Monitoring Of Water Distribution Systems Research Articles

Flow forecasting for leakage burst prediction in water distribution systems using long short-term memory neural networks and Kalman filtering

Reducing pipe leakage is one of the top priorities for water companies, with many investing in higher quality sensor coverage to improve flow forecasting and detection of leaks. Most research on this topic is focused on leakage detection through the analysis of sensor data from district metered areas (DMAs), aiming to identify bursts after their occurrence. This study is a step towards the development of ‘self-healing’ water infrastructure systems. In particular, machine learning and deep learning-based algorithms are applied to forecasting the anomalous water flow experienced during bursts (new leakage) in DMAs at various temporal scales, thereby aiding in the health monitoring of water distribution systems. This study uses a dataset of over 2,000 DMAs in North Yorkshire, UK, containing flow time series recorded at 15-minute intervals for a period of one year. Firstly, the method of isolation forests is used to identify anomalies in the dataset, which are cross referenced with entries in the water mains repair log, indicating the occurrence of bursts. Going beyond leakage detection, this research proposes a hybrid deep learning framework named FLUIDS (Forecasting Leakage and Usual flow Intelligently in water Distribution Systems). A recurrent neural network (RNN) is used for mean flow forecasting, which is then combined with forecasted residuals obtained through real-time Kalman filtering. While providing expected day-to-day flow demands, this framework also aims to issue sufficient early warning for any upcoming anomalous flow or possible leakages. For a given forecast period, the FLUIDS framework can be used to compute the probability of flow exceeding a pre-defined threshold, thus allowing decision-making for any necessary interventions. This can inform targeted repair strategies that best utilize resources to minimize leakages and disruptions. The FLUIDS framework is statistically assessed and compared against the state-of-practice minimum night flow (MNF) methodology. Based on the statistical analyses, it is concluded that the proposed framework performs well on the unobserved test dataset for both regular and leakage water flows.

Machine-Learning-Based Health Monitoring and Leakage Management of Water Distribution Systems

The reduction of pipe leakage is one of the top priorities for water companies, with many investing in greater sensor coverage to improve the forecasting of flow and detection of leaks. The majority of research on this topic is focused on leakage detection through the analysis of sensor data from district metered areas (DMAs), with the aim of identifying bursts after occurrence. This study is a step towards development of ‘self-healing’ water infrastructure systems. In particular, the concepts of machine-learning (ML) and deep-learning (DL) are applied to the forecasting of water flow in DMAs at various temporal scales, thereby aiding in the health monitoring of water distribution systems. This study uses a dataset for ~2500 DMAs in Yorkshire, containing flow time-series recorded at every 15-minute interval over the period of a year. Firstly, the method of isolation forests is used to identify anomalies in the dataset which are verified as corresponding to entries in water mains repair log, indicating the occurrence of bursts. Going beyond leakage detection, this research proposes a hybrid framework of DL models - such as recurrent neural networks (RNNs) and transformer neural networks) - and state-space ML algorithms - such as Kalman filter and autoregressive integrated moving average (ARIMA). The ML algorithms are trained to forecast the stationary component of the expected flow patterns in real-time, which is then combined (through Bayesian updating) with the non-stationary component obtained from DL models. As well as providing expected day-to-day flow demands, this framework aims to issue sufficient early warning for any upcoming anomalous flow or possible leakages. For a given forecast period, the framework can be used to compute the probability of flow exceeding a pre-defined threshold, thus allowing decisions to be made regarding any necessary interventions. This can inform targeted repair strategies which best utilise resources to minimise leakage and disruptions by addressing both detected and predicted burst events.

