Leak Detection Method Research Articles

Development of a shortwave infrared sinuscope for the detection of cerebrospinal fluid leaks.

Cerebrospinal fluid (CSF) rhinorrhea (leakage of brain fluid from the nose) can be difficult to identify and currently requires invasive procedures, such as intrathecal fluorescein, which requires a lumbar drain placement. Fluorescein is also known to have rare but significant side effects including seizures and death. As the number of endonasal skull base cases increases, the number of CSF leaks has also increased for which an alternative diagnostic method would be highly advantageous to patients. We aim to develop an instrument to identify CSF leaks based on water absorption in the shortwave infrared (SWIR) without the need of intrathecal contrast agents. This device needed to be adapted to the anatomy of the human nasal cavity while maintaining low weight and ergonomic characteristics of current surgical instruments. Absorption spectra of CSF and artificial CSF were obtained to characterize the absorption peaks that could be targeted with SWIR light. Different illumination systems were tested and refined prior to adapting them into a portable endoscope for testing in 3D-printed models and cadavers for feasibility. We identified CSF to have an identical absorption profile as water. In our testing, a narrowband laser source at 1480nm proved superior to using a broad 1450nm LED. Using a SWIR enabling endoscope set up, we tested the ability to detect artificial CSF in a cadaver model. An endoscopic system based on SWIR narrowband imaging can provide an alternative in the future to invasive methods of CSF leak detection.

Cyber-Physical System for Diagnostic Along the Controlled Section of the Oil Pipeline

The purpose of the work is to develop an experimental model of the control system for compliance with turns along the control length of the pipeline. The open issue of detecting oil product leaks along the controlled section of the pipeline. Preliminary analysis of leak detection methods and principles of operation of hardware and software security diagnostics of the state of pipe transport networks has been considered. A method of studying experimental data and presenting results has been developed. Different literature sources have been analyzed, these literature sources provide information about real cases of pipeline system diagnostics and leak or defect detection. The software and hardware part of the control systems for conducting checks along the control part of the pipeline have been developed, and checks and evaluations of the results of the system checks have been carried out.

Pipeline leak detection method based on acoustic-pressure information fusion

Pipeline leak detection method based on acoustic-pressure information fusion

Improved Leakage Detection Generalization Ability for Multiscenes Deployment in Industry

In the unattended industrial environment, the piping leakage detection algorithm based on the combination of image detection and machine learning has the advantages of high sensitivity and reliability. However, there are some problems in the practical application, such as a large number of industrial leakage scenes to be detected, a big spatial feature gap between the deployed scenes and the undeployed scenes and the unpredictable actual leakage situation. These cause a significant decrease in the accuracy and reliability of vision-based piping leakage detection models during large-scale multi-scenes industrial deployment. To solve the above problems, we propose a piping leakage detection method with domain generalization (DG) capability. First, we use the adaptive color recovery multi-scale Retinex (AMSRCR) to enhance the spatial features and improve the image quality of leakage liquid which is colorless and transparent. Based on the idea of DG we design the structure of DCM-DenseNet121, which can improve the generalization ability of the model by learning the domain invariant features of the leakage liquid and solve the problem of decreasing accuracy in large-scale multi-scenes deployment. The experiment results show that the leakage detection balanced accuracy achieve 99.7% when inferring on three target scenes. Furthermore, our model achieves efficient detection, maintains a relatively lightweight when performing in extra-domain target scenes and satisfies the industrial field bandwidth limitations.

Multizone Leak Detection Method for Metal Hose Based on YOLOv5 and OMD-ViBe Algorithm

It is necessary to determine the location and number of leaks in a pipeline in time to repair it, thus reducing economic losses. A multizone leakage detection method based on the YOLOv5 and OMD-ViBe algorithm is proposed to detect the metal hose’s location and leakage rate. The deep learning model of YOLOv5 is used to accurately recognize the zone of the metal hose for the region of interest rectification. The multiframe averaging method is applied to construct the initial background of the video frames. The OTSU algorithm based on the background difference method and the adaptive threshold of the maximum intraclass and interclass variance ratio method is used to improve the recognition rate of bubbles and reduce the influence of illumination change. In a comparison with the existing algorithms, the experimental results showed that OMD-ViBe improves the F-measure by 1.79–16.41% and the percentage of misclassification by 0.003–0.165%. Analysis of the pressure data indicated a comprehensive leakage error reduction of 1.53–25.19%, which can meet the requirements of metal hose leakage detection.

