Time and Energy Savings in Leak Detection in WSN-Based Water Pipelines: A Novel Parametric Optimization-Based Approach

This paper presents a novel optimization algorithm for monitoring a complex water pipeline using Wireless Sensor Networks (WSN), in order to solve the trade-off between a timely and accurate detection of a leak, and an efficient utilization of the energy at the WSN’s nodes aimed at prolonging the WSN’s lifetime. The scheme relies on using vibration sensors of different sensitivities to detect vibrations due to a leak, and on exploiting duty-cycling, hierarchical adaptive sampling and wavelet-based signal compression, in order to reduce sensing, computation and communication energies. Given the constraints of a maximum allowable sensor energy, a limited time to detect a leak after it occurs, and an acceptable percentage of signal distortion due to compression, a new optimization-based backtracking learning algorithm is developed here that solves for the values of various monitoring parameters such that it satisfies all the given constraints. Developing such an optimization algorithm has also required performing a sensitivity analysis, i.e. investigating the effect of changing the key monitoring parameters on the performance of leak detection and energy consumption. Simulation results for various cases successfully demonstrate the effectiveness of the algorithm while supporting the prediction of the sensitivity analysis.

     

基于多尺度卷积神经网络的管道泄漏检测模型研究

如何有效检测管道泄漏是节水型社会建设迫切需要解决的关键和热点问题之一。近年来基于深度学习的管道泄漏检测方法发展迅速,本文针对传统单尺度卷积神经网络对泄漏特征提取不充分的问题,提出一种基于多尺度一维卷积神经网络(MS1DCNN)的管道系统泄漏检测模型。该方法利用多个不同卷积尺度的卷积通路并行提取管道泄漏的特征并进行泄漏信息的分类预测。基于经典的管道系统布置,利用瞬变流模型生成管道泄漏工况下的三个水压数据集对模型进行验证,三个数据集分别用于预测管道的泄漏位置、泄漏量和非恒定摩阻系数,对应样本数为39601、3980、4900,并将预测结果与其他深度学习方法和传统的机器学习方法进行对比分析。结果表明：MS1DCNN模型对数据集样本下泄漏位置、泄漏量、非恒定摩阻系数的分类准确率达到99.96%、98.48%、100%,三者平均预测精度比传统一维卷积神经网络(1DCNN)、BP神经网络、支持向量机(SVM)和k近邻算法(KNN)提高0.31%、2%、1.27%、22.8%;MS1DCNN在信噪比为-4～12 dB的噪声环境下各数据集的平均F₁分数分别为99.2%、97.02...     

埋地异型供水管段泄漏定位方法

供水管道泄漏时产生泄漏声波,根据泄漏声波到达安装在管道上的两个传感器的时间差,可以估计出泄漏位置。泄漏声波在管道中的传播速度与管道材料、内径和壁厚等有关。当泄漏发生在由不同类型管道组成的管段上时,用平均声速计算泄漏位置会增大定位的不确定度。借助于供水管网信息化提供的地下管线详实信息,根据各段管道的长度和声速可以更准确地估计出泄漏位置。介绍了异型管段泄漏定位的计算方法,给出一个检测实例和算法的流程。     

管道系统泄漏检测的全频域法

针对长距离管道输水系统的特点,建立了适合各种边界条件的管道水击频域数学模型,并应用拉氏变换原理导出了实测离散函数的频域数学模型。在此基础上,提出完全在频域中检测管道泄漏的新方法,即管道泄漏检测的全频域法。全频域法与之前频域法的差别有两点:一是边界条件不受限制,二是泄漏检测完全在频域中完成,无需求解任何一点的傅里叶逆变换时域函数。最后通过数字算例检验了管道泄漏检测全频域法的可行性。     

An Accurate Leakage Localization Method for Water Supply Network Based on Deep Learning Network