A Novel Deep Learning Method for Water leakage Detection Using Acoustic Features

Conservation of water is one of the major objectives for any country around the world. Water management plays a very important role in a society, as it is one of the basic needs for the mankind. Water leak detection is an important task for ensuring the safety and efficiency of water systems. Deep learning techniques, combined with real-time sensor data, can greatly enhance the accuracy and efficiency of water leak detection. Water leak detection plays a crucial role in maintaining the safety, efficiency, and sustainability of water systems. This paper presents an investigation of the capacity of deep learning methods (DL) to localize leakage in water distribution systems (WDS). Progress in real-time monitoring of WDS and DL has inspired towards new opportunities to develop data-based methods for water leak localization. However, the handlers of WDS need recommendations for the selection of the optimal DL methods as well their practical use for leakage localization. This paper contributes to this issue through an investigation of the capacity of DL methods to localize leakage in WDS. Water leak detection is crucial in conversation of water, cost saving, infrastructure protection prevention of water damage and operation efficiency. This paper shows a proposal for a system based on a wireless sensor network designed to monitor water distribution systems, such as hotel industry, irrigation systems, which, with the help of an autonomous learning algorithm, allows for precise location of water leaks. Autoencoder neural network (AE), an unsupervised DL model, is further developed to detect leak with unbalanced data. The results show AE-DL model achieved high accuracy when leaks occur in pipes inside the sensor monitoring area, while the accuracy is compromised otherwise. This observation will provide guidelines to deploy monitoring sensors to cover the desired monitoring area. A novel strategy is proposed based on multiple independent detection attempts to further increase the reliability of leak detection by the AE-DL and is found to significantly reduce the probability of false alarm.

A Digital Twin of a Water Distribution System by Using Graph Convolutional Networks for Pump Speed-Based State Estimation

Water distribution system monitoring is currently carried out using advanced real-time control technologies to achieve a higher operational efficiency. Data analysis techniques can be implemented for condition estimation, which are crucial tools for managing, developing, and operating water networks using the monitored flow rate and pressure data at some network pipes and nodes. This work proposes a state estimation methodology that enables one to infer the hydraulic state of the operating speed of pumping systems from these pressure and flow measurements. The presented approach suggests using graph convolutional neural network theory linked to hydraulic models for generating a digital twin of the water system. It is validated on two benchmark hydraulic networks: the Patios-Villa del Rosario, Colombia, and the C-Town networks. The results show that the proposed model effectively predicts the state estimation in the two hydraulic networks used. The results of the evaluation metrics indicate low values of mean squared error and mean absolute error and high values of the coefficient of determination, reflecting high predictive ability and that the prediction results adequately represent the real data.

Use of Machine Learning for Leak Detection and Localization in Water Distribution Systems

This paper presents an investigation of the capacity of machine learning methods (ML) to localize leakage in water distribution systems (WDS). This issue is critical because water leakage causes economic losses, damages to the surrounding infrastructures, and soil contamination. Progress in real-time monitoring of WDS and ML has created new opportunities to develop data-based methods for water leak localization. However, the managers of WDS need recommendations for the selection of the appropriate ML methods as well their practical use for leakage localization. This paper contributes to this issue through an investigation of the capacity of ML methods to localize leakage in WDS. The campus of Lille University was used as support for this research. The paper is presented as follows: First, flow and pressure data were determined using EPANET software; then, the generated data were used to investigate the capacity of six ML methods to localize water leakage. Finally, the results of the investigations were used for leakage localization from offline water flow data. The results showed excellent performance for leakage localization by the artificial neural network, logistic regression, and random forest, but there were low performances for the unsupervised methods because of overlapping clusters.

Assessing the Potential of LPWAN Communication Technologies for Near Real-Time Leak Detection in Water Distribution Systems.

