Prediction Of Ultimate Bearing Capacity Research Articles

Ultimate bearing capacity of geosynthetic reinforced soil abutment centrifuge model tests

Five centrifuge models of geosynthetic reinforced soil (GRS) abutments with segmental block facing were loaded in the acceleration field under plane strain condition. Influencing factors including reinforcement tensile strength, setback and bearing area width were considered and analysed. Results show that the abutment with stronger reinforcement remained stable under the maximum loading capacity. However, abutments with weaker reinforcement showed excessive vertical strain, local deformation or even collapse. The ultimate bearing capacity increased with the lengthening of setback but decreased due to a larger bearing area. The rupture of reinforcements was observed and considered as the cause of the failures. Compared with the measured ultimate bearing capacity, the values calculated by the semi-empirical formula of design guidelines were significantly conservative. The failure surface of failed abutment developed from the rear edge of the bearing area to the middle height of the abutment at an angle of nearly 45° + φ/2. The setback and the bearing area width affected the form and position of the failure surface. The difference between the potential failure surface predicted by available methods and the measured failure surfaces has been discussed, and suggestions for the design and ultimate bearing capacity prediction of GRS abutments with segmental block facing are provided.

Prediction of ultimate bearing capacity of rock-socketed piles based on GWO-SVR algorithm

The application of rock-socketed pile in engineering is becoming ever more common. Finding the ultimate bearing capacity of rock-socketed piles with a high-performance ratio and precision is an important area of research. The rock-socketed piles underwent a field load test, and ABAQUS software was utilized to create a model of the interaction between the pile and the soil. For the geometric and physical parameters of the pile, soil, and bedrock, a total of eighteen pile-soil parameters were chosen. Reasonably constructed orthogonal and control variable tests are utilized, and a sensitivity analysis of the relevant factors is performed. Ten elements that significantly affect the ultimate bearing capacity of rock-socketed piles (with a probability less than 0.05) are selected as the input for the bearing capacity prediction of rock-socketed piles based on the test's consistent findings. The ultimate bearing capacity of rock-socketed piles is predicted using the support vector regression (SVR) model, and the absolute coefficient, mean absolute error (MAE), mean square error (MSE) and other indicators are chosen as the evaluation indices of the model prediction effect. The SVR model predicts an absolute coefficient of 0.7, which is an unsatisfactory prediction outcome. Consequently, the model is optimized via the nested grey wolf (GWO) algorithm. With a value of 0.995, the GWO-SVR model is more akin to 1 than the SVR model. There are 0.14 and 0.034 for the MAE and MSE, respectively. The models of (Artificial bee colony) ABC-SVR, (Cuckoo search) CS-SVR, (Sparrow search algorithm)SSA-SVR, and (Particle swarm optimization) PSO-SVR are built. When comparing different assessment indicators, the GWO-SVR model is smaller than the MAE and MSE. When the prediction model is used on a real project, the engineering requirements can be satisfied by the prediction effect.

Finite Element Analysis of Axial Compression Performance of Stainless Steel -Steel Tube Sandwich Concrete Columns

A finite element analysis software, ABAQUS, was used to numerically analyze nine specimens with varying inner steel tube thickness and slenderness ratio to study the axial compression performance of stainless steel - steel tube sandwich concrete columns. The influence of each parameter on the axial compression behavior was explored. The simulation results aligned closely with the experimental results, with the ultimate bearing capacity prediction error within 5%. Bulging deformation consistently occurred on the upper outer steel tube. Increasing the inner steel tube thickness improved the ultimate bearing capacity up to 20%, with the 4-6 mm wall thickness range providing the most effective capacity increase. The ultimate bearing capacity deteriorated up to 5% as the slenderness ratio increased, but the axial compression stiffness markedly decreased due to overall instability. A relationship between the stability coefficient and slenderness ratio was proposed, and the calculation results showed excellent agreement.

