Prediction Of Foundation Settlement Research Articles

FAGSO-BP neural network model for settlement prediction of soft soil foundation

To address the problem of difficulty in theoretical formulas and numerical analysis methods to consider the prediction of foundation settlement in the case of multiparameter coupling, the fireworks algorithm (FWA) with a gravity search operator (FAGSO) is introduced into the back propagation (BP) neural network model, and the weight and threshold processes in the neural network are improved by the FAGSO algorithm. A soft soil foundation settlement prediction model based on a FWA optimized BP neural network (FAGSO-BP) with a gravity search operator is proposed. Based on the second phase of the soft foundation treatment project of the Shatian Port Area, Humen City, and Dongguan City, the parameters of pile load height, pore water pressure, and groundwater level were collected and tested. The results indicate that the average relative error of the predicted cumulative settlement value of the soft soil foundation was 0.06%, root mean square error was 7.68, mean absolute error was 4.30, mean absolute percentage error was 1.40%, and mean square error was 59.98. Compared with the BP neural network, GA-BP neural network, and FWA-BP neural network, the error was smaller and the model stability was higher.

Improving Accuracy in Shallow Foundation Settlement Prediction Using Rock Engineering System Method

Improving Accuracy in Shallow Foundation Settlement Prediction Using Rock Engineering System Method

The influence of soil specimens shape and dimensions on consolidation parameters used in foundation settlement prediction

The theory of elasticity is used in geotechnical engineering for the calculation of foundation settlement. The equation used in the evaluation of consolidation settlement uses the soil compressibility parameters which usually are determined on cylindrical soil specimens with ϕ 71.4 mm. Laboratory tests performed on soil specimens showed that the parameters that are used in foundation settlement analysis are influenced by the dimensions of the tested soil specimens and the shape of that specimen. The paper presents the influence of specimen size, shape and method used for the coefficient of consolidation evaluation on the final value of the foundation settlement. The analysis was performed using the Settle3 software from Rocsience, considering the case of an elastic foundation flexible square foundation (1.5 m × 1.5 m) which transmits to the ground a pressure of 100 kPa.

Foundation Settlement Prediction of High-Plateau Airport Based on Modified LSTM Model and BP Neural Network Model

Foundation Settlement Prediction of High-Plateau Airport Based on Modified LSTM Model and BP Neural Network Model

Composite Foundation Settlement Prediction Based on LSTM–Transformer Model for CFG

Roadbed construction typically employs layered and staged filling, characterized by a periodic feature of ‘layered filling—filling interval’. The load and settlement histories established during staged construction offer crucial insights into long-term deformation under filling loads. However, models often rely solely on post-construction settlement data, neglecting the rich filling data. To accurately predict composite foundation ground (CFG) settlement, an LSTM–Transformer deep learning model is used. Five factors from the ‘fill height–time–foundation settlement’ curve are extracted as input variables. The first-layer LSTM model’s gate units capture long-term dependencies, while the second-layer Transformer model’s self-attention mechanism focuses on key features, efficiently and accurately predicting ground settlement. The model is trained and analyzed based on the newly constructed Changsha–Zhuzhou–Xiangtan intercity railway section CSLLXZQ-1, which has a CFG pile composite foundation. The research shows that the proposed LSTM–Transformer model for the settlement prediction of composite foundations has an average absolute error, mean absolute percentage error, and root mean square error of 0.224, 0.563%, and 0.274, respectively. Compared to SVM, LSTM, and Transformer neural network models, it demonstrates higher prediction accuracy, indicating better reliability and practicality. This can provide a new approach and method for the settlement prediction of newly constructed CFG composite foundations.

Weighted-Combined Model for Reclaimed Foundation Settlement Prediction in Coastal Sludge-Bearing Composite Stratum

Foundation settlement prediction is significant to the reuse and management of the reclaimed land from the sea by dykes where composite stratum of many strata with different physical and mechanical properties is encountered. Toward the foundation settlement analysis of reclaimed land in the Yellow Sea composite stratum in eastern China, a weighted-combination model is proposed in this paper combining the hyperbolic model, exponential curve model, and Asaoka model. First, the weight coefficient of the weighted-combination model is calculated by the reciprocal square method of average absolute error (MAE). Second, the settlement prediction results of different models are evaluated by the absolute error, MAE, root-mean-square error, and mean absolute percentage error. Finally, the settlement mechanism of reclaimed foundations in a composite stratum is analyzed from the point of view of the multistratum coupling, and the adaptability of different models to the settlement prediction of reclaimed foundations in a composite stratum is discussed. The results show that the predicted settlement duration curves of the weighted-combined model are in good agreement with the measured settlement duration curves, and the prediction performance is better than that of the hyperbolic model, exponential curve model, and Asaoka model. The MAE of the weighted-combination model is 75.7% lower than that of the exponential curve model, 90.2% lower than that of the hyperbolic model, and 70% lower than that of the Asaoka model. This model provides a new way to predict the settlement of reclaimed foundations in a similar composite stratum.

