Frequency domain response characteristics and localization of transient wave-based water pipeline leakage

Detecting chronic small leak sizes can be challenging because they may not produce significant or easily noticeable changes in flow rates or pressure differentials. Therefore, specialized techniques are often required to identify and locate chronic small leaks accurately in pipeline systems. The current study aims to address this gap by developing a method to identify multiphase flow leaks in pipelines using time series analysis techniques. An experimental flow loop apparatus, featuring a 2-inch (0.0508 m) diameter and extending 22.6 feet (6.9 m) in length, has been employed to carry out our experiments. The experiments encompass a range of liquid flow rates varying between 170 and 350 kg/min and gas flow rates ranging from 10 to 60 g/min. The system was equipped with three distinct leak opening diameters, measuring 1.8 mm, 2.5 mm, and 3 mm, each separated by 90 mm. Data collected from four dynamic pressure sensors was subjected to time series analysis such as wavelet transforms to detect and pinpoint the location of pipeline leaks. The obtained results indicate that dynamic pressure sensors are effective in detecting leak scenarios, as well as distinguishing between single and multiple leaks. However, for chronic small leaks, analyzing the standalone pressure response over time is generally not sufficient for detection. Time series analysis techniques play a crucial role in accurately identifying chronic small sized pipeline leaks. Discrete Wavelet Transform (DWT) was able to identify the point of leak opening and closing. Furthermore, DWT was able to reduce the false alarms for leak and no leak situations. This study introduces the application of time series analysis on dynamic pressure to detect chronic small sized leaks in multiphase flow pipelines. Additionally, it explores the capacity of wavelet analysis to minimize the occurrence of false alarms for leak and non-leak scenarios thereby addressing crucial safety, environmental, and economic concerns.

A pipeline system is an essential component in the transport of natural gases, crude and oil products in the petroleum industry, as well as gas and water in vital utility systems. Early detection of leaks in pipelines is essential to avoid excessive economical loss and reducing the environmental and health hazards that normally result from undetected leaks. In this paper, a model-based estimation scheme, which was developed as a basis for real-time monitoring of fluid flow in pipelines, is tested experimentally. In this estimation scheme, the fluid flow in a pipeline, which is modelled by a set of non-linear partial differential equations, is represented in a state-space form. A modified extended Kalman filter (MEKF), with its internal model defined by the obtained state-space form, is invoked together with feedforward computations to establish an adaptive multimodel state estimation technique. A laboratory experimental test-rig is constructed to test the validity and effectiveness of the developed leak detection and localization scheme. Experimental results utilizing the laboratory set-up are presented to demonstrate that the developed scheme effectively detects and locates leaks in pipelines within a short time duration.

Industrial fluid pipeline leak detection and localization based on a multiscale Mann-Whitney test and acoustic emission event tracking

This research investigates the applicability of the transient-based frequency-response function (FRF) method for detecting leaks in complex series pipelines. The behaviour of transient waves in these pipelines with internal series junctions indicates that junction reflections modify the system resonant frequencies but have a small effect on the leak-induced information contained within the system frequency responses. The analogous method previously developed for single pipelines is extended to complex series pipe systems by using the analytical transfer matrix method herein and the extended method is validated by two simple numerical experimental cases consisting of 3-series pipes and 10-series pipes, respectively. The applied results indicate that the extended FRF method can be applied to detect single and multiple leaks in complex series pipelines as long as the location and size of the resonant peaks of system frequency responses are accurately determined.

The pipeline leakage detection and leak localization trouble is a highly demanding and dangerous issue. Underground pipelines are critical for transporting enormous fluid volumes (e.g., water) across extended distances. Not only would solving this issue save the nation a great deal of money and resources, but it will also save the environment. However, because of the harsh climatic conditions below earth, current leak detection systems are not enough for monitoring subterranean pipelines. To address these issues, this study suggests a hybrid wireless sensor network for monitoring subterranean pipelines that is based on magnetic induction and time domain reflectometry (TDR). TDR is installed in this instance below a wireless sensor network that is based on MI. TDR significantly reduces the time needed for inspection while accurately locating the leak. Based on MI technology, we provide a wireless sensor network for inexpensive, real-time leak detection in subterranean pipelines. Through the integration of data from several sensor types located within and around subterranean pipes, MISE-PIPE detects leaks. Ad-hoc WSNs are employed in pressure measurement. (WDNs) is a popular subject that has drawn attention from scholars lately. Since leak localisation has a significant influence on the human population and the economy, time and accuracy are essential components. A broad leak localisation technique is proposed using statistical classifiers operating in the residual space. Classifiers are trained using leak data from every node in the network, accounting for demand uncertainty, noise from sensor preservatives, and leak size. After localising and identifying leaks, all monitoring data is sent to the CH using the K-means clustering technique, which performs two vital tasks: optimum clustering, extending the Network Lifetime, and maintaining Quality of Service. The K-Means technique is used to optimise the clustering process. The K-means clustering technique is used to transfer all monitoring data to the CH for the purpose of pipeline leak identification and localisation. Unlike the current underground pipeline monitoring system, our proposed Hybrid TDR-MI-based wireless sensor network allows precise real-time leak identification and localisation.

