Explore the vast range of titles available.

The present research introduces an optimum performance soft computing model by comparing deep (multi-layer perceptron neural network, support vector machine, least square support vector machine, support vector regression, Takagi Sugeno fuzzy model, radial basis function neural network, and feed-forward neural network) and hybrid (relevance vector machine) learning models for estimating the pile group settlement. Six kernel functions have been used to develop the RVM model. For the first time, the single (mentioned by SRVM) and dual (mentioned by DRVM) kernel function-based RVM models have been employed for the reliability analysis of settlement of pile group in clay, optimized by genetic and particle swarm optimization algorithms. For that purpose, a database has been collected from the published article. Sixteen performance metrics have been implemented to record the model's performance. Based on the performance comparison and score analysis, models MS3, MS9, MS17, MS23, and MS25 have been recognized as the better-performing models. Furthermore, the regression error characteristics curve, Uncertainty analysis, cross-validation (k-fold = 10), and Anderson–Darling test reveal that model MS23 is the best architectural model in reliability analysis of pile group settlement. The comparison of model MS23 with published models shows that model MS23 has outperformed with a performance index of 1.9997, a20-index of 100, an agreement index of 0.9971, and a scatter index of 0.0013. The compression index, void ratio, and density influence the pile group settlement prediction. Also, the problematic multicollinearity level (variance inflation for > 10) significantly affects the performance and accuracy of the deep learning model.

Artificial neural networks, machine learning, and data preparation are normally implemented in a wide range of real-world problems, especially in geotechnical applications with optimistic prospects of accurate procedure outcomes. This technique has been utilized to precisely predict the top settlement of piles with various piles and soil parameters. Generally, the pile settlement is an essential requirement to produce a secure structure and has high-performance services. The current article presents the fitting of the artificial neural network (ANN) outcomes by calculating the coefficient of correlation between the predicted and the measured or calculated value of pile settlement. The ANN algorithm is developed using Python 3.9 IDLE and open-source libraries such as Keras, sklearn, Numpy, matplotlib, pandas, and Tensorflow. Because of random training and test performance, the model has been run at least ten times. The ANN model score and are compared for all runs in the testing phase. The higher score and values are chosen. Moreover, the Multivariate Linear Regression with the sklearn library is also offered in this article and utilized to produce a pile settlement formula by applying the same dataset used in ANN. The score and for choosing the first run of the ANN are 99.95% and 0.9631, respectively, while the correlation coefficient for the Multivariate Linear Regression in the training and testing phases is 0.972 and 0.919, respectively. Both techniques illustrate considerable results.

Pile foundation is a commonly recognized form of foundation, and earthquakes are a common seismic damage phenomenon. Accidents resulting from reduction in pile bearing capacity due to earthquakes pose a great threat to people’s lives and safety. This article investigates the interaction between soil and piles under earthquake action. Utilizing the MIDAS GTS NX finite element software, the vertical bearing characteristics of piles under earthquake action are studied. Obtained acceleration of piles, pile settlement, pile axial force, pile top horizontal displacement, soil pore water pressure, and pore pressure ratio under different earthquake magnitudes. The research results indicate that as the depth increases, the acceleration at the pile top is significantly greater than that at the pile bottom, with an average increase of 20% in acceleration at three different earthquake magnitudes; Both the beginning of the pore pressure ratio growth and the ultimate reaching of its stable pore pressure ratio coincide with a rise in earthquake magnitude. Additionally, the axial force of the pile body also increases with the magnitude of the earthquake, and the maximum axial force of the pile body can increase by 40% at the same time. Simultaneously, the magnitude of the earthquake influences both the displacement of the pile body and the settling of the pile top. This article can provide reference for pile foundation design and engineering construction in liquefaction sites.

Due to the unclear mechanisms behind tunneling-induced deformation of pile-raft foundations, there are strict global restrictions on tunneling beneath embankments of high-speed railways. This study conducted a series of two-dimensional tunneling model tests to investigate the tunneling-induced deformation characteristics and mechanisms of pile-raft foundations. Soil displacement field and pile settlement were measured using particle image velocimetry and displacement transducers. The changes in soil displacement and the flexure of the pile-raft foundation in response to varying tunnel-pile distances, ground surface loads, and tunnel volume loss were analyzed. The results indicate that the tunneling-disturbed zone can be categorized into a loosened zone and an arch zone as identified by the propagation and separation of shear bands, with significant soil settlement occurring in the loosened zone. The maximum settlement of piles in a pile-raft foundation is greater than that in greenfield due to the larger loosened zone. However, the settlement width at the ground surface in pile-raft foundations is reduced due to the blocking effect of the piles. According to the relative position between the piles and the formed arch structure, three patterns of tunneling-ground-pile systems can be identified. As the tunnel-pile distance increases, the maximum settlement of the piles decreases. Increasing surface loads hardly affects the maximum settlement value of the pile, while the tunneling-induced arch zone expands significantly. This study provides a fundamental understanding of pile settlement behavior for tunneling beneath the pile-raft foundations of high-speed railways.