While low-power wide-area network (LPWAN) technologies have been studied extensively for a broad spectrum of smart city applications, their potential for water distribution system monitoring in high temporal resolution has not been studied in detail. However, due to their low power demand, these technologies offer new possibilities for operating pressure-monitoring devices for near real-time leak detection in water distribution systems (WDS). By combining long-distance wireless communication with low power consumption, LPWAN technologies promise long periods of maintenance-free device operation without having to rely on an external power source. This is of particular importance for pressure-based leak detection where optimal sensor positions are often located in the periphery of WDS without a suitable power source. To assess the potential of these technologies for replacing widely-used wireless communication technologies for leak detection, GPRS is compared with the LPWAN standards Narrowband IoT, long-range wide area network (LoRaWAN) and Sigfox. Based on sampling and transmission rates commonly applied in leak detection, the ability of these three technologies to replace GPRS is analyzed based on a self-developed low-power pressure-monitoring device and a simplified, linear energy-consumption model. The results indicate that even though some of the analyzed LPWAN technologies may suffer from contractual and technical limitations, all of them offer viable alternatives, meeting the requirements of leak detection in WDS. In accordance with existing research on data transmission with these technologies, the findings of this work show that even while retaining a compact design, which entails a limited battery capacity, pressure-monitoring devices can exceed runtimes of 5 years, as required for installation at water meters in Austria. Thus, LPWAN technologies have the potential to advance the wide application of near real-time, pressure-based leak detection in WDS, while simultaneously reducing the cost of device operation significantly.

Artificial intelligence-based monitoring system of water quality parameters for early detection of non-specific bio-contamination in water distribution systems

Abstract This research aims to simulate bio-contamination risk propagation under real-life conditions in the water distribution system (WDS) of Lille University's Scientific City Campus (France), solving the source identification and the response modeling. Neglecting dynamic reactions and not considering the possible chemical decay of most of the contaminants leads to an overestimation of the exposed population. Therefore, unlike the available event detection models, this study considers the interrelated change of several water-quality parameters such as free chlorine concentration, pH, alkalinity, and total organic carbon (TOC) resulting from the pollutants blending. In fact, starting from regular WDS monitoring, the baseline thresholds for each of the mentioned parameters are established; then, significant deviations from the baseline are used as indication for contaminations. For this reason, the purpose of the research was to develop and demonstrate the feasibility of an artificial intelligence (AI)-based smart monitoring system that will effectively enable water operators to ensure a quasi real-time quality control for early chemical and/or bio-contamination detection and preemptive risk management. Advanced pattern recognizers, such as Support Vector Machines (SVMs), and innovative sensing technology solutions, such as Artificial Neural Network (ANN), have been used for this purpose, identifying the anomalies and the severity-level assessment.

Critical analysis of laboratory measurements and monitoring system of water-pipe network corrosion-case study.

Case study of corrosion failure of urban water supply system caused by environmental factors was presented. Nowadays corrosion monitoring of water distribution systems is an object of major concern. There is possibility of application broad range of techniques like gravimetric and electrochemical. Both kinds of techniques can be applied in laboratory and field conditions. In many cases researches limit the case analysis to measurements in laboratory conditions. Presented work contain critical analysis of results obtained in laboratory and field conditions based on corrosion monitoring of three pipelines systems failure in Krakow.

Assessment of water delivery efficiency in irrigation canals using performance indicators

Agricultural water is delivered by open irrigation canals in system of reservoirs with a widespread distribution in South Korea. Traditional irrigation management problems include water distribution systems with less capacity than the peak demand, irregular delivery rates, and low irrigation efficiency and uniformity. It is necessary to strategically compare the estimated irrigation demands with the actual water supplies for decision making in order to maintain the water supply according to the demand. Accurate measurement and monitoring of water distribution systems is essential in order to solve the problems of water efficiency and availability. Auto water level gauges installed at the head and tail sections of each irrigation canal in the Dongjin River were used to measure the discharge during irrigation periods. In this study, we introduced an approach to assess the water delivery performance indicators of the open irrigation canals, which is essential for identifying the key issues for water management improvement. The irrigation efficiencies according to the water delivery performance indicators were measured with an automatic water gauge in the irrigation canals and were calculated from the spatial and temporal distribution of the water supply for the lack of planning in water delivery. The calculated performance indicators are useful to understand the irrigator behavior and general irrigation trends. Analysis of the results yielded insights into possible improvement methods in order to develop water management policies that enable irrigation planners to improve the temporal uniformity and equity in the water distribution.

Prevalence of Legionella pneumophila in water distribution systems in hospitals and public buildings of the Lublin region of eastern Poland.

