Discharge and flow field simulation of open-channel sewer junction using artificial intelligence methods

Abstract

One of the most important parameters in designing sewer structures is the ability to accurately simulate their discharge and velocity field. Among the various sewer receiving inflow methods, open-channel junctions are the most frequently utilized ones. Because of the existence of separation and contraction zones in the open-channel junctions, the fluid flow has a complex behavior. Modeling is carried out by Radial Basis Function (RBF) neural network, Gene Expression Programming (GEP), and Multiple Non-Linear Regression (MNLR) methods. Finding the optimum situation for GEP and RBF models is done by examining various mathematical and linking functions for GEP, different numbers of hidden neurons, and various spread amounts for RBF. In order to use the models in practical situations, three equations were conducted by using the RBF, GEP, and MNLR methods in modeling the longitudinal velocity. Then, the surface integral of the presented equations was used to simulate the flow discharge. The results showed that the GEP and RBF methods performed significantly better than the MNLR in open-channel junction characteristics simulations. The GEP method had better performance than the RBF in modeling the longitudinal velocity field. However, the RBF presented more reliable results in the discharge simulations.