Water distribution networks are vulnerable to various contamination events that may be accidental or purposeful. Sensors are required for online monitoring of water quality to safeguard human health. Since sensors are costly, their numbers must be limited that makes sensor locations crucial in the water monitoring system. This paper aims at location of sensors in intermittent water distribution system which are more prone to accidental contamination due to contaminants ingress into the pipe lines because of low pressures during non supply hours. Considering deployment of limited number of sensors, the novelty of the paper is to propose a methodology for selection of contamination events with associated risk to be used in design of sensor network. Integrated risk assessment model is used to identify risk prone areas that may lead to possible contamination events. A Genetic Algorithm based methodology is suggested for optimal location of water quality sensors to maximize the detection likelihood of the contamination events within the acceptable time from the risk prone areas to improve network security. A comparison of sensor network design is made by considering contamination events occurring with: (i) equal probability at all the nodes; (ii) equal probability at risk prone nodes; and (iii) probability of occurrences based on quantified risk, to show that identification of risk prone areas and selection of contamination events results in reduction of computational work and more sensible placement of sensors. 相似文献
Surface water is a scarce reource that is applied by various users for a variety of activities. The regulation of surface water use is an element of regional water management at various management levels. At each management level, the allocation of surface water supply capacity is a policy instrument. An optimization model has been formulated to support the evaluation of potential allocations at a particular management level. The model describes the allocation problem as a network, in which arcs represent waterways and nodes represent inlets and locations where there is a demand for surface water supply. The use of surface water for a specific activity at a specific node is referred to as an application, for example, for sprinkling, for use as cooling water, for dissolving effluent, and for conservation of environmental areas. The optimization model generates the optimal allocation of surface water and of surface water supply capacity. The operation of the model was demonstrated by a case study, where it was applied to maximize the expected revenues in agriculture (measured as value added). 相似文献
Within the last years a trend towards in-situ monitoring can be observed, i.e. most new sensors for water quality monitoring are designed for direct installation in the medium, compact in size and use measurement principles which minimise maintenance demand. Ion-sensitive sensors (Ion-Sensitive-Electrode--ISE) are based on a well known measurement principle and recently some manufacturers have released probe types which are specially adapted for application in water quality monitoring. The function principle of ISE-sensors, their advantages, limitations and the different methods for sensor calibration are described. Experiences with ISE-sensors from applications in sewer networks, at different sampling points within wastewater treatment plants and for surface water monitoring are reported. An estimation of investment and operation costs in comparison to other sensor types is given. 相似文献
许多城市的供水管网都安装了SCADA(Supervisory Control And Data Acquisition)系统,基于SCADA系统监测到的数据可对管网泄漏进行检测。通过引进统计学概率论中一基本定理——贝叶斯定理来建立管网泄漏的在线检测与定位模型,一定程度上解决了水力模拟误差、测量误差、测点配置等因素导致的不确定性问题。模型通过实例考核取得较为满意的诊断结果。 相似文献
Traditionally, the optimal design of water distrubution networks has been dealt with using single-objective constrained approaches,
where the aim is to minimize the network investment cost while maintaining minimum pressure head constraints at all nodes.
However, in the last decade some authors have proposed multi-objective approaches which optimize other objectives than network
investment cost. In most cases, these objectives have been formulated using the concept of resilience index, which mimics
the design aim of providing excess head above the minimum allowable head at the nodes and of designing reliable loops with
practicable pipe diameters. Although several authors have proposed different resilience indexes for this pupose, to date there
is no empirical study that analyzes the advantages and disadvantages of these proposals. This paper evaluates the performance
of a well-known multi-objective evolutionary algorithm, the Strength Pareto Evolutionary Algorithm 2, using three different
resilience indexes. The results obtained in two water supply networks under a large number of simulated over-demand scenarios
show the advantages and disadvantages of these measures. 相似文献
A novel sensor partitioning placement model is presented to evenly distribute sensors to water distribution systems (WDS) for monitoring leakages and contamination. First, random walk community detection (RWCD) is used to divide WDS into different partitions. Then, an extended period leakage detection (EPLD) model is presented. The total leakage detection and the average time of leakage detection are used as objective functions for pressure sensor placement. Next, the extended period water quality detection (EPWQD) model is presented. The total intrusion detection, the average percentage of clean water, and the average time of water quality detection are used as objective functions for water quality sensor placement. Evolutionary algorithm (EA) modules are applied to optimize the locations of pressure and water quality sensors. Seven networks are employed to verify the practicability of the model. The results show that leakage and intrusion detection rate is up to 85% during 24 h, and the average percentage of clean water is up to 0.9 in these cases. Finally, the model compares the leakage zone identification (LZI) and the water quality sensor placement strategy (WQSPS) models. The total detection number, the total average time of detection, and the total average percentage of clean water have been improved. Therefore, this model is a high-potential way of sensor placement.
