel settlement in the section close to the center-line of the south-line tunnel cannot be prevented effectively.The differential displacement cannot be reduced by this grouting program.

Behaviours of existing shield tunnels due to tunnelling underneath considering asymmetric ground settlements

New tunnelling underneath could influence existing shield tunnels in underground spaces.The evaluation of the influences of tunnelling-induced ground movements on existing tunnels has been a major concern during urban construction.This paper presents a two-stage analytical method that considers the asymmetric ground settlement for investigating the longitudinal tunnel responses to new tunnelling.An improved semi-analytical solution considering the horizontal movement of the new tunnel is established for evaluating the tunnelling-induced asymmetric greenfield settlement.The proposed method is verified with field measurement data from a case study.A parametric analysis is conducted to study the influences of the input parameters on the tunnel responses.Results indicate that the horizontal movement of the new tunnel due to bias loading or asymmetric construction may lead to asymmetric responses of the existing tunnel.With increasing tunnel horizontal movement,the asymmetry of the tunnel responses becomes more obvious.An increase in the pillar depth and decreases in the tunnel horizontal movement and skew angle lower the internal forces induced by new tunnelling.