سال انتشار: ۱۳۹۱

محل انتشار: نهمین کنگره بین المللی مهندسی عمران

تعداد صفحات: ۹

نویسنده(ها):

M.R.M Tabatabai – Assistant Prof., Faculty of Water Engineering, Power and Water University of Technology, Tehran
A Tahershamsi – Associate Prof., Faculty of Civil and Environmental Engineering, Amirkabir University
R. Shirkhani –

چکیده:

An intelligent method based on adaptive neuro-fuzzy inference system (ANFIS) for identifying stable width of alluvial channels is presented. Many equations are available in the literature to predict stable width of alluvial channel. However, none of them is widely accepted at present, due to the fact that most of them are limited to hypothesis, aimed to simplify the high quantity of involved variables, and a lack of knowledge of some physical process associated with channel formation and maintenance. In this paper, an ANFIS model was established to predict the regime width of gravel bed channels, with the bankfull discharge, mean bed particle size, bed load sediment per unit width and channel slope as four input parameters. A regression equation is also applied to the data. Statistical measures were used to evaluate the performance of the models. Based on comparison of the results, it is found that the ANFIS model gives better estimates than that of the empirical equations