This study develops the mean vertical additional stress coefficient on the basis of vertical additional stress, and an analytical solution for calculating the settlement of pile foundations is derived accordingly. The method simplifies settlement calculations by simply layering the soil layers with different compression moduli, eliminating the need for redundant layering of identical soil types, and it is validated through comparisons with the layer‐wise summation method (LSM) and real project data. The study utilizes the Mindlin solution for obtaining vertical additional stress, distinguishing between stresses caused by the loads from the pile above the calculation point and the remaining other piles (ROPs) in the group based on the horizontal distance from the calculation point to the pile centerline. For the stress caused by the loads from the ROPs in the group, the effect of pile diameter can be ignored because the horizontal distance from the calculation point to the pile centerline is usually greater than three times the pile diameter. The mean vertical additional stress coefficient is defined by integrating vertical additional stress along the calculated depth of soil and averaging it in the depth direction. Additionally, the developed method is compatible with various shaft resistance models, which can be decomposed into rectangular and triangular distributions based on the principle of equal area and consistent vertices. The effectiveness of the proposed method is demonstrated through case studies of pile groups and raft foundations, showing enhanced computational accuracy and efficiency over the conventional LSM.

The authors propose a new approach to the settlement calculation of a single widened pile in a punched hole beyond the linear dependence between stresses and deformations in soil.

An analytical method for the load transfer mechanism of the disconnected piles has been developed in terms of continuum elasticity. To simulate the behavior of a disconnected pile, a fictitious soil–pile column with a continuous modulus function is proposed. The axial force, skin force, and pile settlement along the shaft are explicitly derived. By considering the soil–pile interaction, the unknown coefficients in the solution are computed as a series of algebraic equations. The correctness of the present solution has been validated, and the convergence tests have been implemented. A parametric study has been carried out to examine the impact of various factors, including the pile location, slenderness ratio, and pile-to-soil modulus ratio, on the load transfer of disconnected piles. The results indicate that DRP may subjected to smaller pile displacement and prominent axial force along the shaft with a small slenderness ratio of piles and a big pile-to-soil modulus ratio. Specifically, the negative skin force at the upper part of the disconnected pile is almost counterbalanced by the positive skin force at the lower part of the pile. For end-bearing disconnected piles, the displacement of the surrounding soil is consistently greater than that of the shaft.

Due to the advantages of high bearing capacity, small settlement of pile body, and high material utilization rate, rotary drilling thread special-shaped pile (RDTSSP) has been applied in pile foundation engineering at home and abroad. Through the field static load test, the bearing characteristics of the single pile of the rotary drilling screw pile are tested and analyzed. Based on the field-measured data, the stress characteristics of the rotary drilling screw pile are analyzed by FLAC3D6.0 finite difference software, and the pile characteristics affecting the vertical bearing capacity of the rotary drilling screw-shaped pile are studied. The impact of various pile factors, including length, diameter, and the ratio of pile body to screw modulus, as well as the presence of an enlarged bottom, the elastic modulus of the pile, and the ratio of the pile body to soil elastic modulus, on the load-bearing capacity of rotary drilling thread special-shaped pile (RDTSSP) is examined. The results show that with the increase in pile length, the bearing capacity of the screw-shaped pile increases gradually, but when it increases to a certain value, the increased bearing capacity per unit volume decreases gradually. The increase in pile diameter will lead to a decrease in bearing capacity per unit volume, so the smaller pile diameter should be selected in the design to make full use of the material properties. The bottom expansion has little effect on the bearing capacity, but with the increase in the inner diameter of the bottom expansion, the bearing capacity increases gradually, while the bearing capacity per unit volume decreases and the material utilization rate decreases. Enhancing the modulus of a pile modestly boosts its load-bearing capacity, whereas augmenting the elastic modulus ratio between the pile and the surrounding soil substantially amplifies this capacity. The innovation of this study is to propose a new type of rotary drilling thread-shaped pile, which has significant economic and social benefits in engineering applications.

Time-dependent pile settlement under sustained service load has been reported in the literature and was defined as pile creep. Particle breakage has been found as the main mechanism for pile creep in sand by Leung et al., [1]. Based on the time-to-fracture Fontainebleau sand DEM model proposed by Lei et al., [2], particle breakage induced pile creep is first investigated in a centrifuge virtual chamber, and this is achieved using the particle refined method (PRM). The creep settlement trend observed is similar to that reported by Leung et al., [1], which demonstrates a great potential of the proposed method for the investigation of pile creep and pile ageing (set-up) behaviour.

Constructing offshore wind turbines on artificial islands is considered a viable option, but negative skin friction (NSF) is a significant adverse factor that cannot be ignored. The NSF adversely affects the bearing capacity of pile foundations. Currently, design methods for studying the impact of NSF group effects mainly rely on empirical approaches. Moreover, existing experimental studies do not simulate the NSF experienced by offshore wind turbine pile groups on artificial islands. In order to further explore the impact of pile group effects on NSF experienced by offshore wind turbine pile foundations on artificial islands, this study conducted indoor model tests on single piles and 3 × 3 rectangular pile groups in sandy soil under uniformly distributed loading on surrounding soil. The experiment measured the settlement of piles at various positions within single piles and rectangular pile groups, as well as the settlement of the soil surrounding the piles and the NSF. Through calculations, the experiment determined the neutral points and NSF group effect coefficients for each pile. The results indicate that densely spaced pile groups are advantageous in reducing settlement of the surrounding soil, thereby mitigating the adverse effects of NSF. Due to the influence of pile group effects, different positions within the group experience varying degrees of NSF. Consequently, in practical engineering applications, settlement of both the pile groups and the surrounding soil should be calculated separately. Furthermore, design considerations for the uplift forces and neutral points of piles at different positions within the pile group should adhere to distinct standards.