Load Bearing Capacity Of Piles Research Articles

Using Machine Learning to Predict Axial Pile Capacity

Accurate estimation of the ultimate axial load bearing capacity of piles is necessary to ensure the safety of the supported structures and to prevent cost overruns. Traditional mechanics-based design methods do not always predict pile capacity accurately, or precisely, leaving room for improvement. This study focuses on the potential of machine learning (ML) in estimating pile capacity. A dataset of 546 load tests was compiled from three databases. The baseline performance of traditional design methods was first established by comparing the capacities computed using four traditional approaches, against the capacities interpreted from load tests using Davisson’s criterion. Sixteen different ML techniques were explored. First, the optimal feature selection technique for model training was investigated. Second, hyperparameters of each technique were optimized. The process involved the training of 32,000 different models and tuning their hyperparameters. Next the dataset was randomly split into training (70%) and testing (30%) for comparing the 16 different ML regression models. Each of the optimized models was then trained using six feature sets. The performance of each of the 16 ML models with the best performing feature subset was compared with the baseline performance from traditional methods. Evaluation criteria included measured versus predicted capacities, influence of soil type on accuracy, as well as the absence of pile diameter, or length effects on accuracy and precision. In general, the ML methods performed significantly better than the best traditional method. The current research demonstrated that ML may offer advantages in geotechnical design when large datasets are available.

The Influence of Backfill on the Driving Energy Intensity and Axial Load Resistance of Piles with Shaft Widenings: Modeling Research

This article is dedicated to addressing the current challenge of augmenting the load-bearingcapability of pile foundations. This predicament is most effectively addressed by employing piles with unconventional geometries along with atypical methodologies for installing these foundation piles. The primary objective of the research wasto examine the impact of various fill materials (including both soil and rigid substances) on the energy consumption during pile driving and the resistance to static loads by piles with multiple shaft expansions. The findings derived from model-based investigations demonstrate that the load-bearing capacity of piles with shaft expansions installed with bulk material filling surpassed that of conventional piles (prismatic and pyramidal) by a factor ranging from 1.5 to 4.6. Furthermore, the research outcomes also indicated greater energy consumption (1.14–1.66 times) and enhanced load-bearing capacity (1.15–1.68 times) for piles with shaft expansions driven with backfill in comparison to piles installed without backfill. It is noteworthy that the type of backfill material significantly influenced the energy consumption during pile driving and their stability under axial static loads. The correlation relationships can be applied to approximate projection of the energy-related and structural parameters of piles with shaft expansions embedded with the addition of bulk materials.

Evaluation of ultimate load - bearing capacity of piles based on static compression test and pile dynamic analysis (PDA)

Determining the load bearing capacity of piles from field tests is a reliable method that allows for the verification of load carrying capacity according to theoretical calculations, thereby the ultimate load-bearing capacity of the piles can be evaluated, serving as the basis for selecting the design load-bearing capacity that is suitable for the site conditions. Among the various pile load testing methods, static compression testing is a traditional method known for its high reliability and early adoption. However, when piles are constructed at significant depths or large diameter drilled piles have higher load bearing capacities, static compression testing encounters difficulties due to the large experimental load and extends testing times. In contrast, the pile dynamic analysis method (PDA) introduced by the Case Institute of Technology in the United States in the 1960s determines the load bearing capacity of piles based on stress wave propagation theory in elastic bars. It offers several advantages, including shorter testing times and no need for static loading, making it suitable for challenging terrain conditions. Nowadays, this method is widely used and integrated into the design guidelines and testing standards of many countries. In this article, base on the results of axial static compression tests and PDA method on reinforced concrete piles and drilled piles at several real project to compare and evaluate the load bearing values of the piles and assess the reliability of the testing methods.