The spectrum of impulse response signal from an impulse hammer testing is widely used to obtain frequency response function (FRF) of the structure. However the FRFs obtained from impact hammer testing have not only leakage errors but also finite record length errors when the record length for the signal processing is not sufficiently long. The errors cannot be removed with the conventional signal analyzer which treats the signals as if they are always steady and periodic. Since the response signals generated by the impact hammer are transient and have damping, they are undoubtedly non-periodic. It is inevitable that the signals be acquired for limited recording time, which causes the finite record length error and the leakage error. In this paper, the errors in the frequency response function of multi degree of freedom system are formulated theoretically. And the method to remove these errors is also suggested. This method is based on the optimization technique. A numerical example of 3-dof model shows the validity of the proposed method.

Leak detection and location in liquid pipelines by analyzing the first transient pressure wave with unsteady friction

Leak detection and localization of fluid-filled pipeline using accelerometer pairs and mode separation method

Significant water loss caused by pipeline leaks emphasizes the importance of effective pipeline leak detection and localization techniques to minimize water wastage. All of the state-of-the-art approaches use deep learning (DL) for leak detection and cross-correlation for leak localization. The existing methods’ complexity is very high, as they detect and localize the leak using two different architectures. This paper aims to present an independent architecture with a single sensor for detecting and localizing leaks with enhanced performance. The proposed approach combines a novel EMD with an optimal mode selector, an MFCC, and a two-dimensional convolutional neural network (2DCNN). The suggested technique uses acousto-optic sensor data from a real-time water pipeline setup in UTAR, Malaysia. The collected data are noisy, redundant, and a one-dimensional time series. So, the data must be denoised and prepared before being fed to the 2DCNN for detection and localization. The proposed novel EMD with an optimal mode selector denoises the one-dimensional time series data and identifies the desired IMF. The desired IMF is passed to the MFCC and then to 2DCNN to detect and localize the leak. The assessment criteria employed in this study are prediction accuracy, precision, recall, F-score, and R-squared. The existing MFCC helps validate the proposed method’s leak detection-only credibility. This paper also implements EMD variants to show the novel EMD’s importance with the optimal mode selector algorithm. The reliability of the proposed novel EMD with an optimal mode selector, an MFCC, and a 2DCNN is cross-verified with cross-correlation. The findings demonstrate that the novel EMD with an optimal mode selector, an MFCC, and a 2DCNN surpasses the alternative leak detection-only methods and leak detection and localization methods. The proposed leak detection method gives 99.99% accuracy across all the metrics. The proposed leak detection and localization method’s prediction accuracy is 99.54%, precision is 98.92%, recall is 98.86%, F-score is 98.89%, and R-square is 99.09%.

There is an increasing need for timely pipeline leak detection and localization methods, pipeline leak could lead to not only the loss of the goods but also considerable environmental and economic problems. With the rapid development of hardware and software, the pipeline leak detection and localization algorithms have been widely researched and applied in many Fields. However, traditional methods are usually limited by extracting features manually, which is inefficient and time-consuming. Convolutional neuron network is an effective method to extract features automatically. In this paper, a novel ensemble transfer learning one-dimension convolutional neural network (TL1DCNN) for the pipeline leak detection and localization is proposed. The TL1DCNN plays the role of base learner. The results of a set of obtained base learners are integrated to achieve the task of pipeline leak detection and localization. Firstly, one-dimension convolutional neural network (1DCNN) models with different parameters are pretrained with source domain data. A small learning rate is set to retrain the above 1DCNN models for target task with target domain data in order to obtain TL1DCNN base learners. Then, the four ensemble strategies with different number base learners whose ensemble weights are optimized by particle swarm optimization algorithm are obtained by minimizing the sum of similarity. The dataset simulated by pipeline network model is used to evaluate the effectiveness of the proposed approach. The indicators such as classification accuracy, precision, recall, F_score and confusion matrix are used to compare the proposed approach with traditional methods and other deep learning methods. The experimental results show that the performance of the proposed approach is superior to other compared methods.

