A three-dimensional finite element simulation was carried out to investigate the effects of tunnel construction on nearby pile foundation.The displacement controlled model (DCM) was used to simulate the tunneling-indu...A three-dimensional finite element simulation was carried out to investigate the effects of tunnel construction on nearby pile foundation.The displacement controlled model (DCM) was used to simulate the tunneling-induced volume loss effects.The numerical model was verified based on the results of a centrifuge test and a set of parametric studies was implemented based on this model.There is good agreement between the trend of the results of the centrifuge test and the present model.The results of parametric studies show that the tunnelling-induced pile internal force and deformation depend mainly on the pile?tunnel distance,the pile length to tunnel depth ratio and the volume loss.Two different zones are separated by a 45° line projected from the tunnel springline.Within the zone of influence,the pile is subjected to tensile force and large settlement;whereas outside the zone of influence,dragload and small settlement are induced.It is also established that the impact of tunnelling on a pile group is substantially smaller as compared with a single pile in the same location with the rear pile in a group,demonstrating a positive pile group effect.展开更多
Studies on ballistic penetration to laminates is complicated,but important for design effective protection of structures.Experimental means of study is expensive and can often be dangerous.Numerical simulation has bee...Studies on ballistic penetration to laminates is complicated,but important for design effective protection of structures.Experimental means of study is expensive and can often be dangerous.Numerical simulation has been an excellent supplement,but the computation is time-consuming.Main aim of this thesis was to develop and test an effective tool for real-time prediction of projectile penetrations to laminates by training a neural network and a decision tree regression model.A large number of finite element models were developed;the residual velocities of projectiles from finite element simulations were used as the target data and processed to produce sufficient number of training samples.Study focused on steel 4340tpolyurea laminates with various configurations.Four different 3D shapes of the projectiles were modeled and used in the training.The trained neural network and decision tree model was tested using independently generated test samples using finite element models.The predicted projectile velocity values using the trained machine learning models are then compared with the finite element simulation to verify the effectiveness of the models.Additionally,both models were trained using a published experimental data of projectile impacts to predict residual velocity of projectiles for the unseen samples.Performance of both the models was evaluated and compared.Models trained with Finite element simulation data samples were found capable to give more accurate predication,compared to the models trained with experimental data,because finite element modeling can generate much larger training set,and thus finite element solvers can serve as an excellent teacher.This study also showed that neural network model performs better with small experimental dataset compared to decision tree regression model.展开更多
文摘A three-dimensional finite element simulation was carried out to investigate the effects of tunnel construction on nearby pile foundation.The displacement controlled model (DCM) was used to simulate the tunneling-induced volume loss effects.The numerical model was verified based on the results of a centrifuge test and a set of parametric studies was implemented based on this model.There is good agreement between the trend of the results of the centrifuge test and the present model.The results of parametric studies show that the tunnelling-induced pile internal force and deformation depend mainly on the pile?tunnel distance,the pile length to tunnel depth ratio and the volume loss.Two different zones are separated by a 45° line projected from the tunnel springline.Within the zone of influence,the pile is subjected to tensile force and large settlement;whereas outside the zone of influence,dragload and small settlement are induced.It is also established that the impact of tunnelling on a pile group is substantially smaller as compared with a single pile in the same location with the rear pile in a group,demonstrating a positive pile group effect.
文摘Studies on ballistic penetration to laminates is complicated,but important for design effective protection of structures.Experimental means of study is expensive and can often be dangerous.Numerical simulation has been an excellent supplement,but the computation is time-consuming.Main aim of this thesis was to develop and test an effective tool for real-time prediction of projectile penetrations to laminates by training a neural network and a decision tree regression model.A large number of finite element models were developed;the residual velocities of projectiles from finite element simulations were used as the target data and processed to produce sufficient number of training samples.Study focused on steel 4340tpolyurea laminates with various configurations.Four different 3D shapes of the projectiles were modeled and used in the training.The trained neural network and decision tree model was tested using independently generated test samples using finite element models.The predicted projectile velocity values using the trained machine learning models are then compared with the finite element simulation to verify the effectiveness of the models.Additionally,both models were trained using a published experimental data of projectile impacts to predict residual velocity of projectiles for the unseen samples.Performance of both the models was evaluated and compared.Models trained with Finite element simulation data samples were found capable to give more accurate predication,compared to the models trained with experimental data,because finite element modeling can generate much larger training set,and thus finite element solvers can serve as an excellent teacher.This study also showed that neural network model performs better with small experimental dataset compared to decision tree regression model.
