An alternative approach for investigation of the wave-induced scour around pipelines

Abstract

Scour around submarine pipelines remains a largely complex and not yet fully understood problem. In this study, wave-induced scour around submarine pipelines was investigated. Since various physical processes occur during the development of a scour hole, the effects of each process were considered by employing several nondimensional parameters. To find the effective parameters on equilibrium scour depth, the correlation between independent parameters (e.g. Keulegan-Carpenter number) and dependent parameter (nondimensional scour depth) were determined using different experimental data. Then, an Artificial Neural Network (ANNs) approach was used to develop a more accurate model for prediction of wave-induced scour depth around submarine pipelines. ANN models with different input parameters including gap to diameter ratio, Keulegan-Carpenter number, pipe Reynolds number, Shields number, sediment Reynolds number and boundary layer Reynolds number were trained and evaluated to find the best predictor model. To develop the ANN models, both holdout and tenfold cross-validation methods were used. In addition, an existing empirical method was examined. Results show that the empirical method has a significant error in the prediction of scour depth for the cases with an initial gap between pipe and seabed. It is also indicated that the ANN models outperform the empirical method in terms of prediction capability.

A new method for the prediction of wave runup on vertical piles

“…Ease of the application, as well as less required computational time, have made these methods more suitable for developing predictor models. Data mining methods such as artificial neural networks (ANNs), fuzzy inference systems (FISs) and decision trees (DTs) have been used in several fields of coastal and ocean engineering such as wind-wave prediction (Kazeminezhad et al, 2005), Coastal Engineering 98 (2015) 55-64 scour depth estimation around pipeline Kazeminezhad et al, 2010;Yasa and Etemad-Shahidi, 2014) and structural and hydraulic response of breakwaters (Etemad-Shahidi and Bali, 2011;Etemad-Shahidi and Bonakdar, 2009).…”

Estimation of scour around submarine pipelines with Artificial Neural Network

“…ANNs can be classified in terms of their topology (e.g., single-and multi-layer feed forward networks). In recent years, multi-layer feed forward networks have been applied extensively to solve various engineering problems (e.g., [1,2,14,15,32]). Artificial neurons are the building structure elements of ANNs, the neurons are organized in layers.…”

“…In recent years Artificial Neural Networks (ANNs), Genetic Programming (GP) and Fuzzy Inference Systems (FIS) have been used to predict the equilibrium scour depth around piles or pipes (e.g., [14]). These techniques have also been used in other marine and coastal engineering studies such as nearshore processes and coastal modeling [37,7], wind-wave estimation (e.g., [9,13,42,27]), ecological system analysis in coastal waters [34,8], and current velocity forecasting in straits [1].…”

“…Kazeminezhad et al [14] studied the wave-induced equilibrium scour depth around submarine pipelines using the experimental data from Pu et al [36], Sumer and Fredsøe [38], and Mousavi et al [33] by ANN approach. Kazeminezhad et al [14] tried to determine the non-dimensional effective parameters on equilibrium scour depth.…”

“…Kazeminezhad et al [14] tried to determine the non-dimensional effective parameters on equilibrium scour depth. The correlation between independent parameters (e.g., KC number) and the dependent parameter (nondimensional scour depth) was determined.…”