Prediction of Pile Bearing Capacity Using XGBoost Algorithm: Modeling and Performance Evaluation

The major criteria that control pile foundation design is pile bearing capacity (Pu). The load bearing capacity of piles is affected by the various characteristics of soils and the involvement of multiple parameters related to both soil and foundation. In this study, a new model for predicting bearing capacity is developed using an extreme gradient boosting (XGBoost) algorithm. A total of 200 driven piles static load test-based case histories were used to construct and verify the model. The developed XGBoost model results were compared to a number of commonly used algorithms—Adaptive Boosting (AdaBoost), Random Forest (RF), Decision Tree (DT) and Support Vector Machine (SVM) using various performance measure metrics such as coefficient of determination, mean absolute error, root mean square error, mean absolute relative error, Nash–Sutcliffe model efficiency coefficient and relative strength ratio. Furthermore, sensitivity analysis was performed to determine the effect of input parameters on Pu. The results show that all of the developed models were capable of making accurate predictions however the XGBoost algorithm surpasses others, followed by AdaBoost, RF, DT, and SVM. The sensitivity analysis result shows that the SPT blow count along the pile shaft has the greatest effect on the Pu.

РАЗРАБОТКА МЕТОДИКИ РАСЧЁТА НЕСУЩЕЙ СПОСОБНОСТИ БУРОНАБИВНЫХ КОНИЧЕСКИХ СВАЙ

Three methods for determining the load-bearing capacity of bored conical piles are presented, considering the additional forces of the ground rebound along their inclined side surface under vertical load. It is proposed to determine the bearing capacity according to the results of field tests using the coefficient of transition from the maximum permissible settlement of the building foundation to the settlement of the pile obtained during static tests. Its value varies from 0.1 to 0.3 depending on the angle of the pile taper. To determine the bearing capacity of the empirical method, tabular data of the ground rebound forces on the side surface of the piles are developed. It depends on the strength properties of the base soil, the angle of the pile taper and the depth of the location of the changing cross-section of the pile along the length. The process of compressing the soil in a drilled well with an elastic cylindrical pressiometer is close to the occurrence of a ground rebound when it is pushed apart by the side surface of a conical pile during sediment under load. It is proposed to determine the ground resistance on the side surface of conical piles according to the same dependence as when processing the results of pressiometric tests of soils, taking into account the introduction of a correction factor depending on the parameters of the pile. The calculated load-bearing capacity of the piles, determined by the proposed methods, differs from the actual load-bearing capacity, determined by the results of static tests of full-scale piles, within 10 %. However, these methods need to be improved with the accumulation of statistical data for testing full-scale piles in different ground conditions.

An approach to increasing the load-bearing capacity of drilled injection piles

The problem of strengthening weak or overloaded bases is an important objective of underground space development. It is especially urgent if there are alternating weak layers in the base. The paper presents a practical geotechnical case of strengthening the overloaded base of a reinforced concrete foundation plate for a 25-storey residential building under construction. Combined soil piles that consist of Jet (type 1) soil concrete piles reinforced along the longitudinal axis with drilled injection piles made by electric discharge technology (EDT piles) are used as buried structures. This method of arrangement of a combined buried reinforced concrete structure is conditioned by the need to increase the load-bearing capacity of a pile in soil by two or more times.

Development of improved models for pile load bearing capacity, settlement and reliability analysis

Introduction. Safety of operation and durability of pile foundations and structures as a whole depend on the values of load bearing capacity of piles and reliability in the foundation soils. The key problem of pile analysis consists in reliable determination of its load bearing capacity values according to all performance criteria of the first and second groups of limit states, in revealing of reliable values of reliability (operation safety), economic efficiency and profitability.
 Materials and methods. One of the difficulties in detecting the value of the load bearing capacity of friction piles is to determine the values of friction and cohesive forces and their distribution over the side surface of the pile in the foundation soil when the loaded pile is immobilized (at rest).
 Results. Absence of reliable information on actual friction and cohesive force and, consequently, on actual load bearing capacity of a pile in the conditions of immobility does not allow to estimate its quality taking into account assurance of trouble-free operation (reliability) in real operating conditions at the pre-set operating load, it is impossible to predict the durability of a pile, to make a reasonable choice of pile shape and dimensions, etc. Another pile analysis problem is determining the value of pile settlement. The value of pile settlement is in some cases the most important indicator of the facility performance.
 Conclusions. New approaches to the operation of piles in the foundation soil on the basis of modern methods of reliability calculations with limited statistical information about controlled parameters are proposed. Improvement and development of pile calculation methods can be found in the calculation of deep trencher foundations, in the calculation of open caissons and caissons, the development of new statutory documents on pile foundations; as well as during training process of various universities and as a source for advanced training of specialists.

