Calibration Model for Water Distribution Network Using Pressures Estimated by Artificial Neural Networks (original) (raw)
Related papers
Journal of Hydroinformatics
The development of computational models for analysis of the operation of water supply systems requires the calibration of pipes' roughness, among other parameters. Inadequate values of this parameter can result in inaccurate solutions, compromising the applicability of the model as a decision-making tool. This paper presents a metamodel to estimate the pressure at all nodes of a distribution network based on artificial neural networks (ANNs), using a set of field data obtained from strategically located pressure sensors. This approach aims to increase the available pressure data, reducing the degree of freedom of the calibration problem. The proposed model uses the inlet flow of the district metering area and pressure data monitored in some nodes, as input data to the ANN, obtaining as output, the pressure values for nodes that were not monitored. Two case studies of real networks are presented to validate the efficiency and accuracy of the method. The results ratify the efficie...
In this paper, a novel multiobjective optimization model is presented for selecting optimal locations in the water distribution network (WDN) with the aim of installing pressure loggers. The pressure data collected at optimal locations will be used later on in the calibration of the proposed WDN model. Objective functions consist of maximization of calibrated model prediction accuracy and minimization of the total cost for sampling design. In order to decrease the model run time, an optimization model has been developed using multiobjective genetic algorithm and adaptive neural network (MOGAANN). Neural networks (NNs) are initially trained after a number of initial GA generations and periodically retrained and updated after generation of a specified number of full model-analyzed solutions. Trained NNs are replaced with the fitness evaluation of some chromosomes within the GA progress. Using cache prevents objective function evaluation of repetitive chromosomes within GA. Optimal sol...
Calibration Procedure for Water Distribution Systems: Comparison among Hydraulic Models
Water
Proper hydraulic simulation models, which are fundamental to analyse a water distribution system, require a calibration procedure. This paper proposes a multi-objective procedure to calibrate water demands and pipe roughness distribution in the context of an ill-posed problem, where the number of measurements is smaller than the number of variables. The proposed methodology consists of a two-steps procedure based on a genetic algorithm. Firstly, several runs of the calibrator are performed and the corresponding pressure and flow-rates values are averaged to overcome the non-uniqueness of the solutions problem. Secondly, the final calibrated model is achieved using the calibrator with the average values of the previous step as the reference condition. Therefore, the procedure enables to obtain physically based hydraulic parameters. Moreover, several hydraulic models are investigated to assess their performance on this optimisation procedure. The considered models are based either on ...
The objective of the study was to model and analyze three drinking water distribution networks, calibrate them with Epanet Calibrator software and compare their results with Darwin Calibrator. An ultrasonic flowmeter and pressure data loggers were used, which were configured to record data every ten minutes, the mean of the flows at each node of interest in the network was obtained. The pressure data was used to adjust each network and by varying the roughness, the model could be calibrated and adjusted, among those mathematically simulated with the data obtained in the field. Using this information, equations and calibration curves were established to discriminate the discrepancy between what was modeled and what was observed in the field. Hydraulic calibrations were performed using the Darcy-Weisbach and Hazen-Williams formulas. The results show for each network a variation in the calibrations of 35, 15 and 10 %. It is concluded that these two computational applications show similar results between the simulated and observed data, with the difference that calibration in Epanet is carried out node by node, while in Darwin Calibrator it can be performed by means of groups of calibrations in a given sector.
Water distribution network’s modeling and calibration. A case study based on scarce inventory data
This paper focuses on modeling and calibration of a small and poorly documented (portion of the) water distribution network (WDN) that shows pressure problems. Field campaigns are conducted to reduce the inaccuracies found in the inventory’s drawings and to aid building a first WDN model. A trial and error procedure was then used to produce successive refinements for the desirable WDN’s model fit. The paper describes the path followed through the first model to the final calibrated model, including WDN’s instrumentation, the definition of network zones and the measures taken to deal with the pressure problems
Hydraulic calibration of water distribution network s based on ACO algorithms
2013
The aim of this paper is to investigate a new metho d f r hydraulic calibration of water distribution networks with nodal pressure and pipe flow sampling. In this regard an aggregate of an EPANET simulator model and an Ant Colony Optimiz ation (ACO) algorithm has been used in a MATLAB setting. Generally in the ACO algorithm , the concentration of pheromone and heuristic factor was performed an important role in convergence of calibration model to the global optimal solution. In old models, the global optimal solution was reached with updating the pheromone using the best ant. In this paper, th objective function of the model specifically was defined that one part of it can be used to upda te the pheromone and the other part can be used to update the heuristic factor. So those toget her converged the model to the global optimal solution. The findings of this study showed that th e new ACO algorithm method can lead to the global optimal solution with lesser evaluation than the old ACO...