In the water supply network, leakage of pipes will cause water loss and increase the risk of environmental pollution. For water supply systems, identifying the leak point can improve the efficiency of pipeline leak repair. Most existing leak location methods can only locate the leak point approximately at the node or pipe section of the pipe network but cannot locate the specific location of the pipe section. This paper presents a framework for accurate water supply network leakage location based on Residual Network (ResNet). This study proposes a leak localization idea with a parallel classification and regression process that enables the framework to pinpoint the exact position of leak points in the pipeline. Furthermore, a multi-supervision mechanism is designed in the regression process to speed up the model’s convergence. For a pipe network containing 40 pipes, the positioning accuracy of the pipe section is 0.94, and the MSE of the specific location of the leakage point is 0.000435. For the pipe network containing 117 pipes, the positioning accuracy of the pipe section is 0.91. The MSE of the specific location of the leakage point is 0.0009177. Experiments confirm the robustness and applicability of the framework.

     

供水管网泄漏检测定位方法及仪器

本文研究了城市供水管道泄漏形成多相湍射流引发应力波在管壁中传播机理，分析了泄漏引发的管道横振、纵振和园环振动，提出了一系列和波特征提取指标及其离散数据算法、研究了以泄漏信号应力波时和频域特征指标构造神经网络输入和矩阵，建立了能对管道运行状况进行分类的神经网络模型，以检测管道泄漏故障的发生。研究了抗干扰管网泄漏定位方法，分析了根据管网不同特征对定位公式进行修正以提高泄漏定位精度的方法，实验研究了这一     

埋地压力输水管道渗漏噪声监测试验

为研究渗漏引起压力输水管线振动的在线监测方法及其应用,利用大型水压试验机进行了模型试验。试验时,用水压试验机模拟管道水压环境,并通过开启管道中部的射流孔以模拟渗漏,然后测量和分析管道振动情况。试验使用了3组检波器,分别固定于管道外壁、内壁和悬浮于水中,共测试了4种压力和4种不同直径管道渗漏程度。试验数据显示,无论是悬浮式还是固定式检波器,都能有效地监测到渗漏引起的管道振动,管道振动强度与管内压力以及射流孔大小呈正比关系。     

Entropy-Based Sensor Placement Optimization for Waterloss Detection in Water Distribution Networks

The work presented herein addresses the problem of sensor placement optimization in urban water distribution networks by use of an entropy-based approach, for the purpose of efficient and economically viable waterloss incident detection. The proposed method is applicable to longitudinal rather than spatial sensing, thus to devices such as acoustic, pressure, or flow sensors acting on pipe segments. The method utilizes the maximality, subadditivity and equivocation properties of entropy, coupled with a statistical definition of the probability of sensing within a pipe segment, to assign an entropy metric to each pipe segment and subsequently optimize the location of sensors in the network based on maximizing the total entropy in the network. The method proposed is a greedy-search heuristic.     

HYDRAULIC PRESSURE SIGNAL DENOISING USING THRESHOLD SELF-LEARNING WAVELET ALGORITHM

A pre-filter combined with threshold self-learning wavelet algorithm is proposed for hydraulic pressure signals denoising. The denoising threshold is self-learnt in the steady flow state, and then modified under a given limit to make the mean square errors between reconstruction signals and desirable outputs minimum, so the corresponding optimal denoising threshold in a single operating case can be obtained. These optimal thresholds are used for the whole signal denoising and are different in various cases. Simulation results and comparative studies show that the present approach has an obvious effect of noise suppression and is superior to those of traditional wavelet algorithms and back-propagation neural networks. It also provides the precise data for the next step of pipeline leak detection using transient technique.     

管道泄漏检测的水力瞬变全频域数学模型

输水管道泄漏孔的存在及其位置直接影响着系统压力波形的畸变和衰减特性,通过分析有、无泄漏时任意位置处的压头频域特性可使泄漏检测成为可能.在考虑非恒定摩阻影响的基础上,提出基于水力瞬变全频域数学模型的泄漏检测反问题分析方法.用拉氏频域变换处理边界条件和实测数据,并将遗传算法用于频域反问题模型的求解,在寻优速度上比传统的瞬变时域分析的方法有了较大的改善.算例表明基于水力瞬变全频域数学模型分析的管道泄漏检测是一种有效的新方法.     

