Currently,the vertical drain consolidation problem is solved by numerous analytical solutions,such as time-dependent solutions and linear or parabolic radial drainage in the smear zone,and no artificial intelligence(A...Currently,the vertical drain consolidation problem is solved by numerous analytical solutions,such as time-dependent solutions and linear or parabolic radial drainage in the smear zone,and no artificial intelligence(AI)approach has been applied.Thus,in this study,a new hybrid model based on deep neural networks(DNNs),particle swarm optimization(PSO),and genetic algorithms(GAs)is proposed to solve this problem.The DNN can effectively simulate any sophisticated equation,and the PSO and GA can optimize the selected DNN and improve the performance of the prediction model.In the present study,analytical solutions to vertical drains in the literature are incorporated into the DNN–PSO and DNN–GA prediction models with three different radial drainage patterns in the smear zone under timedependent loading.The verification performed with analytical solutions and measurements from three full-scale embankment tests revealed promising applications of the proposed approach.展开更多
The mechanical behavior of sandy ground during shallow circular tunneling is explored for various overburden heights H(=0.5D,1.0D,1.5D and 2.0D;D is the diameter of the tunnel)and various dilatancy coefficients(w//=0,...The mechanical behavior of sandy ground during shallow circular tunneling is explored for various overburden heights H(=0.5D,1.0D,1.5D and 2.0D;D is the diameter of the tunnel)and various dilatancy coefficients(w//=0,1/3,1/2,and 1;/and w are the internal friction angle and dilation angle,respectively)through finite difference analyses.The ground is modeled as a linear elastic-perfectly plastic material that employs the Mohr-Coulomb yield criterion and obeys the non-associated flow rule.The ground reaction curve is applied in conjunction with the stress path as a conceptual tool for interpreting the mechanical response of the ground to tunneling.It is revealed that,at a certain relaxation value,a yield zone develops during tunneling and extends to the surface.This relaxation value increases with increases in the overburden and w//values for the cases of less shallow tunnels(i.e.,H=1.0D,1.5D and 2.0D),while for the shallowest case(H=0.5D),the extent of the yield zone to the ground surface is not sensitive to the w//value.The shear strain due to tunneling also increases with an increase in the w//value.Moreover,the w//value affects the radial displacement and the surface settlement due to tunneling.The magnitudes of the surface settlement and the radial displacement at the tunnel crown both decrease with an increase in the w//value.The relative difference in the displacement at the tunnel crown between the upper bound and lower bound values,w//(at the last computed stage),increases with an increase in the overburden height.It is recommended,therefore,that careful consideration be given to the dilatancy angle in the case of relatively less shallow tunnels.展开更多
文摘Currently,the vertical drain consolidation problem is solved by numerous analytical solutions,such as time-dependent solutions and linear or parabolic radial drainage in the smear zone,and no artificial intelligence(AI)approach has been applied.Thus,in this study,a new hybrid model based on deep neural networks(DNNs),particle swarm optimization(PSO),and genetic algorithms(GAs)is proposed to solve this problem.The DNN can effectively simulate any sophisticated equation,and the PSO and GA can optimize the selected DNN and improve the performance of the prediction model.In the present study,analytical solutions to vertical drains in the literature are incorporated into the DNN–PSO and DNN–GA prediction models with three different radial drainage patterns in the smear zone under timedependent loading.The verification performed with analytical solutions and measurements from three full-scale embankment tests revealed promising applications of the proposed approach.
文摘The mechanical behavior of sandy ground during shallow circular tunneling is explored for various overburden heights H(=0.5D,1.0D,1.5D and 2.0D;D is the diameter of the tunnel)and various dilatancy coefficients(w//=0,1/3,1/2,and 1;/and w are the internal friction angle and dilation angle,respectively)through finite difference analyses.The ground is modeled as a linear elastic-perfectly plastic material that employs the Mohr-Coulomb yield criterion and obeys the non-associated flow rule.The ground reaction curve is applied in conjunction with the stress path as a conceptual tool for interpreting the mechanical response of the ground to tunneling.It is revealed that,at a certain relaxation value,a yield zone develops during tunneling and extends to the surface.This relaxation value increases with increases in the overburden and w//values for the cases of less shallow tunnels(i.e.,H=1.0D,1.5D and 2.0D),while for the shallowest case(H=0.5D),the extent of the yield zone to the ground surface is not sensitive to the w//value.The shear strain due to tunneling also increases with an increase in the w//value.Moreover,the w//value affects the radial displacement and the surface settlement due to tunneling.The magnitudes of the surface settlement and the radial displacement at the tunnel crown both decrease with an increase in the w//value.The relative difference in the displacement at the tunnel crown between the upper bound and lower bound values,w//(at the last computed stage),increases with an increase in the overburden height.It is recommended,therefore,that careful consideration be given to the dilatancy angle in the case of relatively less shallow tunnels.