جستجوی مقالات مرتبط با کلیدواژه « الگوریتم ژنتیک » در نشریات گروه « مهندسی آب »

Paying attention to the conservation of water resources in order to prevent water crises is one of the most important duties of people in the community, including officials. In this regard, the most effective action is water demand management, for which there are different methods. One of these methods is pressure management in order to demand management, which can be used in normal operating conditions as well as in the event of water scarcity. On the other hand, in critical situations where the available water does not meet the total demand, policies such as intermittent water supply are adopted, which are associated with many problems. Therefore, an alternative method is needed to minimize the disadvantages of intermittent water supply,to meet the objectives of demand management and, at the same time is feasible, efficient, and economical. In this research, a combined simulation and optimization model is created by using EPANET2.2 and MATLAB software. With this model, the effects of adopting a water demand management approach using pressure management on the hydraulics of water distribution networks will be investigated. In this research, optimization is done in two approaches. In each case, a different objective function is defined and a genetic algorithm is used for optimization. The developed model has been analyzed on the WDN of Baharestan city located in Isfahan province. The results show that the model is able to reduce the average network pressure by 8 meters by finding the optimal location and adjusting pressure for pressure-reducing valves under normal conditions. Also, during water scarcity, it is able to distribute the available water among the demand nodes considering equity and justice principles. After imposing an 8% deficit on the network, without applying for a pressure management program, 8 demand nodes experienced a shortage between 15 and 30% and 19 experienced a deficit below 5%. However, after optimizing the pressure, only 3 demand nodes experienced a shortage between 15 and 25% and 6 nodes experienced a shortage of less than 5%.

The paper demonstrates a simulation-optimization framework for enhancing the real-time flood control with gated spillways at places where no flood forecasting data is available. A multi-objective modeling scheme is presented for flood management in a gated spillway in which the operator may specify the priorities on floods based on their different return periods. Two different operation strategies are devised. Both of the operating strategies employ ten-stage policies, which mainly rely on the reservoir water level as the input data. The second strategy benefits from both observed reservoir water level and flood peak. The optimal values of the models parameters are obtained using genetic algorithm. This is a novel approach because none of its policies needs flood forecasting data, thus, making them adaptable to any flood with any return period. To evaluate the performances of the proposed models, the flood control through gated spillway of Karkheh reservoir is considered where flood hydrographs with different return periods are routed through the reservoir.