A reliability-oriented genetic algorithm-levenberg marquardt model for leak risk assessment based on time-frequency features

Since leaks in high-pressure pipelines transporting crude oil can cause severe economic losses, a reliable leak risk assessment can assist in developing an effective pipeline maintenance plan and avoiding unexpected incidents. The fast and accurate leak detection methods are essential for maintaining pipeline safety in pipeline reliability engineering. Current oil pipeline leakage signals are insufficient for feature extraction, while the training time for traditional leakage prediction models is too long. A new leak detection method is proposed based on time-frequency features and the Genetic Algorithm-Levenberg Marquardt (GA-LM) classification model for predicting the leakage status of oil pipelines. The signal that has been processed is transformed to the time and frequency domain, allowing full expression of the original signal. The traditional Back Propagation (BP) neural network is optimized by the Genetic Algorithm (GA) and Levenberg Marquardt (LM) algorithms. The results show that the recognition effect of a combined feature parameter is superior to that of a single feature parameter. The Accuracy, Precision, Recall, and F1score of the GA-LM model is 95%, 93.5%, 96.7%, and 95.1%, respectively, which proves that the GA-LM model has a good predictive effect and excellent stability for positive and negative samples. The proposed GA-LM model can obviously reduce training time and improve recognition efficiency. In addition, considering that a large number of samples are required for model training, a wavelet threshold method is proposed to generate sample data with higher reliability. The research results can provide an effective theoretical and technical reference for the leakage risk assessment of the actual oil pipelines.

Leak Detection in Natural Gas Pipelines Based on Unsupervised Reconstruction of Healthy Flow Data

Summary Timely detection of leak accidents plays an essential role in the safe operation and risk assessment of natural gas pipelines. However, the scarce leak data and complex operating conditions lead to small samples, data imbalance, and problems with confusing operating conditions. The reliance on leak data limits the recognition performance of the artificial intelligence classification method for leakage operating conditions. A leak detection method based on the unsupervised reconstruction of healthy flow data is established to address these problems. First, an unsupervised neural network is established to reconstruct healthy flow data from real natural gas pipelines. And a model update strategy based on active learning is designed to improve the model’s adaptability for time-varying pipelines. Next, a dynamic alarm threshold strategy that accounts for the knowledge of the experience and statistical characteristics of the data segments is suggested to prevent false alarms caused by ambiguous operating conditions. Finally, unlike most recent work that only considers simulated data or laboratory data, this paper conducts a leak case study on an actual natural gas pipeline in service to improve the robustness of the proposed method in the actual operating environment. The findings of this paper can be used as a reference to analyze pipeline behavior analysis based on pipeline flow trend characteristics and early alarm management.

Evaluation of Hydrogen Blend Stability in Low-Pressure Gas Distribution

Natural gas distribution companies are developing ambitious plans to decarbonize the services that they provide in an affordable manner and are accelerating plans for the strategic integration of renewable natural gas and the blending of green hydrogen produced by electrolysis, powered with renewable electricity being developed from large new commitments by states such as New York and Massachusetts. The demonstration and deployment of hydrogen blending have been proposed broadly at 20% of hydrogen by volume. The safe distribution of hydrogen blends in existing networks requires hydrogen blends to exhibit similar behavior as current supplies, which are also mixtures of several hydrocarbons and inert gases. There has been limited research on the properties of blended hydrogen in low-pressure natural gas distribution systems. Current natural gas mixtures are known to be sufficiently stable in terms of a lack of chemical reaction between constituents and to remain homogeneous through compression and distribution. Homogeneous mixtures are required, both to ensure safe operation of customer-owned equipment and for safety operations, such as leak detection. To evaluate the stability of mixtures of hydrogen and natural gas, National Grid experimentally tested a simulated distribution natural gas pipeline with blends containing hydrogen at up to 50% by volume. The pipeline was outfitted with ports to extract samples from the top and bottom of the pipe at intervals of 20 feet. Samples were analyzed for composition, and the effectiveness of odorant was also evaluated. The new results conclusively demonstrate that hydrogen gas mixtures do not significantly separate or react under typical distribution pipeline conditions and gas velocity profiles. In addition, the odorant retained its integrity in the blended gas during the experiments and demonstrated that it remains an effective method of leak detection.

