---

This paper studies thoroughly and deeply the results of about one hundred triaxial compression tests on thirty types of rockfill
materials. The materials are categorized in accordance with their particles shape (angular / rounded) and gradation
characteristics. The main tool of the study is the Hyperbolic Model developed by Duncan and Chang. The focus of the study is
on the variations of deformation modulus of the materials (Ei and Et) with confining stress (&sigma3). Features of the mechanical
behavior of the rockfill materials, as compared with the general behavior of soils, are highlighted through the exponent
parameter (n) of the Hyperbolic Model. It is shown that high confining stresses may have adverse effects on the deformation
modulus of the rockfill materials and make them softer. The particle breakage phenomenon which happens during compression
and shearing is found as the main factor responsible for the above effects and, in general, responsible for controlling the
behavior of the materials. For the rockfill materials of this study, two correlations for estimating the initial elasticity modulus (Ei)
and the internal friction angle (&phi) in terms of particles shape, confining pressure (&sigma3), and coefficient of uniformity (Cu) are
suggested.

---

In comparison with other geomaterials, constitutive modeling of rockfill materials and its validation is more complicated. This is principally due to the existence of more intricate phenomena such as particle crushing, as well as laboratory test limitations. These issues have necessitated developing more complex constitutive models, with many parameters. Regardless of the type of model, the calibrations of the parameters in such models are considered as one of the most important and challenging steps in the application of the model. Therefore, the need for comprehensive and rapid methods for evaluation of optimum parameters of the models is deemed necessary. In this paper, a Neuro-Fuzzy model in conjunction with Particle Swarm Optimization (PSO) is used for calibration of the twelve parameters of Hierarchical Single Surface (HISS) constitutive model based on the Disturbed State Concept (DSC). The Neuro-fuzzy system is used to provide a high-degree nonlinear regression model between the deviatoric stress and volumetric strain versus axial strain that has been obtained from consolidated drained large scale tri-axial tests on rockfill materials. The model parameters are determined in an iterative optimized loop with PSO and ANFIS such that the equations of DSC/HISS are simultaneously satisfied. Material data used in this study are gathered from the results of large tri-axial tests for two rockfill dams in Iran. It is shown that the proposed method has higher accuracy and more importantly its robustness is exhibited through test predictions. The achieved improvement is substantiated in a comparison with the more widely used "Least-Square" method.

---

To investigate the saturation induced collapse deformation behavior of rockfill material, a set of large-scale triaxial tests were conducted in saturated and dry-saturated conditions. Specimens were tested under various confining pressures. For dry-saturated tests, specimens were sheared in various stress levels. Results of all dry saturated tests indicate a sudden reduction in the specimen volume during the submerging process. The ratio of the minimum axial strength of a submerged specimen (at the end of the saturation process) to the shear strength of the specimen before saturation is defined as the coefficient of stress recovery, Csr. Results show that this ratio increases as the confining pressure increases, and decreases as the shear stress level increases. According to the results of dry-saturated tests, reduction values of the internal friction angle caused by saturation (c), the ratio of the elasticity modulus of the material after saturation to its elasticity modulus in dry condition, i.e., Ewet/Edry, and the saturation induced sudden volumetric strain (vc) decrease as the confining pressures increase. However the shear stress level does not have any meaningful effect on the variation of c, Ewet/Edry and (vc).