Estimating Fluid Parameters of Submarine Outfall Using Neural Networks

Abstract

Disposal of the urban and industrial liquid waste has become important by paying attention toenvironmental and human health recently. Submarine outfall diffusers are the major parts of the marinedisposal systems. Pipe of the diffuser, risers and ports, internal and external flows which form thedischarge system are modelled and fluid-structure interaction (FSI) method is utilized by ABAQUSfinite elements program. Coupled CFD & Explicit technique is performed in FSI analysis. Method ofbidirectional fluid-structure interaction (FSI) is used in finite elements method (FEM). Internal andexternal flows constitute fluid domain and diffuser constitutes the structure domain. While internalvelocity and pressure values are obtained from the program, predictions of these results are performed byArtificial Neural Network (ANN) analysis. The average discharge velocities provide to avoid waterintrusion into the ports. According to results obtained by FEM it can be said that the discharge systemworks efficiently. Numerical and estimated values are compared and the relationship between thesevalues is investigated. The correlation coefficients are calculated by using numerical and estimatedvalues and it is observed that a strong relationship is obtained between them.