Prediction of combined static and cyclic load-induced settlement of shallow strip footing on granular soil using artificial neural network (original) (raw)
Related papers
2019
The present study tries to predict the settlement of shallow foundation on granular soil using a mathematical model. The application of feed-forward neural networks with back propagated algorithm is followed for the same. For the development of ANN model, 193 in situ tests data were collected from the literature. The inputs required for the development of model were the foundation pressure, width of footing and the standard penetration number. The predicted settlement using this model was found to compare favourably with the measured settlement. Further the results of sensitivity analysis indicated that the width of foundation has highest impact on the predicted settlement in comparison to other input variables. The present study confirms the ability of ANN models to predict a complex relationship between the nonlinear data as in present case.
2003
The research presented in this thesis focuses on the settlement prediction of shallow foundations on cohesionless soils using artificial neural techniques. The problem of estimating the settlement of shallow foundations on cohesionless soils is very complex and not yet entirely understood. Over the years, many methods have been developed to predict the settlement of shallow foundations on cohesionless soils. However, methods for such predictions that have the required degree ofaccuracy and consistency have not yet been developed. Accurate prediction of settlement is essential since settlement, rather than bearing capacity, generally controls the design process of shallow foundations. In this research, artihcial neural networks (ANNs) are used in an attempt to obtain more accurate settlement prediction. ANNs are numerical modelling techniques that are inspired by the functioning of the human brain and nerve system. ANNs use the data alone to determine the structure of the model as well as the unknown model parameters' ANNs have been applied successfully to many problems in the field of geotechnical engineering and some of their applications are demonstrated in this thesis. A large database comprising a total of 189 case records is used to develop and verift the ANN models. Five parameters are considered to have the most significant impact on the settlement of shallow foundations on cohesionless soils and are thus used as the ANN model inputs. These include the footing width, footing net applied pressure, average SPT blow count over the depth of influence of the foundation, footing geometry and footing embedment ratio. The model output is the average measured sefflement of the foundation, considered in its final state. Two types of ANNs are used for the development of ANN models. The first type is multi-layer perceptrons (MLps) that are trained using the back-propagation algorithm, whereas the second type are B-spline neurofuzzy networks that are trained with the adaptive spline modelling of observation data (ASMOD) algorithm. In relation to the multi-layer perceptrons, the feasibility of ANNs for predicting the settlement of shallow foundations on cohesionless soils is investigated. A number of issues in relation to ANN construction, optimisation and validation are also investigated and guidelines for improving ANN performance are lv Abstract v developed. The issue of data division and its impact on ANN model performance is investigated in some detail by examining four different data division methods, namely, random data division; data division to ensure statistical consistency of the subsets needed for ANN model development; data division using self-organising maps (SOMs) and a new data division method using fuzzy clustering. The success or otherwise of ANNs for settlement prediction of shallow foundations on cohesionless soils is illustrated and compared with three of the most commonly used settlement prediction methods. A hand-calculation design formula for settlement prediction of shallow foundations on cohesionless soils that is based on a more accurate settlement prediction from ANN model is presented. It was found that ANNs have the ability to predict the settlement of shallow foundations on cohesionless soils with a high degree of accuracy and ouþerform traditional methods. It was also found that the new data division method that is based on fuz,zy clustering is suitable approach for data division. In relation to the newofuzzy models, the ability of ANNs to provide a better understanding of the relationship between settlement and the factors affecting settlement is investigated. It was found that neurofuzzy networks have the abilþ to provide a transparent understanding of the relationship between settlement and the factors affecting it. Settlement analysis is often affected by considerable levels of uncertainty that are usually ignored by traditional methods. In this research, ANNs are linked with Monte Carlo simulation to provide a stochastic solution for settlement prediction that takes into account the uncertainties associated with settlement analysis. A set of stochastic design charts that provide the designer with the level of risk associated with predicted settlements are developed and provided.
Prediction of settlement of shallow foundations on reinforced soils using neural networks
Geosynthetics International, 2006
The use of reinforcement to increase the bearing capacity and reduce the settlement of shallow foundations is a common construction technique. Although foundation settlement is a major problem for design, few practical methods have been developed to compute the settlement of shallow foundations on reinforced cohesionless soils. In this study, a feedforward backpropagation neural network (BPNN), which is one type of artificial neural network (ANN), is used to predict the settlement of reinforced foundations. The model performance showed very good agreement with the measured settlements. The results indicate that the developed BPNN model may be a powerful tool to accurately predict settlement of shallow foundations on reinforced cohesionless soils.