Prediction of ultimate bearing capacity of concrete filled steel tube stub columns via machine learning

Prediction of ultimate bearing capacity of concrete filled steel tube stub columns via machine learning

Prediction of ultimate bearing capacity of shallow foundations on cohesionless soil using hybrid LSTM and RVM approaches: An extended investigation of multicollinearity

This research presents the optimum performance model for predicting the shallow foundation ultimate bearing capacity (UBC). Twenty-one models are employed, trained, tested, and compared to find the best architecture computational model. Thirteen performance metrics, including three new index metrics, are used to calculate and analyze the model's performance. Five kernels, linear, polynomial, gaussian, laplacian, and exponential, have been implemented in RVM (mentioned by SRVM). These RVM models have been optimized by each particle swarm optimization (PSO) and genetic (GA) algorithm. Moreover, the kernel function of the higher-performance SRVM model has been used as kernel 1 to develop dual (parallel) kernel function-based RVM (mentioned by HRVM) models. Thus, four combinations have developed four HRVM models optimized by each GA and PSO algorithm. The Adam, root mean square propagation, and stochastic gradient descent with momentum algorithms have optimized long short-term memory (LSTM) models. The analysis of performance metrics reveals that (i) the GA-optimized laplacian SRVM model UBC3 has performed better than the PSO-optimized exponential SRVM model UBC10, (ii) PSO-optimized dual kernel-based HRVM model UBC18 has attained higher performance than GA-optimized dual kernel-based HRVM model UBC14, i.e., 0.9985. Adam-optimized model UBC19 based on the LSTM approach has gained higher performance (R = 0.9999) and the least residuals (RMSE = 5.9132 kPa, MAE = 3.7037 kPa, MAPE = 2.5314 kPa, and WMAPE = 0.0118 kPa). Also, model UBC19 has outperformed models UBC3, UBC10, UBC14, and UBC18 and published models available in the literature with higher index metrics. This study reveals that the HRVM models are less affected by multicollinearity.

Enhancing Ultimate Bearing Capacity Prediction of Cohesionless Soils Beneath Shallow Foundations with Grey Box and Hybrid AI Models

This study examines the potential of the soft computing technique, namely, multiple linear regression (MLR), genetic programming (GP), classification and regression trees (CART) and GA-ENN (genetic algorithm-emotional neuron network), to predict the ultimate bearing capacity (UBC) of cohesionless soils beneath shallow foundations. For the first time, two grey-box AI models, GP and CART, and one hybrid AI model, GA-ENN, were used in the literature to predict UBC. The inputs of the model are the width of footing (B), depth of footing (D), footing geometry (ratio of length to width, L/B), unit weight of sand (γd or γ′), and internal friction angle (ϕ). The results of the present model were compared with those obtained via two theoretical approaches and one AI approach reported in the literature. The statistical evaluation of results shows that the presently applied paradigm is better than the theoretical approaches and is competing well for the prediction of qu. This study shows that the developed AI models are a robust model for the qu prediction of shallow foundations on cohesionless soil. Sensitivity analysis was also carried out to determine the effect of each input parameter. The findings showed that the width and depth of the foundation and unit weight of soil (γd or γ′) played the most significant roles, while the internal friction angle and L/B showed less importance in predicting qu.

Development of new rotation pile technology mirai pile ® and preliminary study in Vietnam on construction

In recent years sustainability and environmental impacts have been highlighted as an important issue in design and construction particularly in urban area in construction of buildings and bridges. Mirai piler (M-pile) is new rotating pile technology, which was developed in 2020, is highly appreciated for its environmentally friendly functions such as: rapid construction, low noise; low vibration; no waste soil during construction; no ground water contamination. In this study, construction sequence and prediction of axial bearing capacity of M-pile on cohesive soil were introduced. M-pile analysis used with outer diameter of 318.5mm and thickness of 12.7mm. The analysis results show that the ultimate bearing capacity prediction of M-pilein soft clay soil considerablyincrease compared with bored and cast-in-place piles with the same diameter and depth thanks to multipleblades welded along the pile shaft.

Ultimate bearing capacity prediction method and sensitivity analysis of PBL

The ultimate bearing capacity of Perfobond leiste (PBL) is one of the key parameters to evaluate the bearing capacity and reliability of steel–concrete structures, and it is very important to predict the ultimate bearing capacity of PBL more accurately. Based on the improved cuckoo search algorithm (CS), two prediction model optimized by back propagation neural network (BPNN) algorithm and extreme learning machine (ELM) were proposed. The local search ability of CS algorithm was improved by the triangular mutation operator and the distance-based distributed discovery probability, and the global search ability was improved by multi-step selection strategy. The weight, threshold, number of input parameters and number of nodes in the hidden layer of BPNN and ELM were optimized by the triangular multi-step cuckoo search (TMCS). The comprehensive sensitivity analysis (CSA) method and Morris sensitivity analysis (MSA) method were used to analyze the sensitivity of six key parameters of PBL, such as thickness of perforated steel plate, diameter of perforated holes, number of perforated holes, diameter of through reinforcement, yield strength of through reinforcement and compressive strength of concrete. The experimental data of push-out tests in published literatures were selected as samples, and the results show that the proposed TMCS-ELM algorithm and TMCS-BPNN algorithm can accurately predict the ultimate bearing capacity of PBL, and the average errors are 4.17% and 2.16% respectively. The sensitivity analysis results show that the compressive strength of concrete has the highest influence on the bearing capacity of PBL, followed by the yield strength of through reinforcement.

