Explore the vast range of titles available.

The partitioning of the urban water supply network can significantly enhance water supply quality. Nonetheless, the bulk of the recently deployed partition approaches overlooked the question of whether the district's fluctuation regulation of flow data is consistent. When the district is modified, it most likely leads to an increase in pressure at a node. To tackle the problem, the flow data from a city's water supply network was evaluated in this article. The random forest approach was also used to extract time-domain characteristics from flow data, and the water supply network split was optimized using the random forest-hierarchical clustering (RF-HC) strategy. Finally, the results were examined and compared. The results suggest that the RF-HC-based water supply network partition technique can better meet the aim of consistent flow changes in the district, as well as offer a theoretical foundation and technological support for the optimal dispatch of press concerning the water supply network.

Purpose: This study describes the trends and applications of machine learning systems in the management of water supply networks. Machine learning is a field in constant development, and it has a great potential and capability to attain improvements in real industries. The recent tendency of data storage by companies that manage the water supply networks have created a range of possibilities to apply machine learning. One particular case is the prediction of pipe failures based on historical data, which can help to optimally plan the renovation and maintenance tasks. The objective of this work is to define the stages and main characteristics of machine learning systems, focusing on supervised learning methods. Additionally, singularities that are usually found in data from water supply networks are highlighted. Design/methodology/approach: For this purpose, eight studies which contain real cases from around the world are discussed. From the data processing to the model validation, a tour of the methods used in each study is carried out. Moreover, the trendiest models are briefly defined together with the mechanisms that best suit their performance. Findings: As a result of the study, it was found that the imbalanced class problem is typical of data from water supply networks where only a small percentage of pipes fail. Consequently, it is recommended to use sampling methods to train classifiers, however, it is not necessary if we are training a regression system. Additionally, scaling and transformation of variables has generally a positive impact on the model's performance. Currently, cross-validation is almost a requirement to obtain reliable and representative results. This technique is employed in all revised studies to train and validate their models. Originality/value: The use of machine learning systems to predict pipe failures in water supply networks is still a developing field. This study tries to define the advantages and disadvantages of different methods to process data from water supply networks, as well as to train and validate the models.

Purpose: This article focuses on the problem of deciding the annual investment that a company should allocate to the rehabilitation of its water distribution and sanitation networks. The objective is to find the investment amount necessary to maintain an adequate quality and sustainability of the infrastructure. It is not a simple decision, as there are different criteria that may be of interest to the managing company. In this paper, we consider four criteria related to the reliability of individual pipes and the complete network. These indicators are the infrastructure value index, the average age of network pipes, the risk index and the probability of failure.Design/methodology/approach: A methodology is proposed to estimate the best annual investment by analysing the evolution of these indicators. Concretely, two strategies are tested. The first one is a minimax-based approach that seeks a balanced solution for all the indicators. The second one is named as minimal deviation strategy and seeks to minimise the deviation of all the indicators in the last year of the time horizon compared to the initial year.Findings: In order to obtain a realistic sample of the performance of both strategies, 201 scenarios, i.e. 201 different annual investments have been tested. According to the first strategy, an annual investment of 55.5 M€ is the best option, while the minimal deviation strategy presents an annual investment of 39.5 M€ as the best decision. The study reveals that different evaluation functions lead to completely different annual investment. Concretely, the minimax evaluation function is more conservative than the minimal deviation strategy.Originality/value: This study proposes an original approach to address the decision problem of investments in asset management. To the best of the authors’ knowledge, it is the first attempt to treat that problem using this kind of evaluation functions. However, it is still a simple proposal and there are many options to continue this line of research.

The water supply network (WSN) is subjected to leaks that compromise its service to the communities, which, however, is challenging to identify with conventional approaches before the consequences surface. This study developed Machine Learning (ML) models to detect leaks in the WDN. Water pressure data under leaking versus non-leaking conditions were generated with holistic WSN simulation code EPANET considering factors such as the fluctuating user demands, data noise, and the extent of leaks, etc. The results indicate that Artificial Neural Network (ANN), a supervised ML model, can accurately classify leaking versus non-leaking conditions; it, however, requires balanced dataset under both leaking and non-leaking conditions, which is difficult for a real WSN that mostly operate under normal service condition. Autoencoder neural network (AE), an unsupervised ML model, is further developed to detect leak with unbalanced data. The results show AE ML 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 and is found to significantly reduce the probability of false alarm. The trained AE model and leak detection strategy is further tested on a testbed WSN and achieved promising results. The ML model and leak detection strategy can be readily deployed for in-service WSNs using data obtained with internet-of-things (IoTs) technologies such as smart meters.

Water Supply and Distribution Networks (WSDNs) offer underexplored potential for energy recovery. While many studies confirm their technical feasibility, few assess the long-term operational compatibility and economic viability of such solutions. This study evaluates the energy recovery potential of the Brussels Capital Region’s WSDN using four years (2019–2022) of operational data. Rather than focusing on available technologies, the analysis examines whether the real behavior of the network supports sustainable energy extraction. The approach includes network topology identification, theoretical power modeling, and detailed flow and pressure analysis. The Brussels system, composed of a Water Supply Network (WSN) and a Water Distribution Network (WDN), reveals strong disparities: the WSN offers localized opportunities for energy recovery, while the WDN presents significant operational constraints that limit economic viability. Our findings suggest that day-ahead electricity markets provide more suitable valorization pathways than flexibility markets. Most importantly, the study highlights the necessity of long-term behavioral analysis to avoid misleading conclusions based on short-term data and to support informed investment decisions in the urban water–energy nexus.

