چكيده به لاتين
Since most soils exist above the ground water table, negative pore water pressures develop in unsaturated soils. This negative pore water pressure, known as matric suction, causes increased shear strength. Therefore, it is required that the effect of the increase in shear strength should be included in geotechnical analyses.
However, experimental studies on unsaturated soils are generally costly, time-consuming, and difficult to conduct. Therefore, it is better to have an empirical method that is able to predict the unsaturated shear strength with respect to the matric suction in a more convenient way.
Recently the artificial intelligence as a functional method, and because of simplicity execution of modelling complicated and nonlinear problems, has attract the attention of geotechnical engineers.
In this study, the shear strength of unsaturated soil has been predicted by using artificial neural networks (ANNs) in reference to data obtained from published references. The used data bank contains some parametes related to features of soils, for example net normal stress, matric suction, internal friction angle and air entry value (AEV). Then the results of ANN have been compared with the real values of unsaturated shear strength and the values obtained from previous equations.
Finally two equations by using gene expression programming (GEP) have been presented to predict the shear strength of various unsaturated soils.