MODELING OF STRESS-STRAIN STATE OF HIGH-RISE BUILDING PILE RAFT FOUNDATION WITH INCOMPLETE PILE INSTALLATION

The object of the study is a pile-raft foundation or mat foundation 180 cm thick of a 25-storey building made of a reinforced concrete frame. When constructing a pile foundation, some of piles are not completely sank down to the reference points. In this connection, it is necessary to identify the reasons and load-bearing capacity of piles, given the soil compaction between piles and under their tips and the possibility of using such piles for further building construction.After studying the materials of soil investigation, the analysis of occurrence, composition, physical-mechanical properties of soils, and the pile field, the stress-strain state model is developed for the pile-raft foundation using the MicroFe software application with the development of design model for the foundation-base-building system.In the compacted soil state between the piles and under the pile tips, the conditions of the ultimate and service limit states are met at the actual depth of pile sinking for the raft foundation.

The influence of corrosion of the material of the pipe barrel and impregnation on the bearing ability of piles

The effect of concrete corrosion on the bearing capacity of short driven reinforced concrete piles in saline soils is substantiated. Based on the results of experiments on testing corrosion products, shear resistance f0 in the thickness of the soil layer in which active corrosion of concrete is expected is determined. Given the influence of the corrosion process on the load-bearing capacity of piles in medium, highly aggressive environments, primary and secondary methods of protection are recommended.

A comparison between performances of the behavioral models in evaluating load-bearing capacity of piles in fine-grained unsaturated soil

<p>Virtually all structural piles are installed on the top of groundwater level, and these piles are located on unsaturated soils. In this case, the negative orifice water pressure caused by capillarity significantly influences the mechanical behavior of unsaturated soils. Consequently, structural suction is highly important to load-bearing capacity of loads. In this paper, an evaluation was drawn between the Mohr-Coulomb, modified Cam-Clay, and Barcelona behavioral models using the finite-difference method, and results of studies conducted to estimate load-bearing capacity in the static state were provided. The behavioral model guidelines matched the laboratory models. To estimate soil vividness on the suction level of concern, the water-soil curve (showing suction patterns in relation to moisture) utilized. The general tendencies of settlement gotten by the numerical examination are reliable with pile insert test results. Results suggest that the Barcelona personality model (BBM) yields more realistic estimates of load capacity as it looks at the effect of unsaturated soil suction.</p>

Numerical ANFIS-Based Formulation for Prediction of the Ultimate Axial Load Bearing Capacity of Piles Through CPT Data

This study explores the potential of adaptive neuro-fuzzy inference systems (ANFIS) for prediction of the ultimate axial load bearing capacity of piles (Pu) using cone penetration test (CPT) data. In this regard, a reliable previously published database composed of 108 datasets was selected to develop ANFIS models. The collected database contains information regarding pile geometry, material, installation, full-scale static pile load test and CPT results for each sample. Reviewing the literature, several common and uncommon variables have been considered for direct or indirect estimation of Pu based on static pile load test, cone penetration test data or other in situ or laboratory testing methods. In present study, the pile shaft and tip area, the average cone tip resistance along the embedded length of the pile, the average cone tip resistance over influence zone and the average sleeve friction along the embedded length of the pile which are obtained from CPT data are considered as independent input variables where the output variable is Pu for the ANFIS model development. Besides, a notable criticism about ANFIS as a prediction tool is that it does not provide practical prediction equations. To tackle this issue, the obtained optimal ANFIS model is represented as a tractable equation which can be used via spread sheet software or hand calculations to provide precise predictions of Pu with the calculated correlation coefficient of 0.96 between predicted and experimental values for all of the data in this study. Considering several criteria, it is represented that the proposed model is able to estimate the output with a high degree of accuracy as compared to those results obtained by some direct CPT-based methods in the literature. Furthermore, in order to assess the capability of the proposed model from geotechnical engineering viewpoints, sensitivity and parametric analyses are done.