Migration of emerging contaminants (ECs) from pipes into water is a global concern due to potential human health effects. Nevertheless, a review of migration ECs from pipes into water distribution systems is presently lacking. This paper reviews, the reported occurrence migration of ECs from pipes into water distribution systems in the world. Furthermore, the results related to ECs migration from pipes into water distribution systems, their probable sources, and their hazards are discussed. The present manuscript considered the existing reports on migration of five main categories of ECs including microplastics (MPs), bisphenol A (BPA), phthalates, nonylphenol (NP), perfluoroalkyl, and polyfluoroalkyl substances (PFAS) from distribution network into tap water. A focus on tap water in published literature suggests that pipes type used had an important role on levels of ECs migration in water during transport and storage of water. For comparison, tap drinking water in contact with polymer pipes had the highest mean concentrations of reviewed contaminants. Polyvinyl chloride (PVC), polyamide (PA), polypropylene (PP), polyethylene (PE), and polyethylene terephthalate (PET) were the most frequently detected types of microplastics (MPs) in tap water. Based on the risk assessment analysis of ECs, levels of perfluorooctanoic acid (PFOA), perfluorononanoic acid (PFNA), perfluorodecanoic acid (PFDA), perfluorohexane sulfonate (PFHxS), and perfluorooctane sulfonate (PFOS) were above 1, indicating a potential non-carcinogenic health risk to consumers. Finally, there are still scientific gaps on occurrence and migration of ECs from pipes used in distribution systems, and this needs more in-depth studies to evaluate their exposure hazards on human health.

Conduit hydropower systems improve the efficiency of water supply networks (WSNs) by utilizing excess network pressure for providing renewable energy while significantly reducing leakage. A major problem in using conduit hydropower is finding the optimum location for installing power generation devices like in-line turbines or pumps operating as turbines (PATs). This paper suggests an optimization model to find the optimum location for placing in-line turbines in WSNs using a non-parametric Rao algorithm for optimal daily power generation. The methodology is tested on a hypothetical 5-Node network and later applied to a benchmark 25-Node network. Installing turbines at optimum locations reduced network leakage by 76332.00 and 380473.87 L, representing approximately 2.57% & 2.94% of the total water demand of 5-Node and 25-Node networks, respectively, and generated 184.12 & 547.48 kWh/day of hydropower.

The water supply network is a crucial component of urban construction and plays a pivotal role in the normal operation of the city. The complexity and periodicity of pressure variations in the water supply networks pose significant challenges to traditional prediction models. In this study, we introduce a novel short-term pressure prediction model, termed the 1DCNN-GRU-multi-head attention (CGMA) model, which incorporates a multi-head attention mechanism alongside an integrated network consisting of one-dimensional convolutional neural networks (1DCNNs) and gated recurrent units (GRUs). Initially, the model employs a 1DCNN network to extract features from the pressure data. Subsequently, the extracted features are input into the GRU neural network, leveraging its long-term dependency capabilities to improve prediction accuracy. Then, the attention mechanism is incorporated into the GRU component to highlight key information, enabling the model to focus on more important data features, thereby improving the prediction performance. We implemented this model in a real urban water distribution system equipped with five pressure sensors. The model achieved a mean absolute error of 0.00197 and a root mean square error of 0.00262. When compared with alternative approaches, our method demonstrated superior predictive performance for pressure data, thereby confirming its efficacy in practical applications.

Pressure sensor placement is critical to system safety and operation optimization of water supply networks (WSNs). The majority of existing studies focuses on sensitivity or burst identification ability of monitoring systems based on certain specific operating conditions of WSNs, while nodal connectivity or long-term hydraulic fluctuation is not fully considered and analyzed. A new method of pressure sensor placement is proposed in this paper based on Graph Neural Networks. The method mainly consists of two steps: monitoring partition establishment and sensor placement. (1) Structural Deep Clustering Network algorithm is used for clustering analysis with the integration of complicated topological and hydraulic characteristics, and a WSN is divided into several monitoring partitions. (2) Then, sensor placement is carried out based on burst identification analysis, a quantitative metric named “indicator tensor” is developed to calculate hydraulic characteristics in time series, and the node with the maximum average partition perception rate is selected as the sensor in each monitoring partition. The results showed that the proposed method achieved a better monitoring scheme with more balanced distribution of sensors and higher coverage rate for pipe burst detection. This paper offers a new robust framework, which can be easily applied in the decision-making process of monitoring system establishment.

Water losses occur in every water distribution systems during their overall exploitation time. Losses cause not only additional operating costs but also generate negative social and ecological consequences. Water losses may have multiple possible reasons, differing in accordance to a water supply system. Therefore, there is a high need to individually analyze each water supply distribution system. The aim of this paper is to analyze and compare water losses in selected two group water supply systems, serving 5 000–10 000 consumers. Water balances, pursued in accordance to the methodology developed by IWA (International Water Association), enabled calculation of water losses indicators for both systems. The obtained results lead to evaluation of the condition of analyzed water supply systems and they suggest potential actions in order to minimize water losses. Moreover, the results indicate the great necessity for working out a reliable method for determination of unavoidable annual real losses in rural water distribution systems with no more than 20 connections per km.