This paper presents a surrogate modeling approach for predicting ground surface settlement caused by synchronous grouting during shield tunneling process.The proposed method combines finite element simulations with ma...This paper presents a surrogate modeling approach for predicting ground surface settlement caused by synchronous grouting during shield tunneling process.The proposed method combines finite element simulations with machine learning algorithms and introduces an intelligent optimization algorithm to invert geological parameters and synchronous grouting variables,thereby predicting ground surface settlement without conducting numerous finite element analyses.Two surrogate models based on the random forest algorithm are established.The first is a parameter inversion surrogate model that combines an artificial fish swarm algorithm with random forest,taking into account the actual number and distribution of complex soil layers.The second model predicts surface settlement during synchronous grouting by employing actual cover-diameter ratio,inverted soil parameters,and grouting variables.To avoid changes to input parameters caused by the number of overlying soil layers,the dataset of this model is generated by the finite element model of the homogeneous soil layer.The surrogate modeling approach is validated by the case history of a large-diameter shield tunnel in Beijing,providing an alternative to numerical computation that can efficiently predict surface settlement with acceptable accuracy.展开更多
Considering that the particular geometric shape of a quasi-rectangular shield,the grout flowing law and its motion process are more complicated than those of a conventional circular shield.To interpret the grouting me...Considering that the particular geometric shape of a quasi-rectangular shield,the grout flowing law and its motion process are more complicated than those of a conventional circular shield.To interpret the grouting mechanical ehaviour in the special-shape shield tail void,the filling and diffusion mechanism of synchronous grouting was analysed.The grout flowing is separated into two independent motion processes,which contains a circumferential filling and a longitudinal diffusion.The theoretical model of the grout pressure spatial distribution was derived based on the principle of fluid mechanics.Then,the pressure distributions in the two directions were obtained using a case study and compared with the field measured data to verify the validation of the model.Although the overall spatial pattern of grout pressure distribution on the tunnel profile show a change trend dominated by the self-weight effect mostly,its local fluctuation characteristics is very abnormal relative to that of a circular shield tunnel.Moreover,the important factors in the model were analysed,including the grout material parameters,the grouting construction parameters,and some geometry parameters.The results show that the pressure loss along this way is positively correlated with the grout flow velocity and is sensitive to the shear yield stress of the grout.The pressure loss along the circumferential direction is the most sensitive to the thickness of the ring cake,and the value range suitable for the model should be 0.02-0.03 m.The pressure loss along the longitudinal diffusion direction is the most sensitive to the size of the tail void.The research results can provide a theoretical basis for the control of special-shape shield construction.展开更多
Abstract.Similarity solution is investigated for the synchronous grouting of shield tunnel under the vertical non-axisymmetric displacement boundary condition in the paper.The synchronous grouting process of shield tu...Abstract.Similarity solution is investigated for the synchronous grouting of shield tunnel under the vertical non-axisymmetric displacement boundary condition in the paper.The synchronous grouting process of shield tunnel was simplified as the cylindrical expansion problem,which was based on the mechanism between the slurry and stratum of the synchronous grouting.The stress harmonic function on the horizontal and vertical ground surfaces is improved.Based on the virtual image technique,stress function solutions and Boussinesq’s solution,elastic solution under the vertical non-axisymmetric displacement boundary condition on the vertical surface was proposed for synchronous grouting problems of shield tunnel.In addition,the maximum grouting pressure was also obtained to control the vertical displacement of horizontal ground surface.The validity of the proposed approach was proved by the numerical method.It can be known fromthe parameter analysis that larger vertical displacement of the horizontal ground surface was induced by smaller tunnel depth,smaller tunnel excavation radius,shorter limb distance,larger expansion pressure and smaller elastic modulus of soils.展开更多
Uplift of segmental linings in shield tunnels presents considerable challenges,potentially compromising the structural integrity of tunnels.The uplift movement can be physically modelled using a Timoshenko beam on a W...Uplift of segmental linings in shield tunnels presents considerable challenges,potentially compromising the structural integrity of tunnels.The uplift movement can be physically modelled using a Timoshenko beam on a Winkler foundation.This study introduces an innovative method employing a physicsinformed neural network(PINN)to solve the governing differential equations of shield tunnel linings under specifiedboundary conditions,known loads,and foundation parameters.Importantly,the PINN does not rely on empirical data for training;instead,it incorporates physics-based constraints to accurately capture spatial variations in load and foundation stiffness during grouting and construction phases.The PINN model was validated with fielddata from a shield tunnel in the Pazhou branch of the Guangzhou-Dongguan-Shenzhen intercity railway line.The results demonstrate the effectiveness of the model in predicting segment uplift.Furthermore,compared to traditional analytical solutions,the PINN model provides a more realistic representation of fieldconditions by integrating spatial variations in loading and foundation support.展开更多
基金theNational Natural Science Foundation of China (GrantNos. 52178385, 52020105002, and 51991393)Scienceand Technology Program of Guangzhou, China (GrantNos. 202102020617 and 202201020171).
