Pressure Sensor Placement in Water Supply Network Based on Graph Neural Network Clustering Method

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.

Estimation of Burst Pressure of PVC Pipe Using Average Shear Stress Yield Criterion: Experimental and Numerical Studies

Polyvinyl chloride (PVC) pipes have been extensively applied in water supply network fields. Understanding the mechanical properties and burst pressure of PVC pipes is necessary because a large number of pipes rupture due to excessive internal water pressure. In this paper, a practical approach based on the average shear stress yield (ASSY) criterion was proposed to assess the PVC pipe burst pressure. In addition, the PVC uniaxial tensile tests and the pipe burst tests were carried out to determine the material characteristic parameters and burst pressure of the PVC pipe. Furthermore, a finite element analysis (FEA) of PVC burst pressure was also performed based on the tangent intersection (TI) method to validate the proposed method and experimental results. Moreover, the impact of material parameters and pipe size, such as the strain hardening exponent and standard dimension ratio (SDR) on bursting pressure, were investigated. The comparison with the proposed theoretical model and the experimental and FEA results shows that the burst pressure derived from ASSY was consistent with the experimental data, with a relative error ranging from −2.76% to 2.65%, which is more accurate compared to other yield criteria. The burst pressure obtained by the ASSY approach declined with the increase of the hardening exponent n and increased with the increase of SDR. Therefore, the burst pressure solution-based ASSY proposed in this paper is an adequately suitable and precise predictive tool for assessing the failure pressure of PVC pipes.

Free Span Analysis for Submarine Pipelines

Pipelines are one of the most important and key elements that align with transferring hydrocarbon products in coastal and offshore industries which are exposed at various risks during their servicing. In this project, we are studding and describing free spanning of marine pipeline based on DNVGL-RP-F-105 regulation applying the finite element method by Abaqus software. For modeling, case studies of Gorze to Kish oil pipeline have been used. In order to provide and study the integrity of the structure against fatigue, the exact place as well as the free span length using software under environmental loading based on DNVGL-RP-F205 has been determined. Since based on DNVGL-TS-F101 free span causes local buckling, fatigue, and pipe burst then given to the servicing as well as environmental conditions, pipe condition has been monitored. Finally, using sensitivity analysis, the effect of different soil classes, elasticity module, and temperature on the pipe condition has been studied. At the end, the question if it is allowed to use a cross model for bed has been answered in previous studies.

Near–Real Time Burst Location and Sizing in Water Distribution Systems Using Artificial Neural Networks

The current paper proposes a novel methodology for near–real time burst location and sizing in water distribution systems (WDS) by means of Multi–Layer Perceptron (MLP), a class of artificial neural network (ANN). The proposed methodology can be systematized in four steps: (1) construction of the pipe–burst database, (2) problem formulation and ANN architecture definition, (3) ANN training, testing and sensitivity analyses, (4) application based on collected data. A large database needs to be constructed using 24 h pressure–head data collected or numerically generated at different sensor locations during the pipe burst occurrence. The ANN is trained and tested in a real–life network, in Portugal, using artificial data generated by hydraulic extended period simulations. The trained ANN has demonstrated to successfully locate 60–70% of the burst with an accuracy of 100 m and 98% of the burst with an accuracy of 500 m and to determine burst sizes with uncertainties lower than 2 L/s in 90% of tested cases and lower than 0.2 L/s in 70% of the cases. This approach can be used as a daily management tool of water distribution networks (WDN), as long as the ANN is trained with artificial data generated by an accurate and calibrated WDS hydraulic models and/or with reliable pressure–head data collected at different locations of the WDS during the pipe burst occurrence.

Implementing and evaluating various machine learning models for pipe burst prediction

By accurate predicting of pipe bursts, it is possible to schedule pipe maintenance, rehabilitation and improve the level of services in water distribution networks (WDNs). In this study, we aimed to implement five artificial intelligence and machine learning regression models such as multivariate adaptive regression splines (MARS), M5' regression tree (M5'), Least square support vector regression (LS-SVR), fuzzy regression based on c-means clustering (FCMR) and regressive convolution neural network with support vector regression (RCNN-SVR) for predicting pipe burst rate and evaluating the performance of these models. The most effective parameters for regression models are pipes age, diameter, depth of installation, length, average and maximum hydraulic pressure. In the present study, collected data include 158 cases for polyethylene (PE) and 124 cases for asbestos cement (AC) pipes during 2012-2019. The results indicate that the RCNN-SVR model has a great performance of pipe burst rate (PBR) prediction.

Analysis of Special Consequences and Losses of Equipment Accident in Thermal Power Plant

Many types of equipment in the thermal power plant has special risks. Once a safety accident occurs, it often causes special consequences and losses. The indirect losses are difficult to calculate in general due to the special property. In this paper, a calculation model was proposed, considering collateral production impact on upstream and downstream industries, the inconvenience impact on people’s electricity and gas supply, and social security panic by rapidly spreading to media and public opinion. An example of a main steam pipe burst accident in a thermal power plant was analysed. The ratio of indirect economic losses and direct economic losses was obtained. Results showed that the ratio value (35.4) was much higher than the value (4) of general industrial accident loss. The ratio value maybe even much higher if the internal medium of special equipment has strong toxic and harmful effects. It is quite important to make concerted efforts to manufacture, usage, management, inspection, safety monitoring, and scientific supervision, in order to detect and eliminate hidden dangers early and ensure the safe operation of special equipment.

Advances in Modeling and Management of Urban Water Networks

This Editorial presents a representative collection of 15 papers, presented in the Special Issue on Advances in Modeling and Management of Urban Water Networks (UWNs), and frames them in the current research trends. The most analyzed systems in the Special Issue are the Water Distribution Systems (WDSs), with the following four topics explored: asset management, modelling of demand and hydraulics, energy recovery, and pipe burst identification and leakage reduction. In the first topic, the multi-objective optimization of interventions on the network is presented to find trade-off solutions between costs and efficiency. In the second topic, methodologies are presented to simulate and predict demand and to simulate network behavior in emergency scenarios. In the third topic, a methodology is presented for the multi-objective optimization of pump-as-turbine (PAT) installation sites in transmission mains. In the fourth topic, methodologies for pipe burst identification and leakage reduction are presented. As for the Urban Drainage Systems (UDSs), the two explored topics are asset management, with a system upgrade to reduce flooding, and modelling of flow and water quality, with analyses on the transition from surface to pressurized flow, impact of water use reduction on the operation of UDSs and sediment transport in pressurized pipes. The Special Issue also includes one paper dealing with the hydraulic modelling of an urban river with a complex cross-section.