Performance Assessment of Various Data-Mining Methods to Determine Depth Velocity Profile at Submerged Hydraulic Jump

Vertical velocity distribution at hydraulic jump is one of the challenging and significant issues among researchers because of the complexity of measurement and calculations. In this research, the application of the SVM and GEP intelligent models has been considered to determine the vertical velocity profile at the submerged hydraulic jump downstream of a sluice gate. Laboratory measured data of number 312 has been used in the simulation. Using dimensional analysis, dimensionless input parameters were introduced to models including  upstream Froud number (Fr1), Tail water Froud number (Fr3), the ratio of upstream flow depth to the tailwater depth , the ratio of the gate opening to the channel width , and the ratio of vertical distance from the channel bed to the channel width . Using the gama test, all five parameters were determined as the optimum combination to simulate velocity profile. Of two Nu-SVM and C-SVM classification models, the first one was opted as optimum model of the SVM algorithm with RBF Kernel function with the setting parameters γ and Nu of values 1.2 and 0.486, respectively. The performance of the Nu-SVM and the GEP intelligent,models were assessed using statistical criteria. The results showed that the values of (RMSE, R2, ) indices for the test phase of the Nu-SVM and the GEP algorithms are (0.09588,0.9770,0.4489) and (0.1161,0.9718,0.3588) respectively; illustrating the superiority of the Nu-SVM algorithm. Also, according to the gana test, the arrangment of the effective dimensionless parameters on the velocity profile is , Fr1, , Fr3 and .