The bottom outlet is essential for dams, controlling reservoir water volume, managing downstream flow, and discharging sediment. Understanding pressure distribution around the high-pressure gate is crucial for assessing risks like cavitation, vibrations, and down-pull forces. This paper presents a model for estimating pressure distribution around the Downpull Force of dams using an Adaptive Neuro-Fuzzy Inference System (ANFIS). The model was trained with laboratory data from physical models of the Ghezghaleh Si, Alborz, Gotvand, Namroud, and Seymareh dams. Analysis revealed that pressure distribution around the bottom lip face of the gates varies from the vertical face and in the vertical direction for 80% and 90% of openings differ from other openings. Results demonstrate a significant reduction in the mean relative error of estimated vertical forces on the gates from 61.2% (using the Naudascher ratio) to 10.1%. Notably, this research uniquely estimates horizontal force levels with an average acceptable error of 5.3%, minimizing the need for costly laboratory modeling. This model's key advantage is its ability to estimate horizontal forces that typically require laboratory testing. Its high accuracy makes it preferable for designing high-pressure gate elevator jacks over standard methods and prior laboratory or numerical studies.
Sajadi et al. (Tue,) studied this question.