Prediction of Ultimate Bearing Capacity of Oil and Gas Wellbore Based on Multi-Modal Data Analysis in the Context of Machine Learning

As important research for drilling engineering, the prediction of oil and gas shaft lining conditions is changing from the traditional method based on the mechanism model to the intelligent prediction method combining the mechanism model with the data model. Therefore, this paper establishes a stacking integrated model for predicting the uniaxial compression strength (UCS) of rock based on four basic parameters that can reflect the characteristics of rock mass. At the same time, the expectation-maximation (EM) algorithm is used to optimize the hidden Markov models (HMM), and a fuzzy random model of the ultimate bearing capacity of oil and gas shaft lining is established. The uncertain distribution of main parameters of rock mass is analyzed, and the corresponding fuzzy random distribution law is obtained. The experimental results show that the stacking integration algorithm is of great help to improve the prediction effect of rock mass compressive strength. The EM-HMM model has the advantages of small error, high efficiency, and fast convergence after two fuzzy random processes. Using this algorithm is helpful to analyze the stress state and parameter response mechanism of the shaft lining, dynamically generate optimized parameters, and provide technical support for reducing the incidence of complex drilling accidents, shortening the well construction period and lowering the drilling cost.

Prediction of Ultimate Bearing Capacity of Pile Foundation Based on Two Optimization Algorithm Models

The determination of the bearing capacity of pile foundations is very important for their design. Due to the high uncertainty of various factors between the pile and the soil, many methods for predicting the ultimate bearing capacity of pile foundations focus on correlation with field tests. In recent years, artificial neural networks (ANN) have been successfully applied to various types of complex issues in geotechnical engineering, among which the back-propagation (BP) method is a relatively mature and widely used algorithm. However, it has inevitable shortcomings, resulting in large prediction errors and other issues. Based on this situation, this study was designed to accomplish two tasks: firstly, using the genetic algorithm (GA) and particle swarm optimization (PSO) to optimize the BP network. On this basis, the two optimization algorithms were improved to enhance the performance of the two optimization algorithms. Then, an adaptive genetic algorithm (AGA) and adaptive particle swarm optimization (APSO) were used to optimize a BP neural network to predict the ultimate bearing capacity of the pile foundation. Secondly, to test the performance of the two optimization models, the predicted results were compared and analyzed in relation to the traditional BP model and other network models of the same type in the literature based on the three most common statistical indicators. The models were evaluated using three common evaluation metrics, namely the coefficient of determination (R2), value account for (VAF), and the root mean square error (RMSE), and the evaluation metrics for the test set were obtained as AGA-BP (0.9772, 97.8348, 0.0436) and APSO-BP (0.9854, 98.4732, 0.0332). The results show that compared with the predicted results of the BP model and other models, the test set of the AGA-BP model and APSO-BP model achieved higher accuracy, and the APSO-BP model achieved higher accuracy and reliability, which provides a new method for the prediction of the ultimate bearing capacity of pile foundations.

Numerical Analysis of CFST Column with PBL Stiffeners under Axial Compression

PBL stiffeners, made of thin-walled steel plates with circular openings and welded to the steel tube of a square concrete-filled steel tubular (CFST) column, can improve the combined effect effectively by co-carrying axial compressive forces and confining the concrete core. A numerical simulation study based on the previous test was conducted to study the ultimate strength of the CFST stub column with PBL stiffeners. Finite element models of CFST with different stiffeners were made and verified by the test results of typical failure modes and load–strain curves of specimens. The parameter study was conducted, including PBL stiffener detailing (i.e., material strength, stiffener thickness, opening diameter, and opening spacing). Finally, based on the study and analysis results, an ultimate bearing capacity prediction formula was proposed, which can reasonably predict the bearing capacity of a square CFST column with longitudinal or diagonal stiffeners, while the methods in ACI, BS5400, EC4, AIJ, and DBJ were more conservative.

