城乡统筹供水管网水质控制优化调度研究

结合实验室数据校核得出适合研究区域内的城乡统筹供水管网水质模型,基于水质模型建立并求解了余氯优化调度模型,开发了在线水质模拟和优化调度管理平台。通过水质优化调度研究,在保障管网中各节点余氯量满足国家规范要求下,相比人工氯投加量下降了20.5%;最后从工程性措施提出了乡镇管网水质改善的建议。     

基于粒子群改进FCM聚类算法优化管网压力监测点布置研究

针对供水管网运行现状,提出压力监测点优化布置方法.以构建节点压力影响系数矩阵采用粒子群优化模糊C均值聚类算法方法求解压力监测点的节点位置.粒子群算法优化避免了FCM聚类算法在初始值选取不当容易陷入局部最优的缺点,提高了压力监测点覆盖节点的精度.结果表明,压力监测点布置合理,且均匀分布于整个管网,同时提供新增压力监测点布置方法,为管网漏失识别定位奠定基础.     

给水管网水质监测模拟及评价研究

本文阐述了给水管网水质监测点的优化布置、水质模拟及评价和水质事故监控系统的设计等三方面内容,包括它们的数学模型、基本原理、求解方法和算例等。本文讨论了根据管网供水情况、水在管网中流经的路径及时间布置水质监测点的方法。如果节点ｊ的进水全部或大部分来自上游节点ｉ,并且ｉ与ｊ水质相差不大时,可以认为节点ｊ“覆盖”节点ｉ。具有最大覆盖水量的节点将成为监测点。在计算机上进行水质模拟是评估配水系统水质变化的有效方法。本文介绍了管网水质数学模型的稳态模型和准动态模型的控制方程及各自的求解方法,最后对模拟结果用水质…     

基于EM算法的树状注水管网优化设计

针对油田系统中的树状注水管网的拓扑优化问题,以最小管网造价为目标函数,以站、间、井的隶属关系惟一性及服务能力等为约束条件,建立优化数学模型。尝试利用一种新型优化算法——类电磁机制算法对模型进行求解,该方法以站、间的空间位置作为带电粒子,在若干带电粒子形成的电场中,粒子受力移动以更新管网的拓扑结构及站、间规模,实现对管网造价的优化。运用实例进行优化验证,优化后的管网造价与原管网的布局造价相比降低了15.28%,充分表明了EM算法在油田树状注水管网拓扑优化方面的有效性。     

自压式树状管网神经网络优化设计

应用Hopfield神经网络模型的优化计算原理与方法, 建立了自压式树状管网神经网络优化设计模型, 并用计算机软件模拟方法求解. 研究表明: 人工神经网络法是快速求解自压式树状管网非线性规划模型的一种新方法, 结合两级优化算法可以实现树状管网全局最优设计.     

供水管网校核模型参数估计与求解方法的研究

研究和分析了在建立管网模型以及随后进行校核中主要考虑的重要参数海澄-威廉阻力系数C值和节点流量q值,对于其初始值的获取提供了一种切实可行的办法。随后建立了管网校核模型及其约束条件,并对如何求解该模型进行了研究。对于目前众多的校核模型求解算法,结合混沌优化算法(Chaos optimal algorithm)、遗传算法(GA)和DFP变尺度算法的优点,形成一种CGA DFP混合优化算法,并将其引入管网模型校核中,经实际管网试算取得了较好的效果。     

供水管网压力监测点优化布置方法

提出了一种供水管网压力监测点的优化布置方法.该方法的优化条件为节点重要度最大化,节点重要度基于熵权法由节点覆盖数量和节点水力灵敏度两个指标计算得出.约束条件为限定压力监测点与被监测节点之间压力相关性的最小值,及限定不同压力监测点覆盖相同节点数量的最大值.将该方法应用于某实际管网,完成了管网节点被一个及两个压力监测点覆盖...     

供水管网水质监测点综合优化布置研究

监测供水管网的水质状况,提高供水水质的安全性是一个复杂而又亟待解决的课题.在基于污染预警监测的优化监测点布置中,加入节点水龄数据集约束,将两个目标综合优化,实现了常规监测意义下的污染灾害预警监控.通过小规模管网实际验证,证明了该方法的合理性和有效性.     

浅析基于传递闭包法对供水管网压力监测点的布置

近年来,供水管网泄漏事故频发,导致大量水资源浪费.管网监测成了控制泄漏的重要手段,其中,管网压力是管网监控的重要数据之一.基于EPANET对管网进行泄漏模拟,通过MATLAB建立压力模糊矩阵,采用模糊聚类中传递闭包的算法,对管网节点进行聚类,并以可靠性和经济性为目标,选择出最合适的压力监测点.该方法简单有效,可为压力监...     

基于系统分析理论给水管网水质模型的建立

提出了一种基于系统分析理论的管网水质分析方法,建立了管网中任意两节点的水质模型.把两节点的水质变化视为系统的输入激励和输出响应,在线性时不变系统的假定下,通过对时域下历史数据的变换和训练,得到频域下的系统函数,建立两节点的水质关系.通过对南方某区域余氯在线监测数据的分析模拟进行验证,结果表明:本模型模拟结果能反映水质变化趋势,模拟误差在实际工程可接受范围内;模型模拟预测具有较好的外延性;模型可对短时间的水质变化进行模拟.     

Risk Based Analysis for Contamination Event Selection and Optimal Sensor Placement for Intermittent Water Distribution Network Security

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.     

Optimal allocation of surface water in regional water management

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).     

Application of ion-sensitive sensors in water quality monitoring.

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.     

面向水环境的传感网虚拟距离覆盖算法

针对水面传感器随机部署时网络覆盖率较低的问题,采用了一种面向水环境的无线传感网虚拟距离覆盖算法,在保证连通性的前提下提高网络的覆盖率。在虚拟距离算法中,每个传感器节点的运动受到3个虚拟距离的影响:节点之间的虚拟距离、未被覆盖区域格点与节点的虚拟距离以及边界与节点间的虚拟距离。仿真结果表明:该算法可以有效地提高网络覆盖率。可以得出以下结论:虚拟距离算法通过对节点位置的控制更新有效提高了网络覆盖率,使节点得到优化部署。     

基于贝叶斯理论的城市供水管网泄漏在线检测与定位

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。     

Resilience Indexes for Water Distribution Network Design: A Performance Analysis Under Demand Uncertainty

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.     

Sensor Partitioning Placements via Random Walk and Water Quality and Leakage Detection Models within Water Distribution Systems

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.

Graphical Abstract

     

Localization of Contamination Sources in Drinking Water Distribution Systems: A Method Based on Successive Positive Readings of Sensors

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.     

Simulated Annealing in Optimization of Energy Production in a Water Supply Network

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.     

Soft sensing of water depth in combined sewers using LSTM neural networks with missing observations

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.