Machine-Learning-Based Road Soft Soil Foundation Treatment and Settlement Prediction Method

In order to effectively predict the settlement of soft soil foundation, improve the accuracy of road soft soil foundation settlement prediction, and improve the safety of the project, this paper proposes an optimized SVM-AR model and discusses the application scope of the SVM model and the time series AR model, respectively. The SVM-AR model is proposed by combining the respective advantages of the two types of models. Firstly, the prediction method of foundation settlement is analyzed and studied, and then the improved ABC algorithm is used to optimize the SVM model. Secondly, the optimized SVM model is combined with the AR model, the ABC-SVM model is used to predict the trend settlement, and the AR model is used to predict the random settlement and then combined to obtain the predicted settlement. The example verification shows that SVM-AR is more accurate than the SVM model prediction results and better reflects the settlement process of highway soft soil foundation.

Experimental Study on Consolidation Characteristics of Compacted Loess

The prediction of foundation settlement is an important topic in loess filling engineering. Based on a filled foundation in Yan’an, China, this study explores the consolidation characteristics of compacted loess with different compaction energy and consolidation pressure through consolidation tests, analyzes the strain-time curve and refines the curve within 2 h, separates the primary and secondary consolidations, and obtains the critical time point between the primary and secondary consolidations. Deformation rate S t ′ and cumulative deformation St were introduced to analyze the S t ′ − St curve at the secondary consolidation stage; the secondary consolidation coefficient was employed to describe the secondary consolidation characteristics of compacted loess. According to the secondary consolidation characteristics, a prediction model of loess settlement considering different compaction energy and fill thickness was proposed, and the applicability of the model was further analyzed. The model will facilitate in guiding the design and construction of loess filling engineering.

Prediction and Stability Assessment of Soft Foundation Settlement of the Fishbone-Shaped Dike Near the Estuary of the Yangtze River Using Machine Learning Methods

Fishbone-shaped dikes are always built on the soft soil submerged in the water, and the soft foundation settlement plays a key role in the stability of these dikes. In this paper, a novel and simple approach was proposed to predict the soft foundation settlement of fishbone dikes by using the extreme learning machine. The extreme learning machine is a single-hidden-layer feedforward network with high regression and classification prediction accuracy. The data-driven settlement prediction models were built based on a small training sample size with a fast learning speed. The simulation results showed that the proposed methods had good prediction performances by facilitating comparisons of the measured data and the predicted data. Furthermore, the final settlement of the dike was predicted by using the models, and the stability of the soft foundation of the fishbone-shaped dikes was assessed based on the simulation results of the proposed model. The findings in this paper suggested that the extreme learning machine method could be an effective tool for the soft foundation settlement prediction and assessment of the fishbone-shaped dikes.

Improved method for settlement prediction of shallow foundations on sand

Shallow foundations on sands are typically designed with reference to settlements that are difficult to predict with a high level of accuracy. The main uncertainties originate from the soil's non-linear behaviour and the fact that methods currently adopted in practice rely on linear elastic approaches and empirical correlations between soil stiffness and in situ test results. To improve the prediction of foundation settlement it is necessary to account for the dependence of stiffness on soil density, stress state and strain levels – even in relatively simple methods. The main objective of this paper is to provide a contribution in this field. An already formulated elastic approach is revised and modified in order to improve the assessment of soil stiffness, taking into account non-linearity due to strain levels and mechanical non-homogeneity, through definition of an ‘active zone’ that is more consistent with the geometry and size of the foundation. A comparison of calculated and measured settlements demonstrates the feasibility of the proposed non-linear method for both small and large deformation levels.