供水管线渗漏水力分析

基于供水管网水力计算理论，建立了以渗漏强度对管线压力的主要影响因素的渗漏状态下管道水力计算模型。应用该模型，可以得到正常与渗漏两种状态下的压力差值的数学表达式与其变化规律，据此可根据压力变化判据渗漏和进行定位。通过模拟计算，介绍了压力变化作为渗漏发生有效判据和初步定位的方法。     

Accuracy and Sensitivity Evaluation of TFR Method for Leak Detection in Multiple-Pipeline Water Supply Systems

The transient frequency response (TFR) based pipe leak detection method has been developed and applied to water pipeline systems with different connection complexities such as branched and looped pipe networks. Previous development and preliminary applications have demonstrated the advantages of high efficiency and non-intrusion for this TFR method. Despite of the successful validations through extensive numerical applications in the literature, this type of method has not yet been examined systematically for its inherent characteristics and application accuracy under different system and flow conditions. This paper investigates the influences of the analytical approximations and assumptions originated from the method development process and the impacts of different uncertainty factors in practical application systems on the accuracy and applicability of the TFR method. The influence factors considered for the analysis contain system properties, derivation approximations and data measurement, and the pipeline systems used for the investigation include simple branched and looped multi-pipe networks. The methods of analytical analysis and numerical simulations are adopted for the investigation. The accuracy and sensitivity of the TFR method is evaluated for different factors and system conditions in this study. The results and findings are useful to understand the validity range and sensitivity of the TFR-based method, so as to better apply this efficient and non-intrusive method in practical pipeline systems.     

基于机器学习的跨海管道泄漏位置预测模型

为解决跨海管道泄漏位置定位问题,利用EPANET 软件对海底管道泄漏探测进行建模,采用BP 神经网络模型和经K-CV 改进的SVR 模型进行泄漏位置预测。对BP 神经网络的隐含层数和学习函数进行优化和选择,使用K-CV 方法对SVR 算法的惩罚系数c 和核函数参数g 进行最优组合探寻。利用EPANET 软件建模数据形成训练集,随机选取测试集进行预测,同时使用均方根误差和相关系数对预测结果进行评价。实例验证结果表明:K-CV 方法能够有效提高SVR 模型预测精度;与水力学稳态方程相比,BP 神经网络模型在泄露位置预测问题中应用范围更广、预测精度更高。     

Pressure Zoning Approach for Leak Detection in Water Distribution Systems Based on a Multi Objective Ant Colony Optimization

Leakages result in considerable loss of water in water pipe networks. Therefore it is an important issue to detect leakage amount and its approximate location. Leakages in water distribution system are directly related to the operating pressure. In the current study, a new model is proposed for leakage amount and location detection and it is applied into two benchmark water distribution networks. In the proposed method, the water distribution networks are divided into three pressure zones in order to consider the leakage differences in different operating pressures. Then, nodal pressures and demands are calibrated using a new multi objective ant colony based optimization model. In this method, leaks are simulated as extra nodal demands. For determining the nodes where leakage happens, a probability based scheme is used. The leakage occurrence probability varies depending on the pressure zone that each node is located. The results illustrate the applicability of the proposed model for detecting the leakages in water distribution systems.     

Efficient design and operation of a data acquisition system for pressurized pipeline systems.

The unsteady flow analysis of pipeline systems provides useful guidelines for implementing data acquisition components such as data filtering ranges, sensor locations and sampling frequencies. A theoretical integration among hydraulics, free vibration analysis and signal processing is proposed for a comprehensive approach aiming at enhanced design and operation of data acquisition system. Transient analysis is performed to extract flow variation by a valve modulation in a pipeline system. Frequency transformation analysis is developed to convert pressure variations between time domain and frequency domain. Free vibration analysis provides spatial distribution of impedance characteristics and pressure variation for determining optimum sensor location. A real-time filter can be designed to secure valid signals of any particular unsteady event. Hypothetical and experimental applications show that the proposed method has potentials of the leakage detection of a pipeline system as well as an efficient design of data acquisition system.     