This paper addresses the problem of the localization of contamination sources after deliberate contaminations in drinking water distribution systems (DWDS). The proposed methodology is based on the information given by successive positive readings of sensors. Thus, it is possible to estimate the localization of the contamination sources based on only the first sensor that detected a contamination, and then update the results when more information is available. From the tests performed on a real drinking water distribution system, it was possible to observe that as new sensors detect changes in contaminant concentration, other possible contaminations may be detected and the location of contamination sources may be more restricted. The results achieved for the two set of sensors considered in the study contained the correct locations and the instants of contaminations previously simulated. Two case studies were also analysed to study the effect of the occurrence of false positives. It was concluded that it is not always possible to verify the occurrence of those anomalies and when it is verified, it is not possible to distinguish between a false positive and a false negative. The occurrence of false positives did not affect also the results related with the real detections. 相似文献
In water supply systems, the potential exists for micro-hydropower that uses the pressure excess in the networks to produce electricity. However, because urban drinking water networks are complex systems in which flows and pressure vary constantly, identification of the ideal locations for turbines is not straightforward, and assessment implies the need for simulation. In this paper, an optimization algorithm is proposed to provide a selection of optimal locations for the installation of a given number of turbines in a distribution network. A simulated annealing process was developed to optimize the location of the turbines by taking into account the hourly variation of flows throughout an average year and the consequent impact of this variation on the turbine efficiency. The optimization is achieved by considering the characteristic and efficiency curves of a turbine model for different impeller diameters as well as simulations of the annual energy production in a coupled hydraulic model. The developed algorithm was applied to the water supply system of the city Lausanne (Switzerland). This work focuses on the definition of the neighborhood of the simulated annealing process and the analysis of convergence towards the optimal solution for different restrictions and numbers of installed turbines. 相似文献
Information and communication technologies combined with in-situ sensors are increasingly being used in the management of urban drainage systems. The large amount of data collected in these systems can be used to train a data-driven soft sensor, which can supplement the physical sensor. Artificial Neural Networks have long been used for time series forecasting given their ability to recognize patterns in the data. Long Short-Term Memory (LSTM) neural networks are equipped with memory gates to help them learn time dependencies in a data series and have been proven to outperform other type of networks in predicting water levels in urban drainage systems. When used for soft sensing, neural networks typically receive antecedent observations as input, as these are good predictors of the current value. However, the antecedent observations may be missing due to transmission errors or deemed anomalous due to errors that are not easily explained. This study quantifies and compares the predictive accuracy of LSTM networks in scenarios of limited or missing antecedent observations. We applied these scenarios to an 11-month observation series from a combined sewer overflow chamber in Copenhagen, Denmark. We observed that i) LSTM predictions generally displayed large variability across training runs, which may be reduced by improving the selection of hyperparameters (non-trainable parameters); ii) when the most recent observations were known, adding information on the past did not improve the prediction accuracy; iii) when gaps were introduced in the antecedent water depth observations, LSTM networks were capable of compensating for the missing information with the other available input features (time of the day and rainfall intensity); iv) LSTM networks trained without antecedent water depth observations yielded larger prediction errors, but still comparable with other scenarios and captured both dry and wet weather behaviors. Therefore, we concluded that LSTM neural network may be trained to act as soft sensors in urban drainage systems even when observations from the physical sensors are missing. 相似文献