Classification of slopes and prediction of factor of safety using differential evolution neural networks

Abstract

Slope stability analysis is one of the most important problems in geotechnical engineering. The development in slope stability analysis has followed the development in computational geotechnical engineering. This paper discusses the application of different recently developed artificial neural network models to slope stability analysis based on the actual slope failure database available in the literature. Different ANN models are developed to classify the slope as stable or unstable (failed) and to predict the factor of safety. The developed ANN model is found to be efficient compared with other methods like support vector machine and genetic programming available in literature. Prediction models are presented based on the developed ANN model parameters. Different sensitivity analyses are made to identify the important input parameters.

Prediction of peak ground acceleration of Iran's tectonic regions using a hybrid soft computing technique

“…To obtain an optimal solution and avoiding this problem, an ANN may be trained using global optimization algorithms (e.g. Das et al, 2011). Ledesma et al (2007) have recently combined ANN and a well-known derivatively-free global optimization algorithm named simulated annealing (SA) to improve the ANN efficiency.…”

Artificial Neural Networks in Geotechnical Engineering

“…Goh (2002) used GA to find the optimum spread of the probabilistic network for liquefaction analysis, and Goh et al (2005) used GA for training the BPNN. Recently, Das et al (2010Das et al ( , 2011a used DE for the BPNN, while predicting swelling pressure of expansive soil and factor of safety of slope, respectively.…”

“…The prediction of factor of safety using the ANN model trained with DENN is found to be more efficient compared to traditional learning algorithms, the Bayesian regularization method (BRNN) and the LM-trained neural network (LMNN) (Das et al, 2011a). The database consisting of case studies of 23 dry and 23 wet slopes with 29 failed and 17 stable slopes, available in Sah et al (1994), is considered.…”

Methods of Sensitivity Analyses and theirs Role in Engineering

“…Representative studies of the use of ANNs to analyze the sensitivity of parameters of an engineering system are e.g. [9][10][11][12]. The paper shows alternative SA techniques and theirs utilization for practical engineering example.…”