Abstract: By GEO5 FEM program with four rockfill slope
modeling and stability analysis was performed for S1, S2, S3 and
S4 slopes where landslides of the shalefills were limited. Effective
angle of internal friction (φ'°) 17°-22.5°, the effective cohesion (c')
from 0.5 to 1.8 kPa, saturated unit weight 1.78-2.43 g/cm3, natural
unit weight 1.9-2.35 g/cm3, dry unit weight 1.97-2.40 g/cm3, the
permeability coefficient of 1x10-4 - 6.5x10-4 cm/s. In cross-sections
of the slope, GEO 5 FEM program possible critical surface tension
was examined. Rockfill dump design was made to prevent sliding
slopes. Bulk material designated geotechnical properties using also
GEO5 programs FEM and stability program via a safety factor
determined and calculated according to the values S3 and S4 No.
slopes are stable S1 and S2 No. slopes were close to stable state
that has been found to be risk. GEO5 programs with limestone rock
fill dump through FEM program was found to exhibit stability.
Abstract: The Cone Penetration Test (CPT) is a common in-situ
test which generally investigates a much greater volume of soil more
quickly than possible from sampling and laboratory tests. Therefore,
it has the potential to realize both cost savings and assessment of soil
properties rapidly and continuously. The principle objective of this
paper is to demonstrate the feasibility and efficiency of using
artificial neural networks (ANNs) to predict the soil angle of internal
friction (Φ) and the soil modulus of elasticity (E) from CPT results
considering the uncertainties and non-linearities of the soil. In
addition, ANNs are used to study the influence of different
parameters and recommend which parameters should be included as
input parameters to improve the prediction. Neural networks discover
relationships in the input data sets through the iterative presentation
of the data and intrinsic mapping characteristics of neural topologies.
General Regression Neural Network (GRNN) is one of the powerful
neural network architectures which is utilized in this study. A large
amount of field and experimental data including CPT results, plate
load tests, direct shear box, grain size distribution and calculated data
of overburden pressure was obtained from a large project in the
United Arab Emirates. This data was used for the training and the
validation of the neural network. A comparison was made between
the obtained results from the ANN's approach, and some common
traditional correlations that predict Φ and E from CPT results with
respect to the actual results of the collected data. The results show
that the ANN is a very powerful tool. Very good agreement was
obtained between estimated results from ANN and actual measured
results with comparison to other correlations available in the
literature. The study recommends some easily available parameters
that should be included in the estimation of the soil properties to
improve the prediction models. It is shown that the use of friction
ration in the estimation of Φ and the use of fines content in the
estimation of E considerable improve the prediction models.