Lateral load bearing capacity modelling of piles in cohesive soils in undrained conditions: An intelligent evolutionary approach

The complex behaviour of fine-grained materials in relation with structural elements has received noticeable attention from geotechnical engineers and designers in recent decades. In this research work an evolutionary approach is presented to create a structured polynomial model for predicting the undrained lateral load bearing capacity of piles. The proposed evolutionary polynomial regression (EPR) technique is an evolutionary data mining methodology that generates a transparent and structured representation of the behaviour of a system directly from raw data. It can operate on large quantities of data in order to capture nonlinear and complex relationships between contributing variables. The developed model allows the user to gain a clear insight into the behaviour of the system. Field measurement data from literature was used to develop the proposed EPR model. Comparison of the proposed model predictions with the results from two empirical models currently being implemented in design works, a neural network-based model from literature and also the field data shows that the EPR model is capable of capturing, predicting and generalizing predictions to unseen data cases, for lateral load bearing capacity of piles with very high accuracy. A sensitivity analysis was conducted to evaluate the effect of individual contributing parameters and their contribution to the predictions made by the proposed model. The merits and advantages of the proposed methodology are also discussed.

A study of Load bearing capacity of piles driven in the Zanzibar harbour submarine Soils

A study of Load bearing capacity of piles driven in the Zanzibar harbour submarine Soils

Load-Bearing Capacity of Piles

Synopsis The Paper presents an approach to the prediction of the bearing capacity of piles in advance of piling operations by the use of static cone penetration tests. The study was carried out on cast-in-situ driven concrete piles. The distribution of skin friction and point resistance at various loads was determined during the tests by measuring strains with wire resistance strain gauges. The values of total skin friction and point bearing were also determined independently at different loads by adopting a cyclic load test technique. Pull-out tests were made to determine the frictional resistance under pulling, and the values obtained were found to be less than those obtained under pushing during the load test. The coefficients of earth pressure were also determined from the friction values obtained during the load tests and were found to decrease from a value equivalent to the passive earth pressure state at the top to a lower value at the bottom. A compilation of data already available on the frictional resistance of piles was also made. It revealed that in soils of average stiffness (cone penetration values of 10–100 kg/sq. cm) the value of unit skin friction of a pile was roughly 2% of the average cone penetration resistance along the pile length. L'article décrit un moyen permettant de prévoir la capacité portante des pieux avant d'entreprendre les travaux de pose de pieux en se servant des essais de pénétration de cône statique. L'étude a été faite sur des pieux battus en béton coulés sur place. La distribution du frottement superficiel et du point de résistance aux différentes charges a éte: déterminée au cours des essais en mesurant la déformation avec des jauges á fil de contrainte. Les valeurs de frottement superficiel et de points de chargé ont été déterminées indépendamment aussi pour des charges différentes en employant la technique d'essais á chargement cyclique. Des essais d'arrachement de pieux ont ét1e faits pour determiner le frottement superficiel lors de l'arrachement et on a trouvé que les valeurs obtenues étaient moindres que celles obtenues lors de la pression pendant l'epreuve de charge. Les coefficients de pression terrestre ont été déterminées aussi d'apres les valeurs de friction obtenues lors des épreuves de charge et on a trouvé qu'ils décroissaient d'une valeur égale á la pression terrestre passive en haut, á une valeur inférieure en bas. On a aussi recueilli les renseignements déjá disponibles sur la r1esistance á la friction des pieux. On s'est apercu que dans les sols de rigidité moyenne (valeurs de pénétration de cône de 10 á 100 kg/sq. cm) la valeur de frottement superficiel unitaire d'un pieu était d'environ 20% de la résistance moyenne de pénétration de cône sur la longueur du pieu.