GIS-Based Identification of Locations in Water Distribution Networks Vulnerable to Leakage

The detection of leakages in Water Distribution Networks (WDNs) is usually challenging and identifying their locations may take a long time. Current water leak detection methods such as model-based and measurement-based approaches face significant limitations that impact response times, resource requirements, accuracy, and location identification. This paper presents a method for determining locations in the WDNs that are vulnerable to leakage by combining six leakage-conditioning factors using logistic regression and vulnerability analysis. The proposed model considered three fixed physical factors (pipe length per junction, number of fittings per length, and pipe friction factor) and three varying operational aspects (drop in pressure, decrease in flow, and variations in chlorine levels). The model performance was validated using 13 district metered areas (DMAs) of the Sharjah Electricity and Water Authority (SEWA) WDN using ArcGIS. Each of the six conditioning factors was assigned a weight that reflects its contribution to leakage in the WDNs based on the Analytic Hierarchy Process (AHP) method. The highest weight was set to 0.25 for both pressure and flow, while 0.2 and 0.14 were set for the chlorine and number of fittings per length, respectively. The minimum weight was set to 0.08 for both length per junction and friction factor. When the model runs, it produces vulnerability to leakage maps, which indicate the DMAs’ vulnerability classes ranging from very high to very low. Real-world data and different scenarios were used to validate the method, and the areas vulnerable to leakage were successfully identified based on fixed physical and varying operational factors. This vulnerability map will provide a comprehensive understanding of the risks facing a system and help stakeholders develop and implement strategies to mitigate the leakage. Therefore, water utility companies can employ this method for corrective maintenance activities and daily operations. The proposed approach can offer a valuable tool for reducing water production costs and increasing the efficiency of WDN.

Automated leakage detection method of pipeline networks under complicated backgrounds by combining infrared thermography and Faster R-CNN technique

Leakage detection is essential to process safety and loss prevention of pipeline networks. As one of the attractive methods for detecting leakages in single pipelines, infrared thermography (IRT) faces new challenges for leakage detection of pipeline networks. Compared with the single pipeline, the pipeline network has a complicated structure with higher topology features and diverse material composition. In addition, the environment of the pipeline network is complex and changeable. These factors increase the complexity of the infrared (IR) thermal images of pipeline networks, which makes the leakage features too weak to be detected via naked-eye observation in an efficient and precise manner. To address this issue, this study develops an automated detection method for pipeline network leakages under complicated background, which is achieved by combining IRT with the Faster Region-based Convolutional Neural Network (Faster R-CNN) technique. First, the pipeline network system in the complicated background is designed for IR thermal image acquisition and data analysis. Then, an automated leakage detection model is built based on Faster R-CNN, which uses a modified VGG16 network for feature extraction for its outstanding performance in the feature extraction of small objects under complicated backgrounds. Finally, the high efficiency and precision of the proposed method for automated detection of pipeline network leakages in complicated backgrounds are verified by extensive experiments. Meanwhile, the generalization ability of the proposed method is verified by conducting experiments under various experimental conditions (different moments all-day, different viewing angles of IR camera, pedestrian disturbing). In general, the proposed method provides a promising way to detect pipeline network leakages in complicated backgrounds.

A Review of Leak Detection Systems for Natural Gas Pipelines and Facilities

Pipelines facilities, used for the transportation of natural gas in large quantities to homes and industries, remain the best economic, most reliable and safest mode of transport of energy. Despite these numerous advantages, gas pipelines have been enmeshed in various accidents and thefts, nonetheless this could be reduced if properly maintained and pipelines can last indefinitely without leaks. Pipelines are susceptible to leakages and rupture accidents as a result of age, corrosion, material defects, operational errors or other reasons. Pipeline failures may be caused intentionally (e.g. vandalism) or unintentionally (e.g. device/material failure and corrosion), which may result into irreversible damages such as financial losses, human casualties, ecological disaster and extreme environmental pollution. Leakages in natural gas facilities and installations require three vital aspects, namely: Gas Leakage Prevention, Gas Leakage Detection and Gas Leakage Mitigation. Many Gas Leak Detection methods are used for pipeline integrity management and especially for minimizing gas leakage. The performance of these methods depends on the approaches, operational conditions and pipeline networks. Also, there are some essential requirements and guidelines which must be met before we can consider any leak detection system suitable for production solutions, including sensitivity, reliability, accuracy and robustness. The attempt of this study is to carry out a critical review of these models, to ascertain the best model(s) applicable to natural gas leak detection. Keywords: Gas Leak Detection System, Leak Location, Leak Size DOI: 10.7176/JETP/13-2-02 Publication date: April 30 th 2023

