Pseudo-Cosine Labyrinth Weir and Investigation of Its Discharge Coefficient Using Simulation-Prediction Approach

Labyrinth weirs are considered as an appropriate choice to correct the weirs that are having difficulty in passing the maximum possible flow. For this purpose, in the present study, a new weir was introduced called the of pseudo-Cosine labyrinth weir. First, models with different widths and heights were built in FLUENT software as a virtual laboratory. The anti-corona algorithm and adaptive neuro-fuzzy inference system (ACVO-ANFIS) were used for predicting discharge coefficient. of pseudo-Cosine labyrinth weir. Validation of the proposed method was performed using Experimental data. Then, to identify the superior model and determine the parameters affecting the discharge coefficient of pseudo-cosine labyrinth weir, the combination of different dimensionless parameters was evaluated. The performance of the proposed method was evaluated with five statistics, including determination coefficient (R2), root means squared error (RMSE), mean absolute percentage error (MAPE), nash-sutcliffe (NSE), and relative root mean square error (RRMSE). The results showed that in low hydraulic heads, the discharge coefficient has its highest value. As the radius increases, the discharge coefficient increases due to the increase in the effective length of the labyrinths. At a constant H/W, with increasing weir height, the discharge coefficient increased. The results of the ACVO-ANFIS model showed that the input variables are the ratio of the radius to the weir height (R/W), the ratio of the length of the weir to weir height (L/W), and the ratio of the hydraulic head to the weir height (H/W), with error values R2=0.971, RMSE=00.9, MAPE=0.006, RRMSE=0.010, and NSE=0.977, the most effective parameters in determining the discharge coefficient of pseudo-cosine labyrinth weirs.