محمدرضا زائر ی

Installation and establishment of appropriate flow measurement structures, their proper operation, and collection of water consumption data play a crucial role in empowering network managers' decision-making, ensuring fair water distribution and transmission, and ultimately achieving water conservation. Flap or hanging gates are simple and inexpensive devices for both automatic control and flow measurement. In this research, the laboratory results obtained from a rectangular hinged gate structure, which is placed in a channel according to hydraulic and geometric specifications and leads to flow rate measurement, were used to develop machine learning models. To estimate the flow rate in this type of channel, models including Group Method of Data Handling (GMDH), Support Vector Machines (SVM), and Random Forest (RF) were employed. To this end, parameters such as water depth, channel width and gate width, length, thickness, and weight were considered as input variables, and flow rate as the output (response) variable for modeling. The results showed that the Root Mean Square Error (RMSE) values for GMDH-, SVM-, and RF-based models were 0.024, 0.011, and 0.041, respectively, and the Coefficient of Determination (R2) values were 0.981, 0.996, and 0.955, respectively. A comparison between past research and the present results indicated the superiority of the SVM-based model over the other developed models. Water depth to channel width was identified as the most significant input data for the developed models

 Dams, as barriers constructed across rivers, are comprised of essential components such as the body, spillway, and drainage systems. Various labyrinth spillway designs, including triangular, trapezoidal, circular, and polygonal horizontal layouts, extend the effective flow path over a fixed width compared to linear spillways. Researchers aim to identify optimal designs balancing high performance and cost-efficiency. Recent advancements highlight the integration of optimization methods and computational fluid dynamics (CFD) to improve labyrinth spillway designs. Studies have explored the hydraulic and geometric factors affecting discharge coefficients (Cd) and flow velocity. Research includes the application of artificial intelligence (AI) models such as artificial neural networks (ANNs), adaptive neuro-fuzzy inference systems (ANFIS), and regression techniques to predict Cd. Notable contributions demonstrate that AI models effectively capture complex nonlinear relationships between geometric parameters and flow rates, outperforming traditional methods. For instance, models like support vector machines (SVM) and adaptive regression spline (MARS) have demonstrated high accuracy in predicting Cd.Despite advancements, precise predictive models for labyrinth spillways with harmonic plans remain underdeveloped. This study addresses this gap by introducing new methodologies, including SVM, random forests (RF), and MARS, to predict Cd. It also quantifies the influence of dimensionless parameters on Cd, synthesizing experimental data to enhance understanding and bridge existing research gaps.

  In this study, soft computing models were developed using experimental results from Arham Namazi and Mozaffari (2023) and Yıldız et al. (2024). To evaluate the accuracy of proposed soft computing equations in estimating the discharge coefficient (Cd) for circular labyrinth weirs arranged harmonically in open channels, the following experimental data were utilized: Yıldız et al. (2024): conducted 215 experiments for weirs with three different heights (P = 20 cm, P = 30 cm, and P = 40 cm) and threedifferent cycle numbers (N = 2, N = 3, and N = 4). Arham Namazi and Mozaffari (2023): performed 18 experiments with a fixed weir height (P = 15 cm) configured as a single cycle (N = 1).In total, 233 experimental results were collected for soft computing-based modeling. Among these, 175 samples (75%) were used for model training, and 58 samples (25%) were allocated for testing the developed models.

 Violin plots for both measured and predicted data inferred by various machine learning models are presented. Violin plots are typically used to compare the distribution of data across different groups in terms of their shape. Additionally, a small box plot is embedded within each violin plot, where the ends of the rectangle represent the first and third quartiles, and the central point denotes the median. it can be observed that all three models—RF, SVM, and MARS—predict similar first and third quartiles and medians, compared to the measured data. In contrast, the first or third quartiles in the equations proposed by Arham Namazi and Mozaffari (2023) and Equation 18 show significant deviations from the measured values. Furthermore, from the perspective of the overall data distribution, the SVM and MARS algorithms demonstrate distributions more similar to the measured data compared to the RF algorithm. This highlights the superior predictive capability of the support vector machine (SVM) approach.

  Labyrinth weirs are consistently proposed as an effective solution for enhancing flood discharge efficiency, particularly in cases where space for weir construction is limited. These weirs have a longer crest length compared to linear weirs, allowingfloodsto pass at shallower depths. Due to the complex relationship between the discharge coefficient and its associated parameters, empirical equations often fail to predict the discharge coefficient with acceptable accuracy.In this study, three different machine learning models were developed to predict the discharge coefficient of semicircular labyrinth weirs with harmonic designs. The results confirm the advantages of the Support Vector Machine (SVM) algorithm. Key findings of the study are summarized as follows:Parameter Sensitivity Analysis: To minimize prediction errors in the machine learning models, a sensitivity analysis was conducted to identify the relative head is importance of different input parameters. Based on this analysis, five input combinations were designed and applied to the machine learning models.Optimal Input Combination: Statistical comparisons between predicted and experimental data revealed that the optimal input combination effectively predicted the discharge coefficient for this type of weir.Model Performance: Using the best input combination, the results showed that the SVM and MARS algorithms outperformed tree-based models, such as Random Forest (RF), in prediction accuracy for harmonic weirs with varying cycles.MARS Model Evaluation: Although the MARS model performed well, comparisons with other regression models from previous studies demonstrated that MARS delivered satisfactory and improved accuracy over those models.