Study on a temperature change phenomenon of gas flow into a negatively-pressured canister

We have been investigating methods for detecting gas leaks from the canister of the concrete cask, which stores spent fuel, by using a temperature change of the canister surface at the time of the leak. This time, we investigated a temperature change inside and outside the canister when gas flowed into due to loss of containment in a negatively-pressured canister by using a small canister model with a simplified internal structure. The kind of internal gas, initial pressure conditions, gas mixing conditions, and a heat rate were used as parameters to clarify the temperature change phenomenon inside and outside the canister before and after the leak at negative pressure. Furthermore, the sensitivity of the leak detection method using the temperature change of the canister surface under each experimental condition was examined, and its practicability to the negatively-pressured canister was confirmed. In the case of the negative pressure, there is a concern that air may enter the canister and oxidize the fuel at loss of containment of the canister. However, using a double wall canister with inert gas filled between the canisters would solve this concern.

Leakage Detection in Water Distribution Networks Based on Multi-Feature Extraction from High-Frequency Pressure Data

Leakage detection is an important task to ensure the operational safety of water distribution networks. Leakage characteristic extraction based on high-frequency data has been widely used for leakage detection in experimental networks. However, the accuracy of single-feature-based methods is limited by the interference of background pressure fluctuations in networks. In addition, the setting of leakage diagnosis thresholds has been insufficiently studied, but influences leakage detection performance greatly. Hence, a new method of leakage detection is proposed based on multi-feature extraction. The multi-features of leakage are composed of instantaneous characteristics (ICs) and trend characteristics (TCs), which constitute comprehensive leakage information. The levels of the instantaneous and trend pressure drops in background pressure fluctuations in network environments are quantified for the setting of leakage diagnosis thresholds. In addition, ICs and TCs are used for leakage degree prediction. The proposed method was applied to an experimental network. Compared with the single-feature-based method and the cumulative sum (CUSUM) method, the proposed method achieved increases of 6.01% and 13.66% in F-Scores, respectively, and showed better adaptability to background pressure fluctuations in complex network environments.

Early Detection and Identification of Damage in In-Service Waterworks Pipelines Based on Frequency-Domain Kurtosis and Time-Shift Coherence

Buried pipelines, such as waterworks pipelines, are critical for transmitting essential resources and energy in modern cities, but the risk of pipeline failure, especially due to third-party interference, is a major concern. While various studies have focused on leak detection in waterworks pipelines, research on preventing impact damage is limited. To address this issue, this study proposes a novel algorithm that utilizes energy and similarity measurements for impact detection and compares it theoretically to existing leak-detection methods. The proposed algorithm utilizes frequency-domain kurtosis to determine the frequency band on which the energy of the impact signals is concentrated, along with a time-shift coherence function to measure the similarity of the signals. The application of the source location using the filtered signals enables accurate detection of the location of third-party interference. The proposed algorithm aims to ensure the safety and to prevent failures of buried pipelines. To verify the feasibility of the proposed algorithm, an excavation experiment using a backhoe was conducted on an in-service waterworks pipeline with a diameter of 2200 mm and a burial depth of 3 m. This experiment confirmed the effectiveness of the proposed algorithm in preventing failures of buried pipelines and demonstrated its practical applicability in the field. The experiment also validated the algorithm’s ability to detect third-party interference damage at various points.

Acoustic detection and localization of gas pipeline leak based on residual connection and one-dimensional separable convolutional neural network

The leakage of natural gas pipelines may cause significant safety accidents and cause severe economic losses to society. Therefore, timely detection and location of pipeline leak is an effective measure to reduce losses. Traditional methods need to extract the leak features from signals and then input them into convolutional neural networks to realize leakage diagnosis, which is a tedious process. This paper proposes a pipeline leak detection method based on residual connections and one-dimensional separable convolutional neural network (1D-RC-SCNN) and optimizes the structure and parameters of the model. The model uses one-dimensional separable convolution to replace the traditional convolutional neural network, which effectively reduces the number of model parameters. The improved residual connection can prevent the training data from overfitting and speed up the model convergence. The leakage signal after segmentation and preprocessing is directly sent to the 1D-RC-SCNN model, the leakage features are adaptively extracted, and then, the results are output through the Softmax classifier. The method directly performs end-to-end processing on the leaked signal, which improves the data processing speed. Finally, the cross-correlation method is used to locate the pipeline leak. The effectiveness of the proposed method is verified by building an experimental platform and compared with related models. The experimental results show that the method has high accuracy for the detection and localization of pipeline leak.

