The strain on any structure is a critical issue worldwide, resulting from loads on the structure. An exact prediction at all the expected strains ranges on the dam will pave the way for better dam management under different discharges. The main aims of the present paper are to study the behaviour of strains on the dam and create a model based on ANN techniques that can be used to predict the strain on the model of the Haditha dam. The ANN is a computational model that simulates the method neurons work in the human brain. The research includes a study of the strains on the dam body and the gate. The input of the present model includes gate opening, discharge, depth of upstream water, and force on the dam body and gate. The model has been applied by using 150 actual testes of strain in the hydraulic laboratory. The model has been achieved by using a MATLAB software with hyperbolic sigmoid transfer function and three nodes. The accuracy of the model was achieved by using some statistical indicators. The results show the ANN is capable of predicting the strain on the Haditha dam with high accuracy. The regression for both strains on the dam body and the gate was more than 89% for all training, validation, testing, and all samples.
The use of traditional methods to predict evaporation may face many obstacles due to the influence of many factors on the pattern of evaporation's shape. Therefore, the use of existing methods of artificial intelligence is a reliable prediction model in many applications in engineering. Monthly measurements were employed in the present work to predict for duration eighteen years, from beginning of January 2000 until December 2017. The best model was chosen using ANNs (MLP, RBF) and AI (SVM) techniques. The best evaporation model prediction was made using ANNs (MLP, RBF) and AI (SVM) technologies, with temperature, wind speed, relative humidity, and sunshine hours used as independent variables. Several statistical metrics have been used to evaluate the effectiveness of the proposed model to other popular artificial intelligence models. The obtained result denotes the superiority of the MLP models over the RBF and SVM models. It is concluded that the MLP model is better than RBF and SVM for evaporation prediction for both groups. A comparison of the model performance between MLP, RBF, and SVM models indicated that the MLP-ANN method presents the best estimates of monthly evaporation rate with minimum RMSE 0.033, minimum MAE 0.026, and maximum determination coefficient 0.967.
Spillways are designing to release surplus water over a volume of storage. The excess water flows from the top of the reservoir and is carried back to the river by a spillway. Many radial gates were destroyed under hydrodynamic load. Radial gate connectors are susceptible to fatigue failure due to excessive vibration; therefore, gate vibration during operation must be investigated to confirm safe operation at the design water pressure. Several studies were carried out to analyse and simulation of flow over the spillway. In this article, the flow pattern over the Haditha dam spillway has been simulated using computational fluid dynamics (CFD). The numerical model was performed using Ansys Fluent 2020 R1 to simulate the flow properties; determination of cavitation damage at three discharges corresponding in the design of Haditha dam are 4700, 7140, and 7900 m3/s. In addition to finding the effect of gate vibration under dynamic water loads. The Realisable k-ɛ turbulence model was utilised with the volume of fluid (VOF) model to simulate the interaction between air and water phases. The validation of the numerical model was achieved by comparing it with a physical model. The physical model of the Haditha Dam spillway was made from iron with a scale of 1:110. It has been designed and constructed in a hydraulic laboratory according to the modelling principle of the hydraulic structure. The results showed that a high agreement between the physical and numerical model and the k-ɛ turbulence model could simulate the Haditha dam spillway with low cost and few times. The cavitation damage may occur at the region start at the end of the arching spillway to stretches downstream, and there is no damage of gate vibration under dynamic water load.
In this paper the artificial neural network used to predict dilly evaporation. The model was trained in MATLAB with five inputs. The inputs are Min. Temperature, Max. Temperature, average temperature, wind speed and humidity. The data collected from Alramadi meteorological station for one year. The transfer function models are sigmoid and tangent sigmoid in hidden and output layer, it is the most commonly used nonlinear activation function. The best numbers of neurons used in this paper was three nodes. The results concludes, that the artificial neural network is a good technique for predicting daily evaporation, the empirical equation can be used to compute daily evaporation (Eq.6) with regression more than 96% for all (training, validation and testing) as well as, in this model that the Max. Temperature is a most influence factor in evaporation with importance ratio equal to (30%) then humidity (26%).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.