Combined particle swarm optimization and fuzzy inference system model for estimation of current-induced scour beneath marine pipelines

摘要

In this paper the capability of Particle Swarm Optimization (PSO) is employed to deal with annAdaptive Network based Fuzzy Inference System (ANFIS) model’s inherent shortcomings to extractnoptimum fuzzy if–then rules in noisy areas arising from the application of nondimensionalnvariables to estimate scour depth. In the model, a PSO algorithm is employed to optimize thenclustering parameters controlling fuzzy if–then rules in subtractive clustering while another PSOnalgorithm is employed to tune the fuzzy rule parameters associated with the fuzzy if–then rules.nThe PSO model’s objective function is the Root Mean Square (RMSE), by which the modelnattempts to minimize the error in scour depth estimation with respect to its generalizationncapability. To evaluate the model’s performance, the experimental datasets are used as training,nchecking and testing datasets. Two-dimensional and nondimensional models are developed suchnthat in the dimensional model the mean current velocity, mean grain size, water depth, pipendiameter and shear boundary velocity are used as input variables while in the nondimensionalnmodel the pipe, boundary Reynolds numbers, Froude number and normalized depth of water arenset as input variables. The results show that the model provides an alternative approach to thenconventional empirical formulae. It is evident that the developed PSO–FIS–PSO is superior tonthe ANFIS model in the noisy area in which the input and output variables are slightly relatednto each other.