基于钢管道上平段容积法导叶漏水量测量与计算

水轮机导叶漏水量的测量具有一定的复杂性和不稳定性。本文基于钢管道上平段为主要测量段的容积法导叶漏水量的测量与计算,是在钢管道布置及结构分析的基础上建立计算模型,利用高精度压力变送器采集数据,实现自动计算。该计算方法在实际测量中的应用表明：测量精度以及测量结果的稳定性均符合要求,减少了人工计算误差,可以为同类型电站水轮机导叶漏水量的测量及计算提供参考。通过导叶漏水量的精确测量,对水电厂水轮机的检修质量评价以及经济运行分析具有一定的意义。     

埋地压力输水管道的分布式光纤连续监测原型试验

以深圳某水源工程大型埋地压力输水管道为例,应用基于Φ-OTDR光纤干涉原理的振动监测方法,对管道进行原型观测试验。通过运用放空阀模拟爆管泄漏事件,并结合敲击试验,检验分布式光纤的监测效果。试验结果表明,分布式光纤用于埋地压力输水管道泄漏连续监测是可行的。     

基于神经网络的管网漏失定位实例研究

为了在复杂且不直观的供水管网中快速实时定位漏点,以某城市区域管网为对象,在其上游、中游和下游各选取3条没有经过训练的管道,进行不同损坏程度的漏损模拟,利用BP神经网络可以逼近任意的非线性映射特点,将模拟数据作为训练样本训练神经网络,建立漏损点位置与测压点压力之间的非线性关系,构建基于BP神经网络的实时漏点定位模型。结果表明,模型预测的漏点位置横纵坐标的平均相对误差分别为4.16%和1.40%,预测的漏点偏移距离最小为6 m。当漏损面积比为0.01时,泄漏流量只有1 L/s,完全可以达到快速定位。此研究成果对实际管网的应用提供了理论基础和技术支持。     

RTU系统在城市引水工程中的应用与施工技术

城市引水工程中的长途输水管线,全程各个关键点的压力监测,直接影响输水系统的安全运行与调控。利用RTU系统完成长输管线压力监测点的数据采集,并通过GPRS与供水调度监控中心组成远程数据采集和监督控制（SCADA）系统,达到引水工程全线的压力监测。以哈尔滨市磨盘山水库引水工程为例,介绍了RTU系统的构成、系统的功能描述、RTU系统工程在安装过程中的关键工艺控制。以期对RTU系统应用的工程技术和维护人员,提供一些实践经验和教训。     

ANALYSIS OF FIRST TRANSIENT PRESSURE OSCILLATION FOR LEAK DETECTION IN A SINGLE PIPELINE

The leak detection is of great importance in the reliable operation and management of a pipeline system. Recently,attention is shifted to the use of the time domain or frequency domain methods based on the transient analysis. These methodssometimes require accurate pressure signals obtained during the transient period or by creating ideal conditions in testing. This paperproposes a method that does not require transient simulations over the whole or an extended period of time, but uses the first transientpressure oscillation to detect leaks. The method considers the propagation of the pressure oscillation wave created from a fast valveclosure and the reflected damp wave from the leak. A leak in the pipe gives rise to reflected waves which in turn creatediscontinuities in the observed signal at the measurement section. The timing of the reflected damp wave and the magnituderepresent the location and the size of the leak, respectively. An analytical expression is derived based on the Method OfCharacteristic (MOC) for the relationship between the leakage and the reflected magnitude. The leak detection procedure based onthe method is also given. Then the reliability of the method is tested on numerically simulated pressure signals and experimentalpressure signals with calibrated leak parameters, and the results indicate a successful application and the promising features of themethod.