Prediction of ultimate bearing capacity of shallow foundation on granular soils using Imperialist Competitive Algorithm based ANN

The prediction of the ultimate bearing capacity of shallow foundation is one of the basic issues in geotechnical engineering. So far, several methods have been used to estimate the ultimate bearing capacity of shallow foundation, including the artificial intelligence methods. In recent years, optimization algorithms have been used to minimize neural network errors, such as Colony algorithm, Genetic algorithm, Imperialist competitive algorithm. In this research, artificial neural networks based on imperialist competitive algorithm (ICA) were used and their results were compared with other methods. The results of laboratory shallow foundation test on granular soils with parameters containing length, buried depth, L/B ratio, density and internal friction angle of soil were used for training and testing of the model. The results showed that ICA-based artificial neural networks predict the final bearing capacity of the shallow foundations with a correlation coefficient of 0.9908 for training data and 0.9882 for testing data. Also, the results of the model showed the superiority of ICA-based artificial neural networks compared to back-propagation neural networks and methods of Meyerhof, Vesic and Hansen methods

Keywords:

Bearing capacity , Shallow foundation , Granular soil , Artificial neural network , Imperialist competition algorithm ,