Foundation settlement prediction of immersed tunnel based on monitoring data

Based on the actual project, through the simulation of the construction steps and the inversion analysis of the monitoring data, the settlement of immersed tube tunnel is predicted. Through analysis, it is found that the whole foundation soil layer of immersed tube tunnel appears rebound, the maximum rebound is 0.045m, and the maximum rebound appears on the surface of the foundation trough. As the depth of the soil deepens, the rebound decreases gradually. After the construction is completed, the vertical strain curves of the immersed tube model are all distributed in a saddle shape. After the immersed tube strain is stable, the strain variables of the immersed tube increase with time basically unchanged. 1000 days after the completion of backfilling, the maximum post-construction settlement is 0.0035m.

THE FORECAST OF LONG-TERM SETTLEMENT OF THE PILE ON SANDSTONES AND CLAYSTONES OF THE PERMIAN AGE

In the article the problem of ensuring the long-term settlement of single piles on claystones and sandstones are reviewed. Incorrect assessment of stabilized settlement of pile foundation can lead to an emergency situation. At the present time for prediction of foundation settlement is widely used finite element method, implemented in a variety of software systems. The aim of the study was to select the optimal model in the software package Plaxis 3D to forecast settlement of driven and bored piles on claystones and sandstones. The authors solved the following tasks: 1) review of the knowledge of long-term settlement of single piles and pile foundations on claystonese and sandstones is performed; 2) the technique is described and numerical experiments are performed in the software package Plaxis 3D for modeling the settlement of a single driven pile and bored pile on claystones and sandstones with varying degrees of weathering; 3) comparison of the results of numerical experiments with long-term field tests of piles on claystones and sandstones is performed; 4) findings from the study are formulated. Numerical experiments of modeling in the software package Plaxis 3D work of driven piles on claystones and sandstones showed that the introduction of soil compaction zones around the driven pile into the calculation scheme makes it possible to obtain close values to long-term settlement of full-scale piles. The authors recommend using the Hardening soil model to predict the work of a driven pile on claystones and sandstones and the Linear-Elastic model to simulate the work of a bored pile on claystones and sandstones. For highly weathered claystones and sandstones soil models need to be corrected for numerical calculations in Plaxis 3D, since the use of the Hardening soil and Linear-Elastic models showed underestimated settlement values in relation to field tests of driven piles.

CPT-Based Nonlinear Stress–Strain Approach for Evaluating Foundation Settlement: Analytical and Numerical Analysis

Due to complexities in soil–foundation interaction and nonlinear behavior of subsoil, considerable uncertainty is involved in the foundation settlement evaluation. In the present paper, a new analytical approach is proposed to estimate the foundation settlement based on soil behavior classification charts developed from CPT records. The approach is founded on the Janbu nonlinear stress–strain method. However, instead of using fixed parameters in the Janbu method, the variable coefficients are used depending on geomaterial properties. Also, in the proposed approach, the scale effect is taken into account for foundation width considering soil stiffness. The proposed procedure is calibrated and verified by a data bank containing 46 case histories including 22 square, 17 circular and 7 rectangular foundations with widths varying between 0.3 and 2.4 m in conjunction with CPT data. Furthermore, the numerical finite difference analysis using a CPT-based stress characteristics method is carried out to validate the proposed approach for the prediction of foundation settlement. The accuracy of the calculations done by the proposed and some available common methods is investigated. Comparisons based on statistical and probabilistic methods apparently reveal that the proposed approach calculates the foundation settlement promisingly.

DMT for Load-Settlement Curve Prediction in a Tropical Sandy Soil Compared to Plate Load Tests

The flat dilatometer test (DMT) has been used as an accurate in situ site investigation tool for foundation settlement prediction. However, few investigations have assessed its performance in settlement prediction in unusual soils. In addition, very little work has been performed to obtain a complete load-settlement prediction curve. This article assesses an approach that uses the DMT to obtain a complete load-settlement prediction curve at a tropical sandy soil site under both natural and inundated conditions. DMTs, plate load tests, and oedometer tests were carried out in these two moisture conditions at the experimental research site located in Bauru, Sao Paulo State, Brazil. The obtained data showed good agreement between the load-settlement curve predicted by the DMT and those determined by the plate load tests at four different depths and two soil conditions. The presented interpretation method based on DMT data worked well to predict the complete load-settlement curve at an unusual soil site at different depths and soil moisture content conditions.