Calibration Of The Water Distribution Network Model
WIT Transactions on Ecology and the Environment, 1970
As a rule models for water distribution systems have to be calibrated for better reflection of the behaviour of the real system. As the first step of calibration the distribution of water losses due to leakage must be studied. Two approaches are proposed in order to calculate the leakage from pipes. The first of them uses an empirical formula which takes into account the length of pipe and mean pressure. This leakage is carried to the terminal nodes and distributed between the nodes proportionally to the pressure in the nodes. For evaluation of pressure in the nodes an iteration process is applied which determines the leakage and pressures intermittently. The second approach uses differences between the measured and calculated pressures. Areas with underestimated and overestimated pressure have been selected and coefficients for the correction of the leakage for these areas calculated. Calculated results for the water distribution network of the City Centre of Tallinn are presented, demonstrating the applicability of the above methods.
Procedia Engineering, 2014
Pressure determination in water distribution systems (WDS) is important because it generally drives the operational actions for leakage and failure management, backwater intrusion and demand control. This determination would ideally be done through pressure monitoring at every junction in the distribution system. However, due to limited resources, it is only possible to monitor at a limited number of nodes. To this end, this work explores the use of an Artificial Neural Network (ANN) to estimate pressure distributions in a WDS using the available data at the monitoring nodes as inputs. The optimal subset of monitoring nodes are chosen through an entropy-based method. Finally, pressure values are compared to synthetic pressure measures estimated through a hydraulic model.
CALIBRATION OF A WATER DISTRIBUTION SYSTEM – A CASE STUDY
Water is the foundation of life. Water Distribution System (WDS) plays a critical role in transporting water to various destinations. Today, a WDS consists of infrastructure that collects, treats, stores, an and consumers. A WDS should be properly designed and maintained. But, it is commonly seen that after construction WDS are not properly maintained. A well designed and maintained WDS helps to function it smoothly. C of utmost importance for the purpose of evaluating a system. It will help authorities to better understand the system and its problems. This will highlight future capital investment programmes so that the authorities may better serve This paper focuses on modeling and calibration of a typical WDS in a Metropolitan area in a well developed country using sophisticated software ArcGIS and InfoWater. The comparisons of the model results (pressure, flow and reservoir levels) with the recorded observations (pressure, flow and reservoir levels) indicated that good calibration was achieved. The performance evaluation of the water supply zone was also done which was found to be satisfactory. Water is the foundation of life. Water Distribution System (WDS) plays a critical role in transporting water to various destinations. Today, a WDS consists of infrastructure that collects, treats, stores, and distributes water between water sources and consumers. A WDS should be properly designed and maintained. But, it is commonly seen that after construction WDS are not properly maintained. A well designed and maintained WDS helps to function it smoothly. Calibration of a WDS is of utmost importance for the purpose of evaluating a system. It will help authorities to better understand the system and its problems. This will highlight future capital investment programmes so that the authorities may better serve the customers. This paper focuses on modeling and calibration of a typical WDS in a Metropolitan area in a well developed country using sophisticated software ArcGIS and InfoWater. The comparisons of the model results (pressure, flow and reservoir with the recorded observations (pressure, flow and reservoir levels) indicated that good calibration was achieved. The performance evaluation of the water supply zone was also done which was found to be satisfactory. Water is the foundation of life. Water Distribution System (WDS) plays a critical role in transporting water to various destinations. Today, a WDS consists of d distributes water between water sources and consumers. A WDS should be properly designed and maintained. But, it is commonly seen that after construction WDS are not properly maintained. A well alibration of a WDS is of utmost importance for the purpose of evaluating a system. It will help authorities to better understand the system and its problems. This will highlight future capital the customers. This paper focuses on modeling and calibration of a typical WDS in a Metropolitan area in a well developed country using sophisticated software ArcGIS and InfoWater. The comparisons of the model results (pressure, flow and reservoir with the recorded observations (pressure, flow and reservoir levels) indicated that good calibration was achieved. The performance evaluation of the water supply