基于广义概念的城市燃气管道泄漏精确定位

为了准确地检测城市燃气管道泄漏,提出了一种基于广义概念的管道泄漏检测定位方法。声发射技术对于管道泄漏的检测、定位是一个极好的工具,但由于泄漏源的传播容易受到周围背景噪声以及复杂工况的影响,其定位误差较大。基于时延估计的互相关信号处理方法被广泛用于管道泄漏检测定位,但由于泄漏应力波传播通道的动态特性,使得源信号在传播过程中会产生波形变化,给互相关函数峰值位置的确定带来困难。由此引入广义相关分析方法,通过对信号进行前置滤波,在一定程度上减少了传播通道动态特性因素对泄漏点定位的不利影响,得到了更为准确的时延估值。在此基础上,通过模拟实验,编写Matlab神经网络代码,构造GRNN模型,进一步预测定位。结果表明,GRNN预测的声发射检测值、互相关定位值以及广义相关定位值,相比之前定位精度分别得到提高,其中基于广义相关的延时估计方法定位最为精确,将该方法用于工程实际中,可以更加精确地定位出泄漏点。     

基于EMD-HHT可定位长输天然气管道第三方破坏事件监测技术*

为适应目前管道安全监测需要,满足对扰动信号分类监测的实际需求,提出1种基于希尔伯变换和经验模态分解（EMD-HHT）的信号特征提取技术,利用基于φ-OTDR分布式光纤传感系统采集振动信号,通过EMD+HHT区分算法对管道沿线振动事件进行分解并提取6个典型特征向量,各特征事件数据经过EMD后选取IMF3为最终提取特征向量的原始数据,BP神经元网络可有效识别机械破坏、敲击破坏、车辆经过、人工挖掘、动力干扰5种事件。研究结果表明:在长输管道信号识别中,BP神经网络对5类事件平均识别率高达98.6%,该技术分类识别5类事件扰动信号,能够达到较高准确性,并且误报率平均在1.3%,能较好满足现场安全实时监测需求。研究结果对长输油气管道附近第三方破坏扰动信号分类监测具有一定参考意义。     

Image rotation method for identification of NPW signals in the localization of pipeline leakage

Gas and oil are mainly transported through long-distance pipelines on land. Pipeline leaks lead to severe hazards to the environment and economy and even imperil human lives. Negative pressure wave (NPW)-based methods are fast and effective for leak monitoring and localization. The key problem for an NPW-based method is to determine the NPW and its arrival time, which is characterized by the knee point in the time domain signal. In this paper, an image rotation method is proposed based on the shape characteristic of the time domain signal induced by an NPW. Through image rotation, the knee point turns into the highest point, which is easy to detect. To verify the performance of the proposed method, leakage experiments were conducted on liquid and gas pipeline models. Previously developed FBG pipe fixture sensors were used to detect an NPW. These sensors were equidistantly installed on the pipeline, forming a sensor array. Based on the sensing array, a novel leak localization algorithm was used to compute the leakage position. The experimental results indicated that the image rotation method has good performance for identifying an NPW, even though many noise- and pressure-induced fluctuations exist in the signals. This method enables automated real-time monitoring and has potential for practical application.     

Probabilistic multiple model neural network based leak detection system: Experimental study

This paper presents an effective decision making system for leak detection based on multiple generalized linear models and clustering techniques. The training data for the proposed decision system is obtained by setting up an experimental pipeline fully operational distribution system. The system is also equipped with data logging for three variables; namely, inlet pressure, outlet pressure, and outlet flow. The experimental setup is designed such that multi-operational conditions of the distribution system, including multi pressure and multi flow can be obtained. We then statistically tested and showed that pressure and flow variables can be used as signature of leak under the designed multi-operational conditions. It is then shown that the detection of leakages based on the training and testing of the proposed multi model decision system with pre data clustering, under multi operational conditions produces better recognition rates in comparison to the training based on the single model approach. This decision system is then equipped with the estimation of confidence limits and a method is proposed for using these confidence limits for obtaining more robust leakage recognition results.     