The sewage pumping station (SPS) serves as the most important structure for the sewage disposal system. The acceptable performances of SPS for reliable design and optimal energy consumption under uncertainties are of great importance for the transformation of wastewater. At a sewage pumping plant, pumps are commonly used on various lines to provide additional head to transport domestic and non-domestic sewage out of towns and villages or to the entrances of treatment plants. Today, the issue of energy management and consumption efficiency is one of the major challenges in water resources and wastewater treatment systems. This dissertation focuses on the planning of sewage pumping energy optimization, which is subject to changes in the rotational speed of the pump and the frequent pattern of inlet flow rate and, the energy consumption of pumping system of Zabol Wastewater treatment plants (WWTPs) was determined and compared using constant speed and optimal speed of pumping rotation. Several models as machine learning approaches were developed to approximate the efficiency of the pumping system in multi-objective optimization approaches (Gao et al., 2012; Marques et al., 2015; Puleo et al., 2014; Wu et al., 2013). It is shown by results from Refs. (Castellet-Viciano et al., 2018; Guo et al., 2014; Molinos-Senante et al., 2013; Pannirselvam and Gopalakrishnan, 2015) that machine learning approaches have high-ability for accurate approximation of energy cost for wastewater treatment. The artificial neural network (ANN) was utilized to estimate the energy efficiency and flow rate for optimization of pumping station (Achieng, 2019; Jamieson et al., 2007; Rao and Alvarruiz, 2007). Using ANN, Rao, and Alvarruiz, 2007 (Rao and Alvarruiz, 2007) approximated the hydrostatic pressures, tank-storage water levels, flow rate, and energy consumption for pumping networks. There conducted that the ANN was reduced the computational burdens about 10-time compared to conventional methods. Using input variables of demand conditions, control settings, and initial starting conditions, Jamieson, 2007 (Jamieson et al., 2007) applied ANN for predictions of storage levels, hydrostatic pressures, and flow rates. Torregrossa et al., 2018 (Torregrossa et al., 2018) simulated the energy consumption using ANN for the pumping station of wastewater and concluded that the ANN was performed with highaccuracy compared to the mathematical relations. For simulating the pumping systems, artificial intelligence techniques are useful tools to reduce computational burdens.optimized the energy of the pumping system using three performance strategies including i) minimizing power consumption, ii) balancing the flow rate, and iii) maximizing efficiency pumping system. Thus, the optimum condition for pumps, which can be determined based on soft computing approach using energy consumption, can be used to approximate the failure modes of SPS in reliability analysis. Therefore, variable speed control was determined for a single-pump pumping station and the optimal rotation speed of the pump was determined using a hybrid optimization model, based on the pump on/off sequence. Then, a machine learning process based on the combined reliability method was developed to estimate the probability of pump failure under the multi-probability performance function and based on the optimal energy conditions of the pumping system. Hourly data measured at Zabol pumping station was generated using the Monte Carlo method based on a probabilistic model in minutes. Comparison of coefficient of determination (R2) of real and computational data showed that the probabilistic normal log model in both Zabol plant of 0.98. In the next step, using the genetic algorithm, the optimal values of the variables of flow rate, load, and power of the pump and thus the efficiency of the pump were calculated. The efficiency resulted from the optimal rotation and the constant rotation for both Zabul stations was 0.86, .In the next step, using the neural network (ANN) model pump rotation speed is simulated based on input variables including pumping flow rate, inlet flow rate, and static height and pumping height. The results showed the accuracy of the models in simulating the pump rotation speed. The value of R2 at the Zabul pumping plant changed from 0.97 to 1 for the ANN method.

A properly monitoring well network can provide quantity and quality data needed to make informed decision making about the state of the environment. The selection of the optimum number of monitoring wells and their spatial distribution is a major challenge for the hydrogeologist. On the other hand, improper distribution of monitoring wells or an insufficient number of them does not properly represent the state of the environment. In this study, the current monitoring network in the study area was evaluated according to the simulation results of MODFLOW and MT3D models. Then, the monitoring network was designed based on the wells in the area with the optimization method developed in this study. The optimization model consists of two objective functions to maximize the Nash Sutcliffe coefficient and to minimize the costs simultaneously, which was defined as one target function by applying the weighting factor W. Genetic algorithm was used to solve the optimization model. The results showed that the finding of the optimal value depends on the value of the weight coefficient (W). Therefore, the best value of W is selected according to an acceptable trade-off between cost and spatial distribution of wells in the area. To choose the best solution, PBIAS, RMSE, and regression coefficients were used in which their values were acceptable in this study. Also, the higher the average optimal TDS values than the average observed TDS values indicated that the optimal network could provide groundwater quality data for more polluted areas. The method presented in this study for other pollutants should be evaluated and validated.

Due to population growth, shortage and severe limitation of water resources, one of the basic steps in water management and planning is reservoir optimization. In the present study, after the introduction of the Gray Wolf optimization algorithm, the performance of this algorithm alone and in combination with the genetic algorithm in optimizing the operation of the Taleghan Dam reservoir has been evaluated. The objective function is to minimize the total squares of relative deficiencies in allocating to it each month and maximize reliability throughout the 11-year transition period from 2009 to 2017. Also, the constraints of reservoir continuity equation, reservoir storage volume and reservoir release volume were applied to the objective function of the problem. The results obtained from the performance evaluation indices of the models showed that in terms of time reliability, vulnerability and sustainability indices, the gray wolf-genetic hybrid algorithm with 72.73, 0.28, 24.66 is better than the gray wolf algorithm with 68.93, 0.29, 21.48 and the algorithm. Genetics with 66.66, 0.41, 21.34.

