Results of Application of Artificial Neural Networks in Predicting Geo-Mechanical Properties of Stabilised Clays—A Review (original) (raw)
Related papers
Nigerian Journal of Engineering, 2020
The multilayer perceptrons (MLPs) artificial neural networks (ANNs) that are trained with feed forward back-propagation algorithm was used in this study for the simulation of unconfined compressive strength (UCS) of cement kiln dust-treated expansive clay. Artificial neural networks (ANNs) are yet to be efficiently extended to soil stabilization aspect of geotechnical engineering. As such, this study aimed at applying the ANNs as a soft computing approach to predict the UCS values of Nigerian expansive clay. For each of the three ANN model development, eight inputs and one output data set were used. The mean squared error (MSE) and R-value were used as yardstick and criteria for acceptability of performance. In the neural network development, NN 8-11-1 that gave the lowest MSE value and the highest R-value were used for all the three outputs in the hidden layer of the networks architecture which performed satisfactorily. For the normalized data set used in training, testing and validating the neural network, the performance of the simulated network was satisfactory having R values of 0.9812, 0.9783 and 0.9942 for the 7, 14 and 28 days cured UCS respectively. These values met the minimum criteria of 0.8 conventionally recommended for strong correlation condition. All the obtained simulation results are satisfactory and a strong correlation was observed between the experimental UCS values as obtained by laboratory test procedures and the predicted values using ANN.
ARTIFICIAL NEURAL NETWORK APPLICATIONS IN GEOTECHNICAL ENGINEERING
2001
Over the last few years or so, the use of artificial neural networks ( ANNs) has increased in many areas of engineering. In particular, ANNs have been applied to many geotechnical engineering problems and have demonstrated some degree of success. A review of the literature reveals that ANNs have been used successfully in pile capacity prediction, modelling soil behaviour, site characterisation, earth retaining structures, settlement of structures, slope stability, design of tunnels and underground openings, liquefaction, soil permeability and hydraulic conductivity, soil compaction, soil swelling and classification of soils. The objective of this paper is to provide a general view of some ANN applications for solving some types of geotechnical engineering problems. It is not intended to describe the ANNs modelling issues in geotechnical engineering. The paper also does not intend to cover every single application or scientific paper that found in the literature. For brevity, some wo...
Journal of Materials in Civil Engineering, 2013
The general swelling model has recently been updated in Israel by applying the Excel-solver command (ESC) analysis to new local test results from 897 undisturbed specimens. In this analysis, the goodness-of-fit statistics obtained classify the category of their associated regression only as fair. Thus, it seems necessary to explore the possibility of enhancing the outputs of this regression analysis by applying the artificial neural networks (ANN) methodology to the same 897 undisturbed specimens. However, it is shown that the use of the ANN outputs should be accompanied by an additional check to ensure that they follow the expected physical swelling behavior, as characterized by the index properties of the soil. The ANN methodology applied in this paper is similar to previous studies in geotechnical engineering. Different models were tested using the same database (i.e., the same 897 undisturbed specimens). The statistical fit of the ANN models were clearly found to be superior to the ESC models. However, in the sense of the required physical behavior, as characterized by the index properties of the soil, the ANN models did not predict swelling values as well as ESC models did, in particular values ranging near (or outside) the data set boundaries. Thus, the former ESC models still remain preferable.
The application of artificial neural network in geotechnical engineering
IOP Conference Series: Earth and Environmental Science, 2018
The artificial neural network (ANN) is a machine learning technique, which can simulate the physiological structure and mechanism of human brain. The study aims to review the principles of ANN algorithm and their application in geotechnical engineering. Firstly, the basic principles of ANN algorithm are introduced. Secondly, the application of ANN algorithm is presented. The review suggests that ANN can classify soil accurately, and it is able to group rock mass, predict the stability of slopes exactly, which could be used for risk assessment. The predicted settlement that is generated by ANN is near real value.