Deterioration of Mechanical Properties of Axial Compression Concrete Columns with Corroded Stirrups Coupling on Load and Chloride

To research the deterioration of the mechanical properties of stirrup-corroded concrete columns under the effect of load and chloride, accelerated corrosion and load carrying capacity tests were carried out on concrete columns subjected to long-term axial loading by means of dry and wet cycles with extra electric currents. The test results showed that under the effect of axial load and chloride, the corrosion-induced cracks of stirrup-corroded concrete columns mainly developed along the direction of the longitudinal reinforcing steel bars (cracks along longitudinal reinforcing steel bars caused by corrosion) and there were almost no corrosion-induced cracks along the direction of the corroded stirrups. The length and maximum width of the corrosion-induced cracks increased with the stirrup corrosion rate, but the average width of the corrosion-induced cracks did not change significantly. After the stirrup-corroded column reached the ultimate load, the concrete cover spalled off in pieces along the corrosion-induced cracks and loading cracks, the core concrete was crushed, and the test column produced obvious brittle failure. With the increase in the corrosion rate of stirrups, the stiffness and ultimate bearing capacity of the column decreased. Considering factors such as damage to the column section caused by stirrup corrosion, the decrease in the lateral restraint effect of the corroded stirrup on the longitudinal reinforcing steel bars, and buckling of the longitudinal reinforcing steel bars, the ultimate bearing capacity prediction model of the short column subjected to axial compression due to stirrup corrosion was established. The calculated values of the model were in good agreement with the measured values, indicating the model has good applicability.

Influence of Load Test Scale on Prediction of Ultimate Bearing Capacity of Aggregate Pier Reinforced Clay

Predicting the bearing capacity of spread footings on aggregate pier-reinforced soil is particularly important for ground improvement. Various methods for predicting the bearing capacity of spread footings supported on aggregate pier-reinforced clay have been proposed. In addition, many fields or laboratory load tests have been conducted to identify the improvement effects of aggregate pier. However, no study has quantitatively compared the effect of the experimental scale on the prediction of bearing capacity. In this study, multiple linear regression analyses were performed for field and laboratory load tests, and the effects of the load test scale on bearing capacity prediction were identified. The sensitivity analysis showed that the prediction model for the laboratory load test (MLRL) exhibited a higher sensitivity for the undrained shear strength than that of the field load test model (MLRF). However, the sensitivity of the area replacement ratio of MLRL was less than half that of the MLRF. As the undrained shear strength increased, the predicted bearing capacity of the MLRL was larger than that of the MLRF owing to the influence of boundary conditions on the experimental equipment.

Axial behavior of circular seawater sea-sand coral concrete columns reinforced with BFRP bars and spirals

• Axial behavior of BFRP bars reinforced seawater sea-sand coral concrete columns was studied experimentally. • The load bearing capacity of B-SSCC columns declined as the spiral spacing narrowed paradoxically owing to the significant discontinuity of coral concrete internally. • Columns with dense stirrups showed more pronounced ductility in the post-peak stage compared with B-SSCC square columns. • An ultimate bearing capacity prediction model is established. For the sake of solving the problem of steel reinforcement corrosion in concrete structures and reducing the transportation cost of concrete raw materials at sea in the development of South China Sea Islands, a new type of coral reef sand concrete columns reinforced with basalt fiber reinforced polymer (BFRP) bars and spirals was proposed. In this study a total of 18 circular seawater sea-sand coral reef concrete columns reinforced with BFRP bars and spirals (B-SSCC) were tested under concentric axial loads. Parameters of nominal longitudinal bar diameters and spiral spacing were investigated to obtain variations on crack propagation, failure modes, load bearing capacity, strain and ductility properties. The results indicated that no obvious cracks were observed until the curves reached up to 0.95 P max approximately and the columns experienced more brittle and explosive failure modes with the increase of longitudinal bar diameter and spiral spacing. The load bearing capacity of B-SSCC columns increased with longitudinal reinforcement ratio, however, declined as the spiral spacing narrowed paradoxically. It was owing to the significant discontinuity of coral concrete internally. Compared with B-SSCC square columns, the circular columns with dense stirrups showed pronounced ductile behavior in the post-peak stage, remarked by improved average ductile coefficient β of 22.6%. Finally, a numerical prediction of load bearing capacity was suggested.

Estimation of ultimate bearing capacity of bored piles using machine learning models

The ultimate bearing capacity of bored piles is an essential parameter in foundation design of structure. In the present study, three Machine Learning (ML) methods namely Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machine (SVM) and Artificial Neural Network (ANN) were utilized to estimate bearing capacity of bored piles based on limited engineering parameters of pile and soil obtained from 75 test sites in Vietnam. These parameters include pile diameter, pile length, tensile strength of main longitudinal steel bar, compressive strength of concrete, average SPT index at the tip of the pile, average SPT index at the pile body. Validation of the methods was verified using standard statistical metrics namely Root Mean Square Error (RMSE) and Correlation coefficient (R). The results show that all the proposed models have good potential in predicting correctly bearing capacity of bored piles on training data (R>0.93) and on testing data (R>0.88) but performance of the SVM model is the best (R:0.985 (training) and R:0.958 (testing). Thus SVM model can be used for the accurate prediction of ultimate bearing capacity of bored piles for proper designing of the civil engineering structure foundation.