文摘This paper presents a surrogate modeling approach for predicting ground surface settlement caused by synchronous grouting during shield tunneling process.The proposed method combines finite element simulations with machine learning algorithms and introduces an intelligent optimization algorithm to invert geological parameters and synchronous grouting variables,thereby predicting ground surface settlement without conducting numerous finite element analyses.Two surrogate models based on the random forest algorithm are established.The first is a parameter inversion surrogate model that combines an artificial fish swarm algorithm with random forest,taking into account the actual number and distribution of complex soil layers.The second model predicts surface settlement during synchronous grouting by employing actual cover-diameter ratio,inverted soil parameters,and grouting variables.To avoid changes to input parameters caused by the number of overlying soil layers,the dataset of this model is generated by the finite element model of the homogeneous soil layer.The surrogate modeling approach is validated by the case history of a large-diameter shield tunnel in Beijing,providing an alternative to numerical computation that can efficiently predict surface settlement with acceptable accuracy.
基金sponsored by the Shanghai Rising-Star Program of China(Grant No.18QB1403800)supported by the Fundamental Research Funds for the Central Universities(Grant No.21D111320).
文摘Considering that the particular geometric shape of a quasi-rectangular shield,the grout flowing law and its motion process are more complicated than those of a conventional circular shield.To interpret the grouting mechanical ehaviour in the special-shape shield tail void,the filling and diffusion mechanism of synchronous grouting was analysed.The grout flowing is separated into two independent motion processes,which contains a circumferential filling and a longitudinal diffusion.The theoretical model of the grout pressure spatial distribution was derived based on the principle of fluid mechanics.Then,the pressure distributions in the two directions were obtained using a case study and compared with the field measured data to verify the validation of the model.Although the overall spatial pattern of grout pressure distribution on the tunnel profile show a change trend dominated by the self-weight effect mostly,its local fluctuation characteristics is very abnormal relative to that of a circular shield tunnel.Moreover,the important factors in the model were analysed,including the grout material parameters,the grouting construction parameters,and some geometry parameters.The results show that the pressure loss along this way is positively correlated with the grout flow velocity and is sensitive to the shear yield stress of the grout.The pressure loss along the circumferential direction is the most sensitive to the thickness of the ring cake,and the value range suitable for the model should be 0.02-0.03 m.The pressure loss along the longitudinal diffusion direction is the most sensitive to the size of the tail void.The research results can provide a theoretical basis for the control of special-shape shield construction.
基金The authors are grateful to the Traffic Technology Fund of Guizhou Province of China(No.2014-122-005)the National Natural Science Foundation of China(Grant No.51208523).
文摘Abstract.Similarity solution is investigated for the synchronous grouting of shield tunnel under the vertical non-axisymmetric displacement boundary condition in the paper.The synchronous grouting process of shield tunnel was simplified as the cylindrical expansion problem,which was based on the mechanism between the slurry and stratum of the synchronous grouting.The stress harmonic function on the horizontal and vertical ground surfaces is improved.Based on the virtual image technique,stress function solutions and Boussinesq’s solution,elastic solution under the vertical non-axisymmetric displacement boundary condition on the vertical surface was proposed for synchronous grouting problems of shield tunnel.In addition,the maximum grouting pressure was also obtained to control the vertical displacement of horizontal ground surface.The validity of the proposed approach was proved by the numerical method.It can be known fromthe parameter analysis that larger vertical displacement of the horizontal ground surface was induced by smaller tunnel depth,smaller tunnel excavation radius,shorter limb distance,larger expansion pressure and smaller elastic modulus of soils.
基金funded by“The Pearl River Talent Recruitment Program”in 2019(Grant No.2019CX01G338)Guangdong Province and Guangdong Provincial Basic and Applied Basic Research Fund Committee(2022A1515240073).
文摘Uplift of segmental linings in shield tunnels presents considerable challenges,potentially compromising the structural integrity of tunnels.The uplift movement can be physically modelled using a Timoshenko beam on a Winkler foundation.This study introduces an innovative method employing a physicsinformed neural network(PINN)to solve the governing differential equations of shield tunnel linings under specifiedboundary conditions,known loads,and foundation parameters.Importantly,the PINN does not rely on empirical data for training;instead,it incorporates physics-based constraints to accurately capture spatial variations in load and foundation stiffness during grouting and construction phases.The PINN model was validated with fielddata from a shield tunnel in the Pazhou branch of the Guangzhou-Dongguan-Shenzhen intercity railway line.The results demonstrate the effectiveness of the model in predicting segment uplift.Furthermore,compared to traditional analytical solutions,the PINN model provides a more realistic representation of fieldconditions by integrating spatial variations in loading and foundation support.