油气管道位移光纤安全监测技术定位理论及预警信号特征研究

管道安全分布式光纤监测系统利用分布式光纤振动传感器两端检测信号的时间差确定管道沿线所发生事件位置,时间差的精度决定对异常事件事发点的定位精度;系统拥有较高的灵敏度,可对1.5 km内敲击、落石、滚石及人工挖掘等威胁管道安全的事件进行报警;事件的定位有一定的误差,对抢修有一定的指导意义。     

Integrated-signal-based leak location method for liquid pipelines

Leaks in pipelines can cause major incidents resulting in both human injuries and financial losses. Among the considerable leak detection and location methods, the Negative Pressure Wave (NPW) based method has been widely used in locating leaks in liquid pipelines. The NPW based method only monitors the pressure changes at two ends of a pipeline. But the pressure is apt to be fixed by the end equipment and the change of it induced by a small or slow leakage is too small to be detected, which limit the application of the NPW based method in these situations. This paper presents a novel leak location method based on integrated signal, which is a combination of the pressure and flow rate signals. The representation of the integrated signal is derived from the transient analysis of the leakage. For the change of the integrated signal induced by a leakage is larger than the pressure change and it is also unaffected by the end equipment, the proposed method can be used to detect and locate small or slow leakage in a pipeline and can also be used in pipelines which end pressures are fixed by some kinds of equipment. The validation of the proposed method also confirms its advantages.     

Leak detection for long transportation pipeline using a state coupling analysis of pump units

Leak detection for long transportation pipeline with a large economic and environmental impact has been an area of intensive research for more than five decades. This paper presents a novel pipeline leak detection scheme based on a state coupling analysis (SCA). Instead of monitoring the pipeline and pump units separately, SCA introduces a new detecting method of analyzing data in a coupling running condition. A novel capture method for abnormal pressure based on logical reasoning algorithm is proposed. Hamming approach degree arithmetic is applied to calculate the matching mode identifying the state of units. SCA is used to reduce the rate of false alarm and detect the leak with a high detecting sensitivity for long transportation pipeline. An on-line software system based on SCA is utilized to achieve superior accuracy and implementation. An industrial case study for coupling system pipeline leak detection is used as an example to validate the effectiveness of the proposed method.     

Detection of small leakage from long transportation pipeline with complex noise

In the long distance pipeline remote monitoring system, small leak detection becomes an important issue. Weak singularities in small leak signals are usually difficult to detect precisely under complicated noise background, which may cause false alarm or miss alarm. The advantage of applying the harmonic wavelet method is explored in this paper. Pipeline small leak sensitive characteristics are recognized and the negative pressure wave inflexions are extracted by harmonic wavelet analysis, expressed in terms of harmonic wavelet time-frequency mesh map, time-frequency contour map, and time-frequency profile plot. This paper also presents a comparative study of both Daubechies wavelet and harmonic wavelet analysis when applied to pipeline small leak detection under complicated background noises. Results of simulating test and field experiment show that it is possible to distinguish weak non-stationarities from complicated noises by harmonic wavelet analysis in pipeline small leak detection system. The comparison clearly illustrates that harmonic wavelet based pipeline small leakage detection method is significantly more accurate than other wavelets analysis such as Daubechies wavelet. This work provides a reliable and safe guarantee for oil and gas long distance transportation, reducing petroleum product losses and protecting surrounding environment.     

Leak location of pipelines based on characteristic entropy

The leakage of oil/gas pipelines is one of the major factors to influence the safe operation of pipelines. So it is significant to detect and locate the exact pipeline leakage. A novel leak location method based on characteristic entropy is proposed to extract the input feature vectors. In this approach, the combination of wavelet packet and information entropy is called “wavelet packet characteristic entropy” (WP-CE). The combination of empirical mode decomposition and information entropy is called “empirical mode decomposition characteristic entropy” (EMD-CE). Both pressure signal and flow signal of low noise and high noise of pipeline leakage are decomposed to extract the characteristic entropy. The location of pipeline leak is determined by the combination of the characteristic entropy as the input vector and particle swarm optimization and support vector machine method (PSO-SVM). The results of proposed leak location method are compared with those of PSO-SVM based on physical parameters. Under the condition of high noise, the results of proposed leak location method are better than those of PSO-SVM based on physical parameters.     

基于声信号特征分析的燃气管道探测识别方法

为了探测和辨识地下燃气管道,避免燃气管道改扩建的过程发生第三方破坏引发安全事故,提出1种基于声信号特征分析的燃气管道探测识别方法,该方法考虑燃气管道声信号声压级低以及易衰减的特点,采用Hilebert-Huang变换算法分析燃气管道流噪声信号特征,建立燃气管道流噪声信号的特征数据库,并通过BP神经网络进行模式识别,判别...     

