Buried pipes are extensively used for oil transportation from offshore platforms. Under unfavorable loading combinations, the pipe’s uplift resistance may be exceeded, which may result in excessive deformations and significant disruptions. This paper presents findings from a series of small-scale tests performed on pipes buried in geogrid-reinforced sands, with the measured peak uplift resistance being used to calibrate advanced numerical models employing neural networks. Multilayer perceptron (MLP) and Radial Basis Function (RBF) primary structure types have been used to train two neural network models, which were then further developed using bagging and boosting ensemble techniques. Correlation coefficients in excess of 0.954 between the measured and predicted peak uplift resistance have been achieved. The results show that the design of pipelines can be significantly improved using the proposed novel, reliable and robust soft computing models.

Soil improvement is required to decrease the construction impact on the adjacent underground structures, when a deep excavation is carried out. Deep soil mixing (DSM) is a common method to control deformation caused by deep excavation. This method is an in situ soil mixing technology that mixes existing soil with cementitious materials. This paper presents a numerical modeling of DSM columns, which was conducted to compare the affected zone achieved by installing two different partially penetrated soil-cement columns using a small scale physical modelling. Test procedure and the finite element analysis that verify ground displacement patterns were described. The finite element method (FEM) was focused on the plane strain numerical modeling in ABAQUS. It was found that higher numbers of piles increase the effect of soil deformation where it will extend the soil in much deeper depth before it fails.