Accurate determination of sediment transport and settling rates in various hydraulic environments, such as rivers, lakes, estuaries, and bays, is of crucial importance for many aspects, including coastal morphology, navigation, water quality, pollutants, and biota. Sand particles and even finer particles can be transported in suspension in rivers, depending on the amount of energy in the flow, among other factors. In many sediment transport studies, due to the highly variable nature of suspended sediments, it is essential to use the most efficient methods and equipment possible when measuring and recording the mass concentration of suspended sediments. ADV velocimeters are used to measure instantaneous flow velocities in three directions. These instruments are easy to use and are widely used for field and laboratory research. Numerous studies have shown that the acoustic backscatter caused by flow turbidity can be a suitable alternative to direct measurement of suspended sediment concentration. The objective of this paper is to investigate the structure of sediment-laden flows in a laboratory flume, with a focus on examining the velocity and concentration profiles using an ADV velocimeter. The suitability and accuracy of the ADV technique for this type of flow have been investigated in previous research, but the effect of meander curvature on the hydraulic characteristics of sediment-laden flow is the focus of this study.

The experiments for this study were conducted in a flume with a total length of 5.8 meters, a depth of 70 centimeters, a width of 20 centimeters, and a bed slope of 0.001, with three consecutive 90-degree bends with radii of curvature of 40, 80, and 120 centimeters in the Physical and Hydraulic Modeling Laboratory of the Faculty of Water and Environmental Engineering at Shahid Chamran University of Ahvaz. To conduct the experiments, salt and kaolin with a density of 2.63 g/cm3 and an average particle size of 4 microns were used as a non-cohesive sediment material, and a dye called coloring powder was used to create the dense fluid. The experiments were carried out at four flow rates of 0.5, 0.7, 0.9, and 1.1 liters per second and at concentrations of 8, 12, 16, and 20 g/l. The prepared dense fluid was transported from the dense fluid tank to a galvanized tank with dimensions of (100×50×125) centimeters and a constant height by a pump .the dense fluid and ambient water in the experimental channel were separated by a baffle sluice gate.By opening the gate, the dense flow was directed into the still water. To keep the still water level constant, uncontaminated water with the required flow rate was introduced into the flume from the downstream end. Since the density difference between the dense fluid and the surrounding fluid is very small, especially in laboratory-scale dense flows, it is very important to control the temperature difference between the dense fluid and the surrounding fluid so that the specific gravity difference between the dense fluid and the surrounding still fluid is only due to the muddy fluid and the temperature difference does not play a role in the creation of the dense flow. In this study, a digital thermometer was used to ensure that the temperature difference did not exceed two degrees Celsius. Concentration and velocity measurements were taken after the complete discharge of the flow head and the uniformization of the flow body. Due to the subcritical nature of the flow in all experiments and the very low velocity of the dense flow, after passing each bend and entering the straight path, the maximum flow velocity returns to the center of the channel and the effect of the previous bend is eliminated; therefore, the short distance between the bends will not interfere with the experiment.

Sediment-laden flows can follow either straight or meandering paths in their movement through rivers or reservoirs. In this study, the behavior of saline dense flow in a flume with three consecutive bends with relative curvatures of 2, 4, and 6, a total length of 5.8 meters, a depth of 70 centimeters, and a width of 20 centimeters was investigated. An acoustic Doppler velocimeter (ADV) was used to measure flow velocity. This device measures water velocity based on the Doppler phenomenon. It also has the ability to measure flow concentration based on the magnitude of the returned pulse intensity. The results show that for all experiments, up to a concentration limit of 15 g/L, the ADV velocimeter can be used to measure the concentration profile pointwise. The steeper the curvature of the meandering path, the more linear the relationship between backscatter signal intensity and concentration becomes. Based on the results obtained, the effect of increasing curvature on the vertical profile of dense flow velocity at the end of the bend shows that the velocity:- in the R/B=4 bend has increased by an average of 15% compared to the velocity in the R/B=2 bend, and- in the R/B=6 bend has increased by an average of 40% compared to the velocity in the R/B=2 bend.- For Froude numbers of dense flows in the range of 0.55 to 2.1, the direction of secondary flow in the downstream of each bend will be normal, similar to open channels. However, with increasing Froude number above 2.1, the direction of secondary flow will reverse.

Turbidity currents, or dense flows, occurs when a fluid moves within another fluid with different densities, also Turbidity Current occurs when a fluid with a higher or lower density than the ambient fluid enters a fluid with a different density. The main cause of this phenomenon is the effect of the difference in density on gravitational acceleration; hence, Turbidity Currents are also referred to as gravitational flows (Graf & Altinakar, 2003). Karamichemeh (2014) investigated the effect of slope and concentration on turbulent flows in the submerged region along a straight path. To achieve this, they conducted 60 experiments with four discharge rates ranging from 5.0 to 2.0 liters per second, four concentrations with volumetric mass of 1013, 1009, 1006, and 1016 kilograms per cubic meter, and three slopes of 8, 12, and 16 percent. The results of this study showed that with an increase in the Richardson number (inverse of the square root of the densimetric Froude number), the intensity of mixing decreases. Additionally, the intensity of mixing in the submerged region is greater compared to the intensity of mixing in the body region. Given the limited studies on the movement of Turbidity currents in curved paths, the aim of this research is to investigate the effect of bends on the Water Entrainment in the plunging region.