In this study, daily simulation models of pan evaporation were developed using a multilayer perceptron neural network, a radial basis function, and an optimized experimental relationship based on the genetic algorithm with 13 input combinations of climate variables, i.e., average daily temperature, maximum and minimum temperature, relative humidity, sunshine hours and wind speed. These models were applied to simulate evaporation in Semnan, Shahrud, and Rasht stations with dry, semi-dry, and very wet climatic conditions, respectively. The best input combination for simulation models was selected based on the quantitative evaluation results; i.e temperature, relative humidity, sunshine, and wind speed which had a correlation coefficient between 0.56 to 0.85, root mean square error between 1.1 to 2.6 mm, and the PBIS coefficient between 1 to 29.5%. The results of the developed models' sensitivity analysis showed that temperature and then relative humidity are sensitive parameters for evaporation simulation. The optimized experimental relationship with the best input combination among the evaporation simulation models had a greater ability to simulate the mean ​​and standard deviation of evaporation, and the model was selected as the best model. Finally, the ability of the best model with the best input combination was confirmed by its application to simulate the evaporation pan in three stations Garmsar (dry), Damghan (semi-dry), and Ramsar (very wet), resulted in correlation coefficients of 0.6 to 0.84, root mean square errors of 1.29 to 3.16 mm and PBIS coefficients of 2.1 to 9.2%.

Contamination of drinking water is known as a major threat of water security around the world. As contamination enters a water distribution network, it spreads rapidly into the network and poses health and safety risks to the community. Using a set of sensors to report the concentration of chlorine or any other chemical, useful observations can be made to detect, identify and manage pollution. Based on these observations, location, concentration and start time of contamination can be determined and decision makers can be informed. In this paper, a simulation-optimization approach is used to solve the problem of contamination source characterization in which the EPANET software is used as a simulator and the Genetic Algorithm is used as an optimizer. The model developed in this paper is implemented on EPANET example 3. Modeling of water distribution networks uses information as input data which can cause error in model simulation. Pipe roughness and chlorine deterioration rate are among these inputs. The model has been implemented to find the location, start time and concentration of inlet pollution and the effect of pipe roughness and chlorine deterioration rate on the model responses have been investigated. The pollution entry scenario is applied to the network and the model presented is accurate in finding the location and time of the contamination. As the variables increase, the model accurately estimates the location and time of entry of the contamination but does not have complete accuracy in estimating the concentration of contamination, which is calculated with standard deviation of σ = 4.8% -8.1%.

Unplanned operation and excessive extraction of groundwater in coastal areas increases the risk of seawater intrusion; so water quality monitoring and management in these areas are of great importance. In this study, an optimal monitoring network with minimum number of wells in Talesh coastal aquifer is designed according to the aquifer vulnerability map and evaluation of the accuracy of monitoring network. In this regard, the aquifer vulnerability map was prepared using the modified DRASTIC index; and genetic algorithm was used to optimize the monitoring network. Three objectives were used in the optimization model including (1) maximizing the correlation between vulnerability index and EC values, (2) minimizing the number of monitoring wells, and (3) maximizing the Nash-Sutcliffe (NS) efficiency. NS, represented the match between the calculated EC distribution obtained from existing monitoring wells and those wells from the newly generated network. Applying the weighting factor w for economic objective, the three above-mentioned objectives are integrated in a single objective function and different weights of w were evaluated. The results showed that the selection of an optimal solution greatly depends on the weighting coefficient w and the best weight was selected according to the vulnerability index and the accuracy of monitoring network. Due to long-term quantitative and qualitative changes in groundwater, it is better to periodically evaluate and redesign groundwater quality monitoring network so that the network could effectively use in planning and applying methods to improve groundwater quality.

