The Effectiveness of Ensemble-Neural Network Techniques to Predict Peak Uplift Resistance of Buried Pipes in Reinforced Sand

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