ANN-based model for predicting the bearing capacity of strip footing on multi-layered cohesive soil
Computers and Geotechnics, 2009
In reality, footings are most likely to be founded on multi-layered soils. The existing methods for predicting the bearing capacity of 4-layer up to 10-layer cohesive soil are inaccurate. This paper aims to develop a more accurate bearing capacity prediction method based on multiple regression methods and multilayer perceptrons (MLPs), one type of artificial neural networks (ANNs). Predictions of bearing capacity from the developed multiple regression models and MLP in tractable equations form are obtained and compared with the value predicted using traditional methods. The results indicate ANNs are able to predict accurately the bearing capacity of strip footing and outperform the existing methods.
Australian Geomechanics, 2002
The problem of estimating the settlement of shallow foundations on granular soils is very complex and not yet entirely understood. The geotechnical literature has included many formulae that are based on several theoretical or experimental methods to obtain an accurate, or near-accurate, prediction of such settlement. However, these methods fail to achieve consistent success in relation to accurate settlement prediction. Recently, artificial neural networks (ANNs) have been used successfully for settlement prediction of shallow foundations on granular soils and have been found to outperform the most commonly-used traditional methods. This paper presents a new hand-calculation design formula for settlement prediction of shallow foundations on granular soils based on a more accurate settlement prediction from an artificial neural network model. The design formula presented is a quick tool from which settlement can be calculated easily without the need for computers.
2018
The paper presents the prediction of the ultimate bearing capacity of different regular shaped skirted footing resting on sand using the artificial neural network. The input parameters for the artificial neural network model were normalised skirt depth, area of the footing and the friction angle of the sand, while the output was the ultimate bearing capacity. The artificial neural network algorithm uses a back propagation model. The training of artificial neural network model has been conducted and the weights were obtained which described the relationship between the input parameters and output ultimate bearing capacity. Further, the sensitivity analysis has been performed and the parameters affecting the ultimate bearing capacity of different regular shaped skirted footing resting on the sand were identified. The study shows that the prediction accuracy of the ultimate bearing capacity of different regular shaped skirted footing resting on sand using artificial neural network mode...
2017
The presence of cemented soils pose significant challenges in drilled shaft design and may prevent accurate estimates of the service limit state if traditional analytical techniques are employed. Thus, an Artificial Neural Network (ANN) is developed and tested as an alternative method for predicting settlement induced by axial loads. Training is carried out using the results of 31 field load tests performed in Las Vegas, USA, where cemented soils are common, and an automated process is employed to determine the optimal network architecture. Ultimately, a cascaded feed-forward ANN with one hidden layer consisting of six artificial neurons produced the highest quality generalization. Ten additional load tests not included in the original training, testing, or validation datasets are reserved to evaluate performance. It is observed that the ANN produces similarly accurate estimates of load-settlement on average as compared to two more traditional t-z style approaches.
Soils and Foundations, 2018
Application of the theory of elasticity for the calculation of foundation settlements yields equations that are well-established and consolidated in geotechnical standards and/or recommendations. These equations are corrected by an influence factor to increase precision and encompass the existing complex geotechnical casuistry. The study presented herein utilizes neural networks to improve the determination of the influence factor (Iα), which considers the effect of a finite elastic half-space limited by an inclined bedrock under the foundation. The results obtained with the utilization of artificial neural networks demonstrate a notable improvement in the predicted value of the influence factor in comparison with existing analytical equations.
Geomechanics and Geoengineering, 2020
This paper proposes a new hybrid artificial neural network and mathematical (ANN-MATH) model to improve the prediction capability of the load-settlement behaviour of shallow foundations in sandy soils. The hybridisation process is performed by replacing the conventional activation function of the ANN output layer by a new mathematical model. Thereafter, 110 full-scale loading tests of shallow foundations, carried out in sand with the cone penetration test (CPT) results, are used to build and validate the proposed model. In terms of accuracy, the proposed model shows a high correlation between the predicted results and the measured data. In addition, the proposed method was compared to the available methods in the literature. It was found that the proposed model is superior to classical and artificial intelligence-based methods by more than 29% and 35%, respectively, in terms of root mean square error (RMSE). Furthermore, a parametric study was undertaken to assess the robustness of the proposed model and to derive the bearing capacity factor based on the CPT test. The bearing capacity factor was found close to those recommended by the French standard NF P 94-261.
The Open Civil Engineering Journal
Introduction: Although it is a regular duty of geotechnical engineers to evaluate how much shallow foundation settles in the granular soil, there is no well-approved formula for this task. The intent of this research is to develop a formula that is adequately simple to be used in routine geotechnical engineering work but complete enough to address the behavior of granular soil associated with the settlement issue. Methods: Cone penetration test and foundation load test data were used to generate a formula that can predict the settlement. Genetic Programming (GP) based Symbolic Regression (GP-SR) and artificial neural networks were used to develop an optimized formula. Settlements were also calculated using the finite method and compared to the results of the developed formula. Results and Conclusion: Two formulas were developed using SR, and several models were developed using ANN. ANN model 1 has the highest R2 value (0.93) and the lowest MSE (0.16) among all developed ANN and GP-S...