The performance of the bio-inspired adaptive neuro-fuzzy inference system (ANFIS) models are proposed for forecasting highly non-linear streamflow of Pahang River, located in a tropical climatic region of Peninsular Malaysia. Three different bio-inspired optimization algorithms namely particle swarm optimization (PSO), genetic algorithm (GA), and differential evolution (DE) were individually used to tune the membership function of ANFIS model in order to improve the capability of streamflow forecasting. Different combination of antecedent streamflow was used to develop the forecasting models. The performance of the models was evaluated using a number of metrics including mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R2) and Willmott’s Index (WI) statistics. The results revealed that increasing number of inputs has a positive impact on the forecasting ability of both ANFIS and hybrid ANFIS models. The comparison of the performance of three optimization methods indicated PSO improved the capability of ANFIS model (RMSE=7.96; MAE=2.34; R2=0.998 and WI=0.994) more compared to GA and DE in forecasting streamflow. The uncertainty band of ANFIS-PSO forecast was also found the lowest (±0.217), which indicates that ANFIS-PSO model can be used for reliable forecasting of highly stochastic river flow in tropical environment.
The hydrological process has a dynamic nature characterised by randomness and complex phenomena. The application of machine learning (ML) models in forecasting river flow has grown rapidly. This is owing to their capacity to simulate the complex phenomena associated with hydrological and environmental processes. Four different ML models were developed for river flow forecasting located in semiarid region, Iraq. The effectiveness of data division influence on the ML models process was investigated. Three data division modeling scenarios were inspected including 70%–30%, 80%–20, and 90%–10%. Several statistical indicators are computed to verify the performance of the models. The results revealed the potential of the hybridized support vector regression model with a genetic algorithm (SVR-GA) over the other ML forecasting models for monthly river flow forecasting using 90%–10% data division. In addition, it was found to improve the accuracy in forecasting high flow events. The unique architecture of developed SVR-GA due to the ability of the GA optimizer to tune the internal parameters of the SVR model provides a robust learning process. This has made it more efficient in forecasting stochastic river flow behaviour compared to the other developed hybrid models.
Dam and powerhouse operation sustainability is a major concern from the hydraulic engineering perspective. Powerhouse operation is one of the main sources of vibrations in the dam structure and hydropower plant; thus, the evaluation of turbine performance at different water pressures is important for determining the sustainability of the dam body. Draft tube turbines run under high pressure and suffer from connection problems, such as vibrations and pressure fluctuation. Reducing the pressure fluctuation and minimizing the principal stress caused by undesired components of water in the draft tube turbine are ongoing problems that must be resolved. Here, we conducted a comprehensive review of studies performed on dams, powerhouses, and turbine vibration, focusing on the vibration of two turbine units: Kaplan and Francis turbine units. The survey covered several aspects of dam types (e.g., rock and concrete dams), powerhouse analysis, turbine vibrations, and the relationship between dam and hydropower plant sustainability and operation. The current review covers the related research on the fluid mechanism in turbine units of hydropower plants, providing a perspective on better control of vibrations. Thus, the risks and failures can be better managed and reduced, which in turn will reduce hydropower plant operation costs and simultaneously increase the economical sustainability. Several research gaps were found, and the literature was assessed to provide more insightful details on the studies surveyed. Numerous future research directions are recommended.
Dam operation and management have become more complex recently because of the need for considering hydraulic structure sustainability and environmental protect on. An Earthfill dam that includes a powerhouse system is considered as a significant multipurpose hydraulic structure. Understanding the effects of running hydropower plant turbines on the dam body is one of the major safety concerns for earthfill dams. In this research, dynamic analysis of earthfill dam, integrated with a hydropower plant system containing six vertical Kaplan turbines (i.e., Haditha dam), is investigated. In the first stage of the study, ANSYS-CFX was used to represent one vertical Kaplan turbine unit by designing a three-dimensional (3-D) finite element (FE) model. This model was used to differentiate between the effect of turbine units’ operation on dam stability in accordance to maximum and minimum reservoir upstream water levels, and the varying flowrates in a fully open gate condition. In the second stage of the analysis, an ANSYS-static modeling approach was used to develop a 3-D FE earthfill dam model. The water pressure pattern determined on the boundary of the running turbine model is transformed into the pressure at the common area of the dam body with turbines. The model is inspected for maximum and minimum upstream water levels. Findings indicate that the water stress fluctuations on the dam body are proportional to the inverse distance from the turbine region. Also, it was found that the cone and outlet of the hydropower turbine system are the most affected regions when turbine is running. Based on the attained results, a systematic operation program was proposed in order to control the running hydropower plant with minimized principal stress at selected nodes on the dam model and the six turbines.
This study focuses on improving the safety of embankment dams by considering the effects of vibration due to powerhouse operation on the dam body. The study contains two main parts. In the first part, ANSYS-CFX is used to create the three-dimensional (3D) Finite Volume (FV) model of one vertical Francis turbine unit. The 3D model is run by considering various reservoir conditions and the dimensions of units. The Re-Normalization Group (RNG) k-ε turbulence model is employed, and the physical properties of water and the flow characteristics are defined in the turbine model. In the second phases, a 3D finite element (FE) numerical model for a rock-fill dam is created by using ANSYS®, considering the dam connection with its powerhouse represented by four vertical Francis turbines, foundation, and the upstream reservoir. Changing the upstream water table minimum and maximum water levels, standers earth gravity, fluid-solid interface, hydrostatic pressure, and the soil properties are considered. The dam model runs to cover all possibilities for turbines operating in accordance with the reservoir discharge ranges. In order to minimize stresses in the dam body and increase dam safety, this study optimizes the turbine operating system by integrating turbine and dam models.
1 December 2017 in Journal of Computational and Theoretical Nanoscience
Understanding the dynamic behavior of a dam against seismic load is important to determine its safety requirements. Complex dam–reservoir–foundation system interactions must be considered when evaluating the seismic behavior of a rockfill dam. The interactions are coupled with the hydrodynamic pressure generated from seismic forces. This paper presents the dynamic analysis of the Temenggor rockfill dam with foundational effects by considering the dam’s connection with the reservoir bed and water. ANSYS® was used to create a 3D numerical model of the dam. Incompressible fluid and foundation were assumed for both cases of fixed and bedrocks. Various proportions were assumed for the elasticity module to analyze the complete dynamic interactions between the dam and the reservoir. The generated results from ANSYS for multiple frequencies proved to be excellent. Analysis results showed that the ranges of stress increased from 97% to 99.8%. Adding the water effect to the model decreased the natural frequencies of the system and increased the stresses on all boundary condition assumptions (fixed, shallow, and deep rock foundation) at different percentages but helped stabilize the mode shapes.