---

The safety of buried pipes under repeated load has been a challenging task in geotechnical engineering. In this paper artificial neural network and regression model for predicting the vertical deformation of high-density polyethylene (HDPE), small diameter flexible pipes buried in reinforced trenches, which were subjected to repeated loadings to simulate the heavy vehicle loads, are proposed. The experimental data from tests show that the vertical diametric strain (VDS) of pipe embedded in reinforced sand depends on relative density of sand, number of reinforced layers and height of embedment depth of pipe significantly. Therefore in this investigation, the value of VDS is related to above pointed parameters. A database of 72 experiments from laboratory tests were utilized to train, validate and test the developed neural network and regression model. The results show that the predicted of the vertical diametric strain (VDS) using the trained neural network and regression model are in good agreement with the experimental results but the predictions obtained from the neural network are better than regression model as the maximum percentage of error for training data is less than 1.56% and 27.4%, for neural network and regression model, respectively. Also the additional set of 24 data was used for validation of the model as 90% of predicted results have less than 7% and 21.5% error for neural network and regression model, respectively. A parametric study has been conducted using the trained neural network to study the important parameters on the vertical diametric strain.

---

Conventional investigations on the behavior of reinforced and unreinforced soils are often investigated at the failure point. In this paper, a new concept of comparison of the behavior of reinforced and unreinforced soil by estimating the strength and strength ratio (deviatoric stress of reinforced sample to unreinforced sample) at various strain levels is proposed. A comprehensive set of laboratory triaxial compression tests was carried out on wet (natural water content) non-plastic beach silty sand with and without geotextile. The layer configurations used are one, two, three and four horizontal reinforcing layers in a triaxial test sample. The influences of the number of geotextile layers and confining pressure at 3%, 6%, 9%, 12% and 15% of the imposed strain levels on sample were studied and described. The results show that the trend and magnitude of strength ratio is different for various strain level. It implies that using failure strength from peak point or strength corresponding to the axial-strain approximately 15% to evaluate the enhancement of strength or strength ratio due to reinforcement may cause hazard and uncertainty in practical design. Hence, it is necessary to consider the strength of reinforced sample compared with unreinforced sample at the imposed strain level. Only one type of soil and one type of geotextile were used in all tests.

---

ABSTRACT The influence of the sand placement method above geotextile layer on interface shear strength behavior was investigated. Seven different types of woven and non woven geotextile were used with only poorly graded sand. The investigation involved placement of sand layer through inclined horizontal plane with different angles. This step constitutes a fundamental step for assessing soil to be deposited in different plane and therefore with different internal soil fabric. The interface shear strength was evaluated by using direct shear test. Although the investigated soil is uniform poorly graded sand, the influence of the deposit plane was significant especially for nonwoven geotextile. Differences in soil interface shear strength associated with the tested geotextiles samples shows that samples with higher mass per unit area and same opening sizes had the higher interface friction angle regardless the bedding plane. Influence of bedding plane on interface modulus of elasticity which used in most of interface modeling was investigated using Janbu’s formula. It is noted that the use of secant interface modulus of elasticity at 1% strain and at 50% of peak stresses gave a consistent prediction of n and Ku constant appear in Janbu’s formula for all types of geotextile. The above results were reflected in the prediction for interface molded such as Chen and Juran as shown. Therefore, the existing interface modeled is needed to be modified to account for the method that the sand is being placed above the geotextile layer.