Urban water distribution networks (WDNs) have wide range and intricate topology, which include leakage, pipe burst and other abnormal states during production and operation. With the continuous development of the Internet of Things (IoT) technology in recent years, the means of monitoring the WDNs by using wireless sensor network technology has gradually received attention and extensive research. Most of the existing researches select the deployment location of sensors according to the hydraulic state of the WDNs, but the connectivity and topology between the nodes of the WDNs are not fully considered and analyzed. In this study, a new method that can integrate the topological features and hydraulic model information of the WDN is proposed to solve the problem of optimal sensor placement. First, the method preprocesses the covariance matrix of the pressure sensitivity matrix of the water distribution network by a diffusion kernel-based data prefiltering method and obtains the new network topology weights and its Laplacian matrix under the constraints of the network topology through a data-based graphical Laplacian learning method. Then, the sensor placement problem is transformed into a matrix minimum eigenvalue constraint problem by the Graph Laplace Regularization (GLR)-based method, and finally the selection of sensor nodes is accomplished by the method based on Gershgorin Disc Alignment (GDA). The proposed strategy is tested on a passive Hanoi network, an active Net 3 network, and a larger network, PA2, and is compared with some existing methods. The results show that the proposed solution achieves good performance in three different leak localization methods.

Localizing leakages in large water distribution systems is an important and ever-present problem. Due to the complexity originating from water pipeline networks, too few sensors, and noisy measurements, this is a highly challenging problem to solve. In this work, we present a methodology based on generative deep learning and Bayesian inference for leak localization with uncertainty quantification. A generative model, utilizing deep neural networks, serves as a probabilistic surrogate model that replaces the full equations, while at the same time also incorporating the uncertainty inherent in such models. By embedding this surrogate model into a Bayesian inference scheme, leaks are located by combining sensor observations with a model output approximating the true posterior distribution for possible leak locations. We show that our methodology enables producing fast, accurate, and trustworthy results. It showed a convincing performance on three problems with increasing complexity. For a simple test case, the Hanoi network, the average topological distance (ATD) between the predicted and true leak location ranged from 0.3 to 3 with a varying number of sensors and level of measurement noise. For two more complex test cases, the ATD ranged from 0.75 to 4 and from 1.5 to 10, respectively. Furthermore, accuracies upwards of 83%, 72%, and 42% were achieved for the three test cases, respectively. The computation times ranged from 0.1 to 13 s, depending on the size of the neural network employed. This work serves as an example of a digital twin for a sophisticated application of advanced mathematical and deep learning techniques in the area of leak detection.

In this work, a miniaturized, low-cost, low-power and high-sensitivity AlN-based micro-electro-mechanical system (MEMS) hydrophone is proposed for monitoring water pipeline leaks. The proposed MEMS Hydrophone consists of a piezoelectric micromachined ultrasonic transducer (PMUT) array, an acoustic matching layer and a pre-amplifier amplifier circuit. The array has 4 (2 × 2) PMUT elements with a first-order resonant frequency of 41.58 kHz. Due to impedance matching of the acoustic matching layer and the 40 dB gain of the pre-amplifier amplifier circuit, the packaged MEMS Hydrophone has a high sound pressure sensitivity of -170 ± 2 dB (re: 1 V/μPa). The performance with respect to detecting pipeline leaks and locating leak points is demonstrated on a 31 m stainless leaking pipeline platform. The standard deviation (STD) of the hydroacoustic signal and Monitoring Index Efficiency (MIE) are extracted as features of the pipeline leak. A random forest model is trained for accurately classifying the leak and no-leak cases using the above features, and the accuracy of the model is about 97.69%. The cross-correlation method is used to locate the leak point, and the localization relative error is about 10.84% for a small leak of 12 L/min.