Accurate spatial estimation of precipitation plays a key role in many hydrological modelling, water resources planning and agricultural management studies. In order to estimate high-resolution precipitation in the current research, an estimation model based on PRISM framework considering Digital Elevation Model (DEM) and other spatial attributes is developed and applied to Sefidroud basin during the years 2000-2015. In the first step, the monthly results were compared with modified Inverse Distance Weighted (IDW) as a benchmark method. Considering both models’ degrees of freedom, the parameters are calibrated with Genetic Algorithm in annual time scale and the obtained parameters are utilized to estimate model monthly cross validation error. According to the monthly results, both models had roughly same statistical performance in estimating precipitation at the selected rain gauges. In spite of similar statistical performance of the models, the spatial distribution of precipitation provided by the PRISM based method is more consistent with topographic pattern and existing evidences. In the next step the proposed model’s ability to estimate mean monthly precipitation is compared with ordinary kriging method and according to the results, in wet months the developed model and in dry months kriging method represents more optimal results. According to small amount of summer precipitation, PRISM based approach is considered to be a better tool for spatial interpolation of precipitation than kriging.

Leakage in water distribution networks will cause waste of water and reduced pressure. Different leak detection methods are used in the networks among which the Meta-search algorithms have received much attention in the recent years. WaterGEMS commercial software uses genetic algorithm for optimal design and calibrate water distribution networks and detect leakage. In this paper, the WaterGEMS V8i performance in leakage detection using Darwin Calibrator tool was investigated in two hypothetical networks (Poulakis and Aniton). In the Poulakis network where only the node's pressure was put into the software as observational data, the location of leakage was determined at or in the vicinity of the exact location. However, in the Aniton network, where the input discharge was also introduced to the program as observational data, the location and the amount of the leakage were calculated more accurately. These results were similar to the leakage resulted in using the Ant colony algorithm.WaterGEMS is therefore evaluated as a good tool for engineers for estimating the location and amount of leakage in water networks.

In this study, a simulation-optimization model is used for multi-period consequence management of sudden contamination in urban water distribution network. The tools used in the management of consequences in this study are to discharge contaminated water by hydrants, to cut or plug the pipes to control the flow path in the network or to isolate the different areas, as well as to switch the pumps on or off to regulate the water flows pressure into the network. EPANET software is used for simulation and single-objective genetic algorithm is used for optimization. In this study, the three objective functions are to minimize system return time to normal situation, minimize the mass of contamination consumed, and minimize the number of infected nodes. Each of the objective functions mentioned is executed for two different management scenarios. In the first scenario, the status of the hydrants, valves and pumps is constant from the beginning to the end of the management period. In the latter scenario, the status of the hydrants, valves and pumps can be changed periodically from the beginning to the end of the management period. The number of decision variables in this study was 54, which included determining whether the hydrants were open or closed, whether the pipes were closed or connected, and whether the pumps were on or off. The contamination loading is injected from the three candidate nodes into the network. The results show that alternating situations of hydrants, valves and pumps, compared to the situation where the hydrants, valves and pumps are in constant condition, decreases the return time to a normal state between 13 and 26.5 percent, the amount of contaminated water consumed between 12 and 20 percent and the number of infected nodes between 6 and 21 percent. It should be noted that in all scenarios, the minimum water pressure at the nodes of the network is controlled from the minimum permissible value and the increase in the number of management responses actions is controlled from the maximum permissible value. The alternation of the opening and closing of the hydrants and valves, as well as the switching of the pumps on or off, helps to improve the target functions to an acceptable extent.

Water distribution networks are amongst the most important infrastructures of water supply projects, which attracts notable financial credits from the governments. As optimal design can significantly reduce the costs of such large projects, designers always try to minimize the costs while applying all the constraints and technical specifications of the project. Genetic algorithm is one of the most popular approaches for optimizations in the design projects. This research aims at evaluating the meta-heuristic methods used in designing the urban water distribution networks and to assess the genetic algorithm as an optimization mean for such methods. Given the heavy costs associated with water distribution network projects, it is very important how a model perform the cost evaluation. For the current study, the modeling was first performed by WaterGEMS software and the total cost was calculated based on the price list. Then, according to the objective function and cost criterion and with respect to constraints of speed and pressure in the network, optimization was performed and the final cost was obtained. The results of the proposed method showed that by optimization, the investment cost would decrease by about 14% compared to the original plan. Comparison was also made to other meta-heuristic algorithms which confirmed better performance of the proposed algorithm with regards to costs.

