Dynamic torsional response of pre-strained end bearing pile embedded in pre-strained isotropic saturated soil medium

The influence of initial strain state on the dynamic response of an end bearing pile embedded in isotropic saturated soil is investigated through the linearized theory of small elastic perturbation superposed on largely stressed bodies. The governing equations for soil, based on Blot＇s poroelasticity theory, are derived in the cylindrical coordinates, and the pile is modeled by using the one-dimensional elastic theory. The analytical solutions of pile impedance, frequency response of both twist angle and time history of velocity response are obtained by using of separation of variables technique. Finally, a parametric study of the influence of initial strains on the torsional impedance, twist angle, and velocity response at the top of the pile is carried out.

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.

A new method of testing pile using dynamic P-S-curve made by amplitude of wave train

A new method of detecting the vertical bearing capacity for single-pile with high strain is discussed in this paper. A heavy hammer or a small type of rocket is used to strike the pile top and the detectors are used to record vibra- tion graphs. An expression of higher degree of strain (deformation force) is introduced. It is testified theoretically that the displacement, velocity and acceleration cannot be obtained by simple integral acceleration and differential velocity when long displacement and high strain exist, namely when the pile phase generates a whole slip relative to the soil body. That is to say that there are non-linear relations between them. It is educed accordingly that the force P and displacement S are calculated from the amplitude of wave train and (dynamic) P-S curve is drew so as to determine the yield points. Further, a method of determining the vertical bearing capacity for single-pile is dis- cussed. A static load test is utilized to check the result of dynamic test and determine the correlative constants of dynamic-static P(Q)-S curve.

Stability Analysis of Piles Subjected to Lateral Load in Static and Seismic Conditions

It is disclosed a method for the stability analysis of foundation piles and piers subjected to lateral loading, both static and seismic conditions. The stability analysis for stratified soil is based upon the models of foundation soil-structure interaction and the Rankine＇s theory of earth passive pressure. In addition, its application is simpler and it can be solved using a spreadsheet. The procedure described in this work can be used in homogeneous soils as in stratified soils, considers the horizontal drag forces exerted by the soil mass against the foundation during an earthquake, can be used easily in the four pile and piers boundary cases, and considers the pore pressure generated in a fine saturated soil during an earthquake or during a rapid application of the horizontal load. The solution of two examples are shown, one in static condition and one in seismic condition, detailing the procedure step by step.