The aim of this study was to determine the prevalence of L. pneumophila in water supply systems, hospitals and public buildings in the Lublin region of eastern Poland. The study was carried out in 26 different objects in the Lublin region. The number of Legionella bacteria in water samples was determined by the membrane filtration method and/or by surface inoculation in accordance with the standards. The study showed the presence of L. pneumophila in 166 hot water samples (74.77%). In 34.33% (n=57) of water samples the count of tested bacteria exceeded the acceptable level of >100 CFU/100 ml. Of the samples where an acceptable level of bacteria was exceeded, 49 samples had an average level of L. pneumophila (100-1,000 CFU/100 ml), and the level in 8 samples was high (>1,000 CFU/100 ml). The water samples collected form the hot water supply system of hospitals and public buildings showed exceeded counts of L. pneumophila, indicating the risk of infection. The constant monitoring of water distribution systems is an important element of the control of infections caused by these organisms.

Case study: a smart water grid in Singapore

As aging water distribution infrastructures encounter failures with increasing frequency, there is a real need for integrated, on-line decision-support systems based on continuous in-network monitoring of hydraulic and water quality parameters. Such systems will form the basis of a Smart Water Grid, allowing water utilities to improve optimization of system operation, manage leakage control more effectively, and reduce the duration and disruption of repairs and maintenance. WaterWiSe is an integrated, end-to-end platform for real-time monitoring of water distribution systems that addresses these needs. This paper describes how WaterWiSe's sensing and software platforms have helped improve the operational efficiency of the water supply system in downtown Singapore.

Sequential Monitoring of Water Distribution Network

Monitoring drinking water is a public health problem because water is essential for human life. A typical modern drinking water distribution system includes a water purification plant, water towers, water tanks, pumps and pipes. Many procedures are developed for monitoring water quality in water treatment plants. Monitoring of water distribution systems has received less attention.The goal of this paper is to study the problem of drinking water safety by ensuring the monitoring of the distribution network from water tower to private residences. The proposed approach is based on the observation of residual chlorine concentrations which are provided by sensors network. By using the hydraulic model, it is possible to compute the nominal residuals chlorine concentrations under assumption that quality of the water at the water tower output is known. If a significant reduction of the residual chlorine concentrations is observed then it can be interpreted as presence of a dangerous water contamination. This event should be detected as reliable as possible provided an acceptable detection delay and false alarm rate. The traditional abrupt change detection theory is well developed in the case when the duration of the post-change mode is infinite. Unfortunately, in the discussed case the transient signal duration is short. Hence, the usage of traditional change detection algorithm is compromised.A criterion based on the minimization of the missed detection probability provided that the false alarm rate is upper bounded is used in the paper. A suboptimal detection algorithm is designed. The theoretical analysis and the results of simulation are provided.

Book Reviews

Book Reviews

Pressure and Flow Uncertainty in Water Systems

In the monitoring of water distribution systems, the inaccuracy of input data contributes greatly to the inaccuracy of system state estimates calculated from them. It is important, therefore, that the system operators are given not only the values of flows and pressures in the network at any instant of time but also that they have some indication of how reliable these values are. The quantification of the inaccuracy of calculated flows and pressures caused by the input data uncertainty is called here confidence limit analysis. Several confidence limit analysis algorithms are presented. These include a Monte Carlo simulation method, an optimization method, and a sensitivity matrix technique. The performance of these algorithms is assessed in terms of their suitability for real‐time control or design stage applications. Results are presented for a realistic test network.

Committee Report: Current Practice in Bacteriological Sampling

A survey of AWWA utility members indicated that there is great variability among sampling programs for microbiological monitoring of water distribution systems. This variability includes the number of samples collected, the use of check samples, the patterns of sample collection over the area of the distribution system and over time, and the sample collection and laboratory examination techniques. Since little research has been conducted on the various elements of a sampling program, there is as yet no basis for specifying the sampling procedures for an ideal bacteriological monitoring program.