Comparison of The Hydraulic Efficiency of labyrinth Weirs with a Quarter and Semi-Circular Crest Shape Using Neural Networks (QNET, SVM, GEP, ANN)
While having economic advantages, non-linear weirs have more passing flow capacity than linear weirs. These weirs have higher discharge efficiency with less free height upstream compared to linear weirs by increasing the length of the crown at a certain width. Intelligent algorithms have found a valuable place among researchers due to their great ability to discover complex and hidden relationships between effective independent parameters and dependent parameters, as well as saving money and time. In this research, the performance of support vector machine (SVM), gene expression programming (GEP), software (QNET) and artificial intelligence network (ANN) in predicting the discharge coefficient of non-linear Weirs of 318 data series for the first scenario And the second scenario includes the number of 363 data series and the third scenario includes data integration (the sum of the first and second scenario) which includes 681 data series. The difference between the first and second scenarios is in the shape of the quarter-circle and semi-circle weir crown. The geome tric and hydraulic lines used in this research include total water load ratio (H_T/p), magnification) L_C/W), cycle wall angle (α) and discharge coefficient (Cd). The results of artificial intelligence showed that the combinations (Cd, H_T/p, α, L_C/W) in QNET, ANN, GEP, SVM algorithms in the training stage related to the superior scenario are equal to the evaluation indicators respectively (R2=0.9960), (RMSE=0.0080), (DC=0.9961), (R2=0.9980), (RMSE=0.0057), (DC=0.9980), (R2=0.9837), (RMSE=0.0207), (DC=0.9838) and (R2=0.9902), (RMSE=0.0186), (DC=0.9830). Which has led to the most optimal output compared to other combinations, which indicates a very favorable accuracy in all four methods, namely ANN, QNET, SVM and GEP in predicting the weir discharge coefficient is non-linear. The results of the sensitivity analysis showed that the effective parameter in determining the nonlinear weir discharge coefficient in all methods is the total water load ratio parameter (H_T/p).
- حق عضویت دریافتی صرف حمایت از نشریات عضو و نگهداری، تکمیل و توسعه مگیران میشود.
- پرداخت حق اشتراک و دانلود مقالات اجازه بازنشر آن در سایر رسانههای چاپی و دیجیتال را به کاربر نمیدهد.