Fictitious soil pile model for dynamic analysis of pipe piles under high-strain conditions

A fictitious soil pile(FSP)model is developed to simulate the behavior of pipe piles with soil plugs undergoing high-strain dynamic impact loading.The developed model simulates the base soil with a fictitious hollow pile fully filled with a soil plug extending at a cone angle from the pile toe to the bedrock.The friction on the outside and inside of the pile walls is distinguished using different shaft models,and the propagation of stress waves in the base soil and soil plug is considered.The motions of the pile—soil system are solved by discretizing them into spring-mass model based on the finite difference method.Comparisons of the predictions of the proposed model and conventional numerical models,as well as measurements for pipe piles in field tests subjected to impact loading,validate the accuracy of the proposed model.A parametric analysis is conducted to illustrate the influence of the model parameters on the pile dynamic response.Finally,the effective length of the FSP is proposed to approximate the affected soil zone below the pipe pile toe,and some guidance is provided for the selection of the model parameters.

Dynamic response of a pile embedded in elastic half space subjected to harmonic vertical loading

An analytical method is developed to investigate the dynamic response of a pile subjected to harmonic vertical loading.The pile is modeled as a one-dimensional（1D）elastic rod.The elastic soil is divided into a homogeneous half space underlying the base of pile and a series of infinitesimally thin layers along the vertical shaft of pile.The analytical solution for the soil-pile dynamic interaction problem is obtained by the method of Hankel transformation.The proposed solution is compared with the classical plane strain solution.Arithmetical examples are presented to demonstrate the sensitivity of the vertical impedance of the pile to relevant parameters.

Prediction of bearing capacity of pile foundation using deep learning approaches

The accurate prediction of bearing capacity is crucial in ensuring the structural integrity and safety of pile foundations.This research compares the Deep Neural Networks(DNN),Convolutional Neural Networks(CNN),Recurrent Neural Networks(RNN),Long Short-Term Memory(LSTM),and Bidirectional LSTM(BiLSTM)algorithms utilizing a data set of 257 dynamic pile load tests for the first time.Also,this research illustrates the multicollinearity effect on DNN,CNN,RNN,LSTM,and BiLSTM models’performance and accuracy for the first time.A comprehensive comparative analysis is conducted,employing various statistical performance parameters,rank analysis,and error matrix to evaluate the performance of these models.The performance is further validated using external validation,and visual interpretation is provided using the regression error characteristics(REC)curve and Taylor diagram.Results from the comparative analysis reveal that the DNN(Coefficient of determination(R^(2))_(training(TR))=0.97,root mean squared error(RMSE)_(TR)=0.0413;R^(2)_(testing(TS))=0.9,RMSE_(TS)=0.08)followed by BiLSTM(R^(2)_(TR)=0.91,RMSE_(TR)=0.782;R^(2)_(TS)=0.89,RMSE_(TS)=0.0862)model demonstrates the highest performance accuracy.It is noted that the BiLSTM model is better than LSTM because the BiLSTM model,which increases the amount of information for the network,is a sequence processing model made up of two LSTMs,one of which takes the input in a forward manner,and the other in a backward direction.The prediction of pile-bearing capacity is strongly influenced by ram weight(having a considerable multicollinearity level),and the effect of the considerable multicollinearity level has been determined for the model based on the recurrent neural network approach.In this study,the recurrent neural network model has the least performance and accuracy in predicting the pile-bearing capacity.