Water distribution networks (WDNs) are complicated infrastructures which their construction, operation and maintenance have considerable costs. Since most of the variables effective on the design and operation of WDNs cannot be computed and achieved accurately and definitely, uncertainty subject should be considered as an inseparable issue in the calculation of these networks. In this study, using the fuzzy logic concept and genetic optimization algorithm, the impact of uncertainties of input variables (nodal demands and pipe roughness coefficients) on the results of hydraulic analysis of two sample networks have been examined. In this regard, first, the fuzzy membership functions of input variables have been determined and by considering the simultaneous impacts of these variables' uncertainties, the output variables of hydraulic analysis have been calculated more accurately. Afterwards, variables of pressure, velocity and energy loss have been considered as representers for evaluating the hydraulic performance of network elements (nodal demand and pipes). In order to calculate the hydraulic performance indices of these elements, after analyzing the network based on the pressure driven simulation method, penalty curves defined according to the available standards, have been employed and the obtained results have been compared to the results of the demand driven simulation method. In addition, a new relation for combining the performance indices of network elements and obtaining an index for evaluating the total pipe performance and calculating the total hydraulic performance index of network has been introduced. According to the obtained results, slight uncertainties in the input variables of hydraulic analysis lead to high uncertainties in the outputs of the hydraulic analysis of WDNs. Meanwhile, velocity in pipes more than nodal pressures are affected by the uncertainties of input variables of hydraulic analysis. Also, implementing the pressure driven simulation method in performance evaluation of WDNs in their operation period leads to more reasonable and real results. For instance the total performance of network was 0.56 for 9-loop network and was 0.26 and 0.59 for 2-loop network, respectively, based on demand and pressure driven simulation methods.

In this research, a deterministic algorithm based on the Genetic Optimization (GA) method was used to optimal water allocation from surface and underground resources between different uses in the operation of Yamchi reservoir dam in Ardabil province. The objective function in the optimized model was to maximize the profit of water allocated to the agricultural sector according to the selected cropping pattern, so that the supply of drinking and environmental requirements was considered as a constraint in the optimal model. The rainfall and inflow to the reservoir are discretized due to their non-deterministic property, and then for different values of the initial volume of the reservoir at the beginning of the operation period and any logical combination of rainfall and inflow to the reservoir (under the three scenario: minimum, normal and maximum), the optimal model was implemented. The results showed that in the minimal and normal scenario with increasing initial volume of the reservoir, the profit was increased, but in maximum scenario, the initial volume of the reservoir had no effect on the profit. The smaller the initial volume of the reservoir had the lower the relative yield of the products, which is most evident in the minimum scenario. Also, the amount of water allocated from groundwater resources to agricultural sector varies from 3.1 to 7.9 MCM, which corresponds to the potential for extracting water through utilization wells.

Sustainable management of water resources in various basins depends on accurate estimation of water balance. Reviewing literature of water balance models reveals that most published works are focused on hydro-climatologic water balance models, which consider aquifers like tanks with one or two soil layers. These models use empirical equations to calculate the effects of groundwater on hydro-climatological water balance. In this study, we have tried to advance previous studies by linking previously developed hydro-climatological and groundwater balance models. In the developed model in this study, the aquifers were modeled more accurately by using the tank-model approach. Optimizaing the parameters of the joint water balance model is an important step for achieving proper water balance model performance. In order to assess the performance of the recommended model, hydro-climatological and groundwater water balance in Neyshabur and Rokh plains were modeled in a nine-year period. The results proved that the proposed approach can be used for modeling water balance of other basins in the country. Although it was suggested that it can be better to use distributed modeling which allows considering interactions between surface water and groundwater resources.