Effective ways to improve the accuracy of liquid-filled pipeline leak detection are one of the key issues that need to be addressed urgently in a conservation-oriented society. Recently, pipeline leak detection methods based on deep learning have developed rapidly. To improve the learning ability of convolutional neural network for pipeline leak signal features and leak detection accuracy, a multi-scale residual networks (MSRNs) model is proposed in this paper for liquid-filled pipeline leak detection and localization. The model uses convolutional kernels of different scales to extract multiscale features of pipeline leakage signals based on deep residual networks (DRNs) and uses fully connected layers to fuse the features, thus improving the accuracy of pipeline leakage detection and localization. Among them, the large convolution kernel can acquire the low-frequency information of the signal due to its sizable perceptual field, the medium convolution kernel can capture the local and global features of the signal, and the small convolution kernel is more sensitive to the high-frequency information of the signal. Meanwhile, a pipeline leakage test platform is built to evaluate the proposed model. The test results show that the accuracy of leak detection and localization of MSRN model is 98.3%, which is better than that of single-scale DRN model. In addition, the proposed MSRN model is verified to have good generalization and noise immunity through testing and analyzing the leakage signals under different pressures and background noises.

At present, hydrocarbon leaks, generated mainly by corrosion of pipelines, cause large economic losses for Mexico. These leaks constitute a problem of serious consequences in Mexico and in other countries in the world. This work describes the results of the tests conducted on a new sensor cable for the detection and location of leaks in pipelines for transportation of hydrocarbons. When a liquid or gas enters in contact with the wall of the sensor cable, it causes a short circuit in the wires; changing the measurement of the resistance may detect and locate the leak. The new sensor cable that is presented in this article has advantages over cables with similar characteristic made in other countries. The use of this sensor cable in pipelines of PEMEX will avoid economic losses, environmental damage and risks of possible explosions to the population. The experimental results demonstrate these advantages.

When multiple leaks occur at the same time, the influence of leak acoustic wave signals is superposed in the leak acoustic wave signal, which affects the propagation and attenuation rule of the transient acoustic signal. The traditional leak localization method is impossible to effectively locate the multiple leak signals under the condition of mixed signal. Thus, a localization method of multiple leaks based on time-frequency analysis of acoustic wave and improved differential evolution is proposed. Since the decomposition model number of Variational Mode Decomposing (VMD) affects the feature extraction, the energy function is used to improve VMD (IVMD). Therefore, the decomposition model number of VMD is determined by energy function of each component. The IVMD is applied to acoustic wave analysis and processing. Additionally, the number of multiple leaks is extracted by Time-frequency Analysis (TFA). Then, the multiple leaks localization function is obtained. Differential Evolution (DE) is easy to fall into local optimum, and its convergence speed is slow in the later stage of evolution, Particle Swarm Optimization Algorithm (PSO) is used to improve the global convergence speed of DE, and the multiple leaks positions are calculated by improved differential evolution. By analyzing the acquired acoustic wave data of multiple leaks in experimental pipeline wtih acoustic sensor PCB 106B, the results show that the proposed method can accurately locate multiple leaks in pipeline, and the minimum error of leak localization is 18 m.

A novel pipeline leak detection and localization method based on the FBG pipe-fixture sensor array and compressed sensing theory

Pipeline leakage seriously threatens the efficient and safe gas drainage in coal mines. To achieve the accurate detection and localization of gas drainage pipeline leakages, this study proposes a gas drainage pipeline leakage detection and localization approach based on the pressure gradient method. Firstly, the basic law of gas flow in the drainage pipeline was analyzed, and a pipeline network resistance correction formula was deduced based on the pressure gradient method. Then, a drainage pipeline model was established based on the realizable k-ε turbulence model, and the pressure and flow velocity distribution during pipeline leakage under different leakage degrees, leakage locations, and pipeline negative pressures were simulated and analyzed, thus verifying the feasibility of the pipeline leakage detection and localization method. It is concluded that the positioning errors of pipeline leakage points under different leakage degrees, different leakage positions, and different pipeline negative pressures were 0.88~1.08%, 0.88~1.49%, and 0.68~0.88%, respectively. Finally, field tests were conducted in the highly located drainage roadway 8421 of the Fifth Mine of Yangquan Coal Industry Group to verify the accuracy of the proposed pipeline leakage detection and localization method, and the relative error was about 8.2%. The results show that with increased pipeline leakage hole diameters, elevated pipeline negative pressures, and closer leakage positions to the pipeline center, the relative localization error was smaller, the localization accuracy was higher, and the stability was greater. The research results could lay the foundation for the fault diagnosis and localization of coal mine gas drainage pipeline networks and provide technical support for safe and efficient coal mine gas drainage.