Estimation of Velocity Distribution in Smooth-Bed Open Channels Using Adaptive Neuro-Fuzzy Inference System and Genetic Programming

Estimation of Velocity Distribution in Smooth-Bed Open Channels Using Adaptive Neuro-Fuzzy Inference System and Genetic Programming

Saeed Samadianfard1 Davood Farsadizadeh2 Ali Hosseinzadeh Dalir3 Mohammad Ali Ghorbani4

1) Assistant Professor, Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Iran
2) Professor, Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Iran
3) Professor, Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Iran
4) Associate Professor, Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Iran

IOI Code : XYAA-ZBDKA
Publication : 2nd International conference on sustainable development, strategies and challenges With a focus on Agriculture, Natural Resources, Environment and Tourism(2icsda.ir)
Abstract :
    Due to the importance of velocity distributions in open channels and their relations to other important hydraulic parameters such as discharge, shear stress and sediment transportation, presenting the mathematical model for estimating velocity distribution is necessary. In the current research, intelligent methods including genetic programming and adaptive neuro-fuzzy inference system have been used for estimating velocity distributions in open channels. For comparing the mentioned methods, some experiments have been carried out in an open channel with discharge rates in the range of 4.8-32.89 l/s and furthermore, velocity distributions have been measured by precision of 0.1 cm/s in the every 1 cm distance from the bottom of the channel. The obtained results from statistical analysis of the methods showed that genetic programming had better accuracy in comparison with adaptive neuro-fuzzy inference system in estimation of velocity distributions in channel sections. Then, the mentioned method can be used for predicting velocity distributions in open channels with suitable precision.

Keywords : estimation genetic programming neuro fuzzy open channels velocity distribution