GRNN-based models for hydraulic jumps in a straight rectangular compound channel

The difficulty of the problem of the flow hydraulics in compound channels is due to the implicit interaction between the floodplains and the main channel, characterizing every particular shape of the compound channel. The problem is much more complicated when it comes to an energy dissipator like a hydraulic jump as is the case in the present study. In this paper, the general regression neural network (GRNN) was applied to predict the basic characteristics of hydraulic jumps in a straight rectangular compound channel: (i) the sequent depths ratios, (ii) the relative energy losses, and (iii) the relative lengths. Experiments were carried out with three different values of the ratio between the main channel width and the flood plain one (W-y). The W-y values were: (1/4, 1/3, and 1/2). For each W-y ratio, several values of inflow Froude number were considered according to the five inflow ratio depths' (W-z) values (0.167, 0.200, 0.253, 0.287, and 0.333) between the first sequent depth and of the main channel one. The predicted values in the testing stages using GRNN followed the experimental ones with a correlation coefficient (R) of 0.990 for the sequent depth's ratios, 0.982 for relative energy losses, and 0.873 for the relative lengths of hydraulic jumps. The best models have been selected among several input configurations for each of three considered characteristics of the jump.