ANN prediction of some geotechnical properties of soil from their index parameters
This paper presents artificial neural network prediction models which relate compaction characteristics, permeability, and soil shear strength to soil index properties. In this study, a database including a total number of 580 data sets was compiled. The database contains the results of grain size distribution, Atterberg limits, compaction, permeability measured at different levels of compaction degree (90-100 %) and consolidated-drained triaxial compression tests. Comparison between the results of the developed models and experimental data indicates that predictions are within a confidence interval of 95 %. To evaluate the effect of each factor on these geotechnical parameters, sensitivity analysis was performed and discussed. According to the performed sensitivity analysis, Atterbeg limits and the soil fine content (silt+clay) are the most important variables in predicting the maximum dry density and optimum moisture content. Another aspect that is coherent from the sensitivity analysis is the considerable importance of the compaction degree in the prediction of the permeability coefficient. However, it can be seen that effective friction angle of shearing is highly dependent on the bulk density of soil.
Plasticity prediction of expansive soil treated with sand by artificial neural network
Clay soils consist of fine particles and are generally characterized by low strength. The interactions between clays and water result in high-plasticity clay mixtures that can easily deform or crack. It should be noted that the addition of sand to expansive soils can help to improve their particle size and reduce their plasticity, and consequently augment their strength. The present study aims mainly to develop a model for the prediction of the plasticity index (PI) of soil treated with sand, at various contents using the artificial neural network (ANN) method. It was revealed that the ANN technique ensures good prediction accuracy for a large number of parameters related to geotechnical problems. For the purpose of predicting the plasticity index values of sand-treated soils, the results of experimental tests that were conducted on 38 soil samples were collected and thoroughly analyzed. It was decided to consider three inputs, namely the plastic limit, liquid limit, and sand percen...
International Journal for Research in Applied Science and Engineering Technology, 2022
The artificial neural network is robust in predicting soil properties. The present study aims to determine the suitable hyperparameters such as number of hidden layers, neurons, and backpropagation algorithms for the best prediction of geotechnical properties of soil. The supervised learning category-based multilayer perceptron artificial neural network approach is used, and models are developed in MATLAB R2020a. The ANN models are configured with neurons (5, 10 & 15), hidden layers (one to five), and a backpropagation algorithm (LM, BFG, SCG, GDA, GD & GDA). Fifteen ANN models are developed for each algorithm. The study shows that the LM, BFG, and SCG algorithm-based ANN models require strongly (0.61-0.8) to very strongly (0.81-1) correlated datasets. On the other hand, the GDM, GD, and GDA algorithm-based ANN models require only strongly correlated datasets to achieve a performance of more than 0.9. In most cases, it is also found that the GDM, GD, and GDA algorithm-based ANN models achieve high performance with three hidden layers interconnected with ten neurons. Still, LM algorithm-based ANN model achieves high performance with a single hidden layer interconnected with 5/15 neurons. The present work draws a relationship between the correlation coefficient and the number of hidden layers & neurons. It also helps to study the effect of hidden layers and neurons on the performance of ANN models. Formulas are derived from the performance of ANN models to calculate the required number of hidden layers and neurons for a particular backpropagation algorithm to achieve a testing performance of more than 0.9.
Machine learning techniques applied to prediction of residual strength of clay
Open Geosciences, 2011
Stability with first time or reactivated landslides depends upon the residual shear strength of soil. This paper describes prediction of the residual strength of soil based on index properties using two machine learning techniques. Different Artificial Neural Network (ANN) models and Support Vector Machine (SVM) techniques have been used. SVM aims at minimizing a bound on the generalization error of a model rather than at minimizing the error on the training data only. The ANN models along with their generalizations capabilities are presented here for comparisons. This study also highlights the capability of SVM model over ANN models for the prediction of the residual strength of soil. Based on different statistical parameters, the SVM model is found to be better than the developed ANN models. A model equation has been developed for prediction of the residual strength based on the SVM for practicing geotechnical engineers. Sensitivity analyses have been also performed to investigate...