No abstract

The scour around submarine pipelines may influence their stability; therefore scour prediction is a very important issue in submarine pipelines design. Several investigations have been conducted to develop a relationship between wave-induced scour depth under pipelines and the governing parameters. However, existing formulas do not always yield accurate result due to the complexity of the scour phenomenon. Recently, machine learning approaches such as Artificial Neural Networks (ANNs) have been used to increase the accuracy of the scour depth prediction. Nevertheless, they are not as transparent and easy to use as conventional formulas. In this study, the waveinduced scour was studied in both clear water and live bed conditions using M5' model tree as a novel soft computing method. M5' model is more transparent and can provide understandable formulas. To develop the models several dimensionless parameter such as gap to diameter ratio, Keulegan-Carpenter number and Shields' number were used. The results show that the M5' models increase the accuracy of the scour prediction and that Shields' number is very important in the clear water condition. Overall, results illustrate that the developed formulas could serve as 2 a valuable tool for the prediction of wave-induced scour depth under both live bed and clear water conditions.

Reliable prediction of scour depth is important in engineering analysis concerned with pipeline stability. The aim of this study is to develop an accurate formula for prediction of the current-induced scour depth under pipelines. Previous experimental data are collected and used as a database by which to study the effect of different parameters on the scour depth. Decision tree and nonlinear regression approaches are used to develop engineering design formulae for estimation of the current induced scour depth in both live bed and clear water conditions. It is demonstrated that the proposed formulas are more accurate than previous ones in predicting the scour depth in all conditions. Probabilistic formulas are also presented for different levels of risk, aimed at safe and economic design of submerged pipelines.