Energy Dissipation in Rough Chute: Experimental Approach Versus Artificial Intelligence Modeling

Abstract

Equipment of chute structures is necessary in dam spillway and irrigation canals for the dissipation of water excess energy. This chapter investigates the effects of different variables including roughness, height and slope of chute on energy dissipation using non-dimensional relationships. Datasets are used to develop a regression model with nine data intelligent analytic (artificial intelligence, AI) models. The chapter indicates that the relative energy loss can be essentially expressed as a function of scale roughness. In the range of the experimental data, chute slope and ratio between the critical water depth and the chute height cannot influence the significant effects on energy loss. Maximum and minimum relative energy dissipation occurs at the slopes of 16.4 and 35°, respectively. CCNN model yields excellent performance for predicting of relative energy loss (R2 = 0.983 and RMSE = 0.02). The methodologies are adaptable in real decision support systems for disaster risk mitigation.