Acoustic detection technology for gas pipeline leakage

Gas leakage from pipeline leads to significant environmental damages and industrial hazards, so small leakage detection for gas pipeline is essential to avoid these serious leakages. However, because of the high frequency component of leakage signal attenuates quickly, traditional detection method which inspects pressure or vibration signal has problem to get effective information from leakage signal. So, a novel detection method based on acoustic wave is proposed. This paper, firstly, researches on the phonation principle of pipeline leakage and the characteristic of sound source, and simulates the leakage acoustic field on the basis of aero acoustics. Secondly, using Wavelet Packet Transform method and Fuzzy Support Vector Machine pattern classification, the laboratory testing for identifying acoustic signal of gas pipeline leakage is presented. Finally, the field application demonstrates that the detection system could identify small gas leakage effectively and avoids false-alarms which caused by running conditions with a good prospect.     

Experimental study on leak detection and location for gas pipeline based on acoustic method

The leak of gas pipelines can be detected and located by the acoustic method. The technologies of recognizing and extracting wave characteristics are summarized in details in this paper, which is to distinguish leaking and disturbing signals from time and frequency domain. A high-pressure and long distance leak test loop is designed and established by similarity analysis with field transmission pipelines. The acoustic signals collected by sensors are de-noised by wavelet transform to eliminate the background noises, and time-frequency analysis is used to analyze the characteristics of frequency domain. The conclusion can be drawn that most acoustic signals are concentrated on the ranges of 0-100 Hz. The acoustic signal recognition and extraction methods are verified and compared with others and it proves that the disturbing signals can be efficiently removed by the analysis of time and frequency domain, while the new characteristics of the accumulative value difference, mean value difference and peak value difference of signals in adjacent intervals can detect the leak effectively and decrease the false alarm rate significantly. The formula for leak location is modified with consideration of the influences of temperature and pressure. The positioning accuracy can be significantly improved with relative error between 0.01% and 1.37%.     

A wave change analysis (WCA) method for pipeline leak detection using Gaussian mixture model

This paper presents a novel pipeline leak detection scheme based on gradient and slope turns rejection (GSTR). Instead of monitoring the pipeline under constant working pressure, GSTR introduces a new testing method which obtains data during the transient periods of different working pressures. A novel pipeline leak detection method based on those transient data without failure history is proposed. Wavelet packet analysis (WPA) is applied to extract features which capture the dynamic characteristics from the non-stationary pressure data. Principal component analysis (PCA) is used to reduce the dimension of the feature space. Gaussian mixture model (GMM) is utilized to approximate the density distribution of the lower-dimensional feature space which consists of the major principal components. Bayesian information criterion (BIC) is used to determine the number of mixtures for the GMM and a density boosting method is applied to achieve better accuracy of the distribution estimation. An experimental case study for oil pipeline system is used as an example to validate the effectiveness of the proposed method.     

ARX modeling approach to leak detection and diagnosis

This work presents a time series strategy for detection, location and quantification of leaks in large pipeline systems. The technology has two active components, which operate sequentially: the Detector and the Localizer. The Detector continuously screens real-time data, searching for any anomalies such as leaks, which are detected (or not) depending on their size and position. The Detector is based on auto-regressive multi-input/multi-output (MIMO) ARX predictors with one input filter. Subsequent to successful leak detection, the Localizer is launched to diagnose the leak via estimation of its parameters – diameter and location – using recorded data on a Search Time Window that includes information in the neighborhood of the instant of detection. The Localizer is also an ARX predictor, but with two input processors, the first is a filter for dynamic plant inputs and the second filter processes “parameter signals” of active leaks. The Localizer is developed beforehand via model identification with plant data under the action of known, artificially simulated, leaks. It is, therefore, able to recognize an active pattern of leak parameters, by maximizing the adherence of its predictions to data in the Search Time Window. The proposed detection and location methods were successfully tested in simulated leak scenarios for an industrial naphtha pipeline.     

Numerical and experimental study on the generation and propagation of negative wave in high-pressure gas pipeline leakage

Negative-wave-based leakage detection and localization technology has been widely used in the pipeline system to diminish leak loss and enhance environmental protection from hazardous leak events. However, the fluid mechanics behind the negative wave method has yet been disclosed. The objective of this paper is to investigate the generation and propagation of negative wave in high-pressure pipeline leakage. A three-dimensional computational fluid dynamic (CFD) study on the negative wave was carried out with large eddy simulation (LES) method. Experimentally validated simulation presented the transient wave generation at the leak onset and the comprehensive wave evolution afterwards. Negative wave was proven to be a kind of rarefaction acoustic waves induced by transient mass loss at the onset of leakage. Diffusion due to the density difference at wave fronts drives the negative wave propagation. Propagation of negative wave can be categorized into three states – semi-spherical wave, wave superposition and plane wave, based on different wave forms. The wave characteristics at different states were elucidated and the attenuation effects were discussed respectively. Finally, a non-dimensional correlation was proposed to predict the negative wave amplitude based on pipeline pressure and leak diameter.     

