Author(s): Hossein Bonakdari; Azadeh Gholami; Isa Ebtehaj; Abdolmajid Mohammadian; Bahram Gharabaghi; Saeed Reza Khodashenas

Linked Author(s): Hossein Bonakdari

Keywords: Stable channel; Experimental model; ANFIS; Evolutionary optimization algorithm; Bank profile shape

Abstract: Forecasting the bank profile shape of stable hydraulic channels using empirical, experimental, and numerical models is an important research topic among river science engineers. In the present paper, the application of soft computing methods is evaluated in predicting the geometry of stable channel cross-sections. In this way, using a combination of the Particle Swarm Optimization (PSO) algorithm with an Adaptive Neuro-Fuzzy Inference System (ANFIS) model, a novel evolutionary system called ANFIS-PSO is presented. Besides, a new Group Method of Data Handling (GMDH) scheme known as Generalized Structure of GMDH (GSGMDH) was introduced. The authors also measured the coordinates of points located on a channel boundary in a stable state using a sensor instrument in the laboratory at four different flow discharge rates of 1.157, 2.18, 2.57, and 6.2 L/s. The results indicated that the evolutionary ANFIS-PSO model with Root Mean Squared Error (RMSE) and Mean Absolute Relative Error (MARE) of 0.0132 and 0.1326 performed better than the individual ANFIS, GMDH, and GSGMDH. These findings demonstrate the high accuracy of the ANFIS-PSO model in predicting bank profile characteristics. The robust evolutionary model proposed here can be used in designing and estimating stable channel dimensions. The second-degree polynomial equation proposed by the GSGMDH model can be utilized in predicting the coordinates of other points located on a stable boundary of a channel cross-section.

DOI: https://doi.org/10.3850/IAHR-39WC2521711920221118

Year: 2022