Particle Swarm Fractional Order Burgers Model of Accumulated Pore Pressure Subject to Constant Cyclic Loading of Principal Stress Axis

The uneven settlement of soft soil foundation caused by the traffic load has become an urgent problem. The reasonable and accurate prediction of long-term settlement of soft soil foundation subject to traffic loading is of great significance. On the basis of experiment of soft clay under cyclic loading, we take the initial law of accumulative pore water pressure to establish the Burgers model and the fractional order Burgers model. Also, the particle swarm optimization was used to optimize the parameters of Burgers model. Through the comparison of the results, we have found that the fractional order Burgers is more suitable for simulating the accumulative pore pressure of saturated soft soil subject to cyclic loading with principal stress axis deflection, and it can be applied to the prediction of foundation settlement.

Analysis and Prediction of Foundation Settlement of High-Rise Buildings under Complex Geological Conditions

Based on an example of a project in Tangshan, the high-rise buildings are built in karst area and mined out affected area which is treated by high pressure grouting, and foundation is adopted the form of pile raft foundation. By long-term measured settlement of high-rise buildings, It is found that foundation settlement is linear increase with the increase of load before the building is roof-sealed, and the settlement increases slowly after the building is roof-sealed, and the curve tends to converge, and the foundation consolidation is completed. The settlement of the foundation is about 80% - 84% of the total settlement before the building is roof-sealed.Three layer BP neural network model is used to predict the settlement in the karst area and mined affected area.Compared with the measured data, the relative difference of the prediction is 0.91% - 2.08% in the karst area, and is 0.95% - 2.11% in mined affected area. The prediction results of high precision can meet the engineering requirements.

Using small-strain stiffness to predict the load-settlement behaviour of shallow foundations on sand

Foundation settlement prediction is a challenging task due to the difficulties associated with the quantification of the soil stiffness and the abundance of available analysis methods. Of the different soil stiffness moduli that may be measured, the initial small-strain stiffness is important since it can be measured both in the field and the laboratory, and settlement prediction methods using this parameter are becoming more common. The objective of this paper is to present a settlement prediction method for shallow foundations that only uses small-strain stiffness as input parameter. The method was developed by conducting physical modelling in the geotechnical centrifuge at the University of Pretoria to quantify the behaviour of shallow foundations on sand. Bender and extender elements were used to obtain the small-strain stiffness profile below the foundation before it was vertically loaded and the load-settlement curve determined. The tests were conducted on different density sands corresponding to loose, medium-dense and dense sand. A non-linear stepwise analysis approach was used in conjunction with a softening function, with variables calibrated to obtain the best fit solution for the different sand densities. Results indicate that the accuracy of the proposed method decreases as the sand density increases, but that load-settlement behaviour can be predicted with reasonable accuracy.

Settlement Prediction of Foundations on Argillite-Like Soils (as Exemplified by the Perm' Region)

Settlement Prediction of Foundations on Argillite-Like Soils (as Exemplified by the Perm' Region)

Predicts Based on Multi Modality Support Vector of the Settlement of Composite Foundation

Composite foundation settlement is affected by many factors, and settlement data is a non-linear changing process with complexity, suddenness and progressive nature and so on. So we must analyze and predict the stability of the foundation settlement. Because empirical mode decomposition (EMD) provides a new way for foundation settlement prediction, we can extract modal signals associated with the foundation settlement mechanisms by decomposing the monitoring data of settlement by EMD and use the support vector machine ( Support Vector Machine, SVM) modal to predict the obtained signal, Calculation results of the modal synthesis and accumulation of foundation settlement, get the evolution of Change with the time of foundation settlement. Combined with the engineering example for the application ,shows that the prediction model has good effect in multi modality support vector, a high degree of agreement with the monitoring values, indicating that this method has a promotional value.

Foundation Settlement Prediction Based on a Novel NGM Model

Prediction of foundation or subgrade settlement is very important during engineering construction. According to the fact that there are lots of settlement-time sequences with a nonhomogeneous index trend, a novel grey forecasting model called NGM(1,1,k,c)model is proposed in this paper. With an optimized whitenization differential equation, the proposed NGM(1,1,k,c)model has the property of white exponential law coincidence and can predict a pure nonhomogeneous index sequence precisely. We used two case studies to verify the predictive effect of NGM(1,1,k,c)model for settlement prediction. The results show that this model can achieve excellent prediction accuracy; thus, the model is quite suitable for simulation and prediction of approximate nonhomogeneous index sequence and has excellent application value in settlement prediction.