Urban water distribution networks (WDNs) in developing economies often refrain from investing in sensor-based leakage management technologies due to financial constraints and other techno-managerial issues. Thus, this study proposes a generalized decision support framework based on network sensitivity analysis (NSA) and multi-criteria decision-making (MCDM) to assess the prospect of effective leakage control through robust sensor placement in existing deficient WDNs. Four sensitivity parameters are formulated for NSA to ascertain the pressure response of the potential sensor positions for diverse hydraulic and leak scenarios. Subsequently, selecting the optimal number of sensors and their relative positions within the WDN is framed as an MCDM problem that entails the simultaneous maximization of Euclidean distances among the potential sensor positions and the leak-induced pressure residuals obtained at these sensors. The proposed methodology is developed on a numerical benchmark network assuming ideal conditions, and its applicability is verified on a sensor-equipped experimental network considering realistic system uncertainties. The outcome of this study aims to provide an insightful understanding of the system behavior that governs its leak localization potential and ascertain the practical challenges of sensor-based leakage monitoring in existing WDNs. Decision-makers of resource-strained utilities can beneficially utilize the proposed framework to assess the environmental and cost trade-offs of employing sensor-based technologies for leakage management and proactive decision-making before its actual implementation.

This paper presents a method for optimal pressure sensor placement in water distribution networks using information theory. The criterion for selecting the network nodes where to place the pressure sensors was that they provide the most useful information for locating leaks in the network. Considering that the node pressures measured by the sensors can be correlated (mutual information), a subset of sensor nodes in the network was chosen. The relevance of information was maximized, and information redundancy was minimized simultaneously. The selection of the nodes where to place the sensors was performed on datasets of pressure changes caused by multiple leak scenarios, which were synthetically generated by simulation using the EPANET software application. In order to select the optimal subset of nodes, the candidate nodes were ranked using a heuristic algorithm with quadratic computational cost, which made it time-efficient compared to other sensor placement algorithms. The sensor placement algorithm was implemented in MATLAB and tested on the Hanoi network. It was verified by exhaustive analysis that the selected nodes were the best combination to place the sensors and detect leaks.

This article presents a new data-driven method for locating leaks in water distribution networks (WDNs). It is triggered after a leak has been detected in the WDN. The proposed approach is based on the use of inlet pressure and flow measurements, other pressure measurements available at some selected inner nodes of the WDN, and the topological information of the network. A reduced-order model structure is used to calculate non-leak pressure estimations at sensed inner nodes. Residuals are generated using the comparison between these estimations and leak pressure measurements. In a leak scenario, it is possible to determine the relative incidence of a leak in a node by using the network topology and what it means to correlate the probable leaking nodes with the available residual information. Topological information and residual information can be integrated into a likelihood index used to determine the most probable leak node in the WDN at a given instant k or, through applying the Bayes\' rule, in a time horizon. The likelihood index is based on a new incidence factor that considers the most probable path of water from reservoirs to pressure sensors and potential leak nodes. In addition, a pressure sensor validation method based on pressure residuals that allows the detection of sensor faults is proposed.

This paper describes issues of leakage localization in liquid transmission pipelines. It focuses on the standard leak localization procedure, which is based on the calculation of pressure gradients using pressure measurements captured along a pipeline. The procedure was verified in terms of an accuracy and uncertainty assessment of the resultant coordinate of a leak spot. An important aim of the verification was to assess the effectiveness of the procedure in the case of localization of low intensity leakages with a level of 0.25-2.00% of the nominal flow rate. An uncertainty assessment was carried out according to the GUM convention. The assessment was based on the metrological characteristics of measuring devices and measurement data obtained from the laboratory model of the pipeline.

暂无摘要。

Leak localization is essential for the safety and maintenance of storage vessels. This study proposes a novel circular acoustic emission sensor array to realize the continuous CO₂ leak localization from a circular hole on the surface of a large storage vessel in a carbon capture and storage system. Advantages of the proposed array are analyzed and compared with the common sparse arrays. Experiments were carried out on a laboratory-scale stainless steel plate and leak signals were obtained from a circular hole in the center of this flat-surface structure. In order to reduce the influence of the ambient noise and dispersion of the acoustic wave on the localization accuracy, ensemble empirical mode decomposition is deployed to extract the useful leak signal. The time differences between the signals from the adjacent sensors in the array are calculated through correlation signal processing before estimating the corresponding distance differences between the sensors. A hyperbolic positioning algorithm is used to identify the location of the circular leak hole. Results show that the circular sensor array has very good directivity toward the circular leak hole. Furthermore, an optimized method is proposed by changing the position of the circular sensor array on the flat-surface structure or adding another circular sensor array to identify the direction of the circular leak hole. Experiential results obtained on a 100 cm × 100 cm stainless steel plate demonstrate that the full-scale error in the leak localization is within 0.6%.