Human societies nowadays undergo huge expenses to meet the water requirements aiming at maximizing the benefits and minimizing the costs. The goal of reduced costs can substantially be met by reduction in the cost of network pipes while satisfying the minimum pressure at nodes; i.e. 14 meters. This study is a multi-objective optimization function that will be constructed in a part of the water distribution network of the Homashahr city in Kerman province. In optimization of water distribution network, in addition to financial problems, other aspects should also be noted such as pressure and velocity of water in pipes which play key role in network design. In this study, the pressure was considered as a second objective function and the velocity was set as a boundary condition. When the objective function is defined only on the basis of cost, the network can face inadequate pressure in consumers’ connections. In this study “WaterGems” software is used for hydraulic simulation and also optimization process based on genetic algorithm. Based on the two objective functions defined in terms of cost reduction and improved network pressure, a scenario with suitable condition was derived. This scenario caused 15% reduction in total costs of the project.

Land subsidence is often triggered by over abstraction of groundwater due to increased demands from agriculture, industry and domestic uses. This problem is investigated for Shabestar plain formulating a framework to estimate subsidence potentials and the outcome is compared with measured values of them with the lowest threshold value of 30 cm. The research puts together seven hydrogeological and geological factors affecting land subsidence, which comprise groundwater level decline, aquifer media, recharge, groundwater withdrawal, land use, aquifer thickness and fault distance. Although the framework results are acceptable, Genetic Algorithm (GA) was used to optimize weights and to improve the correlation between calculated indices and their corresponding measured subsidence values. Results confirm the improvement and show further that the southern and southeastern areas in Shabestar plain have most subsidence potentials. As such management plans are essential to meet the local demands and yet to protect land against subsidence and other adverse impacts.

Optimization and modeling of the pressurized irrigation system in other to reduce their construction cost has attracted many scientists up to the present time. Optimization of these irrigation systems has often been conducted by using available commercial codes or toolbox's of conventional evolutionary algorithms combined with hydraulic models. Developed code that is based on genetic algorithm assigns an integer numeric to each available diameter. Then, by applying the cross-over, mutation and reinsertion with elitism approach on set of chromosomes optimum diameter of pipes are selected. Optimum diameters are sent to another subroutine that has been developed to simulating water hammer pressure in which maximum pressures due to water hammer phenomenon in all pipe are calculated. Then, calculated maximum pressures are sent to optimization subroutine again where constrains of working pressure are substituted by the bursting pressure constrains. Exchange of information between optimization and hammer models continues so that the calculated optimal diameters have not change. The results showed that optimized design by the present model reduces cost of implementation of pipelines of Ismailabad irrigation network from 825935.28$ to 730958.37$ which is equivalent to 11.5% of the cost of implementing of the pipelines.Also the results showed that by changing diameter of 3 pipes of 16 existing pipes we can control excess pressure of water hammer due to rapid closing of all valve at the end of pipelines during less than 1 second. In this case the cost of implementing of the pipelines increases 6.1% e.g. from 730958.37$ to 775511.5$.

In this paper a genetic algorithm method is applied for the optimal design of sewer networks. By studying the list price and the records and reports of contractors of sewer network construction, a cost function is derived. The variables in this function are the pipe diameter and the pipe slope. The results showed the capability of the presented model for the optimal design of sewer networks. Optimization of Urmia sewer network using the proposed model led to 13 percent decrease in construction cost. Among the advantages of the proposed model are considering the execution aspects and avoiding drop at pipe joints. Proposing a method for calculating rainwater, the impact of rainwater on design of sewer networks was also examined. According to the results for the case study of Urmia city, considerable discharge of rainwater (up to 10 times of sanitary sewer discharge) enters into the sewer network which is not consistent with the primary design criteria of the separate network. Considering the rainwater in design of sewer networks would lead to considerable increases in pipe sizes and network costs.