Comparison Between Two Different Adaptive Neuro Fuzzy Interface Systems in Side Weir Characteristic Simulation

---

Thursday 2 july 2015

12:45 - 12:48h at Oceania Foyer (level 0)

Themes: (T) Water resources and hydro informatics (WRHI), (ST) Surface and subsurface flow interactions, Poster pitches

Parallel session: Poster pitches: 11L. WRHI - FlowInteractions

---

Side weirs have a critical role in many hydraulic structures. Designing the appropriate side weir needs the ability to simulate the discharge coefficient in different conditions. The aim of this paper is to develop and compare two different hybrid soft computing methods in modified side weir discharge coefficient simulation. For this reason, the Adaptive Neuro-Fuzzy Interface System (ANFIS) is combined with two optimization algorithms of Differential Evaluation (ANFIS-DE) and Genetic Algorithm (ANFIS-GA) to predict the discharge coefficient. In order to finding the most appropriated input variables, four different input combinations were investigated. The results showed that the ANFIS-DE with RMSE of 0.077 has better performance compared with the ANFIS-GA with RMSE of 0.079.