Bearing capacity of single stone column in clay using finite element limit analysis

Stone columns are used as an efficient ground improvement technique, which could increase the bearing capacity of native soft soil, reduce settlement, increase rate of consolidation and mitigate liquefaction potential. In this study, the finite element limit analysis (FELA) with the adaptive mesh, including both upper bound and lower bound approaches, was applied for prediction of ultimate bearing capacity of single stone column. It was observed that a critical slenderness ratio exists in which the failure mechanism changes from punching to bulging. An equation was derived for prediction of the critical slenderness ratio as a function of cohesion of the native clayey soil and friction angle of the stone column. A two-criteria equation is also presented to predict the ultimate bearing capacity of single stone column under both punching and bulging mechanisms. Moreover, the effect of footing roughness on the ultimate bearing capacity of the stone column was investigated. It was observed that the influence of footing roughness is more significant for bulging-type failure. The results of this study are also compared with some of the previously published analyses in the literature.

Experimental investigation of full-culm bamboo tubes strengthened by filled concrete and bamboo sheets under axial compression

To solve the problem of low compressive bearing capacity for the full-culm bamboos caused by their radial gradient variation and limited wall thickness, a new method, in which the concrete was filled inside the cavities of bamboo tubes and the bamboo sheets were wound onto the bamboo tubes with epoxy resin adhesive, was proposed in this paper to improve the behavior of full-culm bamboo structural members. The failure modes, ultimate bearing capacity of full-culm bamboo tubes with or without nodes, concrete-filled full-culm bamboo columns (CBs) and bamboo sheet-strengthened concrete-filled full-culm bamboo tubes (BSCBs) were investigated. Finally, the ultimate bearing capacity prediction method for CBs and BSCBs was studied based on the existing typical FRP-confined concrete columns. The results showed that the existence of bamboo nodes in the full-culm bamboo tubes may result in a decrease in the bearing capacity. In particular, the ultimate stress of specimens with relatively larger diameters and without nodes can be increased by a maximum of 18.2% compared to tubes with bamboo nodes. The ultimate bearing capacity of the full-culm bamboo tubes can obviously be increased using the scheme of filling concrete internally and strengthening by bamboo sheets externally. The average ultimate bearing capacity of CBs can be increased by a maximum of 65.3% compared with the corresponding full-culm bamboo tubes, and the average ultimate bearing capacity of BSCBs is at most 2.51 times higher than that of corresponding CBs. Although the bamboo tube and concrete cannot simultaneously reach the ultimate bearing capacity due to a certain difference in terms of their mechanical properties, such as the peak strain and elastic modulus, the ultimate bearing capacity of CBs and BSCBs can be predicted accurately using some existing typical strengthening models in terms of FRP-confined concrete columns.

Prediction of Ultimate Bearing Capacity of Shallow Foundations on Cohesionless Soils: A Gaussian Process Regression Approach

This study examines the potential of the soft computing technique—namely, Gaussian process regression (GPR), to predict the ultimate bearing capacity (UBC) of cohesionless soils beneath shallow foundations. The inputs of the model are width of footing (B), depth of footing (D), footing geometry (L/B), unit weight of sand (γ), and internal friction angle (ϕ). The results of the present model were compared with those obtained by two theoretical approaches reported in the literature. The statistical evaluation of results shows that the presently applied paradigm is better than the theoretical approaches and is competing well for the prediction of UBC (qu). This study shows that the developed GPR is a robust model for the qu prediction of shallow foundations on cohesionless soil. Sensitivity analysis was also carried out to determine the effect of each input parameter.

Prediction of Ultimate Bearing Capacity and Structural Optimization of Aluminum Alloy Plate Joints Based on Artificial Neural Network

Prediction of Ultimate Bearing Capacity and Structural Optimization of Aluminum Alloy Plate Joints Based on Artificial Neural Network

Prediction of Ultimate Bearing Capacity of Aggregate Pier Reinforced Clay Using Machine Learning

Prediction of Ultimate Bearing Capacity of Aggregate Pier Reinforced Clay Using Machine Learning