Fault diagnosis of pipeline and pump unit systems using status coupling analysis

Earlier studies on fault diagnosis of the pipeline and pump unit systems (PPU) relied mainly on independent equipment analyses, which usually lead to false alarms because of the loss of information fusion. The aim of this study is to utilize the status coupling relationship to improve fault detection sensitivity and reduce false alarm rate. A real-time status identification of related equipment step is added between capturing abnormal signals and listing out diagnosis results. For example, when the pipeline pressure fluctuation is found abnormal, a status analysis of pump units is performed immediately, if the pump units are proven to be operational normally, then the pipeline leak alarm is acknowledged valid. The logical reasoning algorithm is used to capture abnormal conditions of pipeline pressures. The pump unit faults are captured by combining information from multiple sources. Field applications show that the proposed method significantly improves the PPU fault detection capability on fault detection sensitive and accuracy.     

基于微型惯性传感器的井下人员跟踪定位系统*

为了解决当前煤矿井下使用的WIFI人员定位系统在煤矿井下复杂环境中受到干扰,造成使用精度误差等问题,研究并提出使用微型惯性传感器制作足部轨迹测量传感器,通过惯性轨迹测量算法计算并跟踪井下人员的移动轨迹。使用基于固定阈值的零速检测技术和基于Kalman滤波的零速校正技术估计并校正由于系统长期工作造成的偏移误差。通过实验证明采用微型惯性传感器能够在不依赖于外部传感器的情况下对人员轨迹实现测量跟踪,Kalman滤波的应用能够减少惯性轨迹测量系统造成的长期漂移误差,可避免井下复杂工作环境对定位造成的干扰。     

基于时序片段的油气管道运行工况识别方法*

为准确识别管道系统运行工况,提高对油气管道突发事故的响应速度,综合提升管网安全管理水平,提出1种基于时序片段的油气管道运行工况识别方法。首先,构建基于概率分布的状态变化识别模型,提取油气管道中不同运行状态点;其次,建立基于时间序列片段的工况识别模型,快速识别不同时间长度内油气管道运行工况;最后,以国内某成品油管道为例进行方法验证。研究结果表明:该方法可有效识别成品油管道阀门开关状态、泵异常停机和阀门内漏3种运行工况。对比传统的识别方法,该方法可降低状态变化点的漏报率,提升管道运行工况识别的准确率。研究结果可为油气管道系统运行工况识别提供新的借鉴方法。     

基于一维卷积神经网络的燃气管道泄漏声发射信号识别*

为保障燃气管道系统安全运行,及时诊断管道故障,基于VGG-16模型提出基于一维卷积神经网络的燃气管道故障诊断模型,提取原始声发射信号特征参数,有效诊断燃气管道故障。结果表明:基于一维卷积神经网络的燃气管道故障诊断模型,能够有效解决燃气管道故障诊断过程中数据预处理复杂、特征提取困难以及识别准确率低等问题,可为燃气管道故障诊断提供技术支撑。     

Real-time leak detection in oil pipelines using an Inverse Transient Analysis model

Based on Inverse Transient Analysis (ITA) method, a real-time leak detection method is proposed to capture leak location and the associated leak rate in oil pipe conveyance systems. In the proposed approach, location and flow rate of leak (if any), the fluid properties, as well as physical parameters of the system, are calculated in consecutive periods through minimizing the discrepancy between the calculated and measured flow parameters of the system. The method of characteristics is employed to numerically calculate the transient responses of the system and the genetic algorithm is utilized as the optimization engine. The proposed approach was applied to several real pipeline systems in which the required transient flow data are either directly collected from the field or fabricated with a third-party numerical software. Extensive numerical explorations were conducted to investigate the performance of the proposed method in real-time leak detection and to determine the extent to which field data errors, stemming from Supervisory Control and Data Acquisition (SCADA) systems and measurement equipment, affect the leak flow rate and location detectability of the proposed approach. The results show that the proposed approach provides promising results under a variety of transient and steady-state flow conditions even in the case with small leak flow rate of around 2% of the line rate. The results also reveal that the noises in the measurement data and the errors originated from SCADA systems do not significantly compromise the leak detectability of the proposed approach, confirming that the proposed approach can be utilized in practice.