Influencing mechanisms of gas bubbles on propagation characteristics of leakage acoustic waves in gas-liquid two-phase flow

Propagation speed of acoustic waves in liquid can be significantly degraded when gas bubbles exist. To reveal the influence of gas bubbles on propagation characteristics of leakage acoustic waves in liquid pipelines, numerical simulation is utilized in the present paper. It can be divided into three stages when leakage acoustic waves propagate through a single gas bubble and the influence of each stage on propagation characteristics of acoustic waves is discussed. In gas-liquid two-phase flow, there are two basic mechanisms of gas resistance on wave propagation: elastic resistance effect and drag resistance effect. The results show that the influence of elastic resistance effect on sound speed is much greater than that of drag resistance effect. When propagating through a long gas bubble with the radius of 2 mm and the length of 7 mm, the elastic resistance effect causes a time delay of 0.00038 s while the drag resistance effect only causes a time delay of 0.00002 s. The results of this paper contribute to better understanding of the differences in acoustic wave propagation characteristics between different flow patterns in gas-liquid two-phase flow, and lay a foundation for the utilization of acoustic leakage detection methods in gas-liquid two-phase flow pipelines.

Artificial Intelligence and Internet of Things-Based Leak Detection Method for the Water Supply Network

The good management and safe operation of the urban water supply network are of great significance to residents’ lives and industrial production. In view of the difficulties in supervision and leakage location of the urban water supply network, based on the technology of Internet of things and artificial intelligence algorithm, a leakage detection method of the urban water supply network is proposed. First of all, low-power, low-cost terminal detection equipment and gateway monitoring equipment are developed for remote data transmission through WiFi or cellular data networks. The data organization, storage, release and control are realized by using the data center software platform. Second, the leakage location model of the water supply network is established by using remote pressure monitoring data, and the accurate location of pipe network leakage is realized. Based on ALO and PSO optimization algorithms, the water supply network in an industrial area of a city in China is solved. Finally, the performance of the two optimization algorithms is compared and analyzed. The results show that the designed intelligent monitoring system of the water supply network can monitor the pipe network well. In addition, on the problem of leakage detection, the ALO algorithm is superior to the PSO algorithm in terms of optimization ability and search efficiency. The leakage monitoring method of water supply networks proposed in this study can provide a reference for the design and management of urban water supply networks.

Prediction of the probabilistic water leak location in underground pipelines using Monte Carlo simulation

Abstract The water loss rates in Brazil are still very concerning and cause huge financial, social, and environmental damages. Although great advances have been made in acoustic leak detection methods, some of them are intrusive or at least demand convenient access points to the pipe's surface. Furthermore, some methods are expensive and require a highly experienced and qualified operator. Thus, the goal of this paper is to establish a benchmark using a simplistic analytical model for the ground surface analysis for leaks location, simplifying the search process carried out in water networks, and requiring minimal system interference. For leak location prediction, the proposed method considered two seismic wave paths – the compressional body waves and the Rayleigh superficial waves. The traveltime curves of the compressional waves are calculated as a function of the surface wave's experimental information. Monte Carlo Simulations were carried out to test each model's precision considering uncertainties related to the input parameters of the problem. At last, through a parametric study, the two seismic events were combined to obtain better accuracy in predicting the leakage epicenter location. In the results, the maximum absolute error found was 15 cm, and the minimum improvement obtained with the parametric study was 27.4%.

Feasibility analysis of blending hydrogen into natural gas networks

Hydrogen fuel has the potential to mitigate the negative effects of greenhouse gases and climate change by neutralizing carbon emissions. Transporting large volume of hydrogen through pipelines needs hydrogen-specific infrastructure such as hydrogen pipelines and compressors, which can become an economic barrier. Thus, the idea of blending hydrogen into existing natural gas pipelines arises as a potential alternative for transporting hydrogen economically by using existing natural gas grids. However, there are several potential issues that must be considered when blending hydrogen into natural gas pipelines. Hydrogen has different physical and chemical properties from natural gas, including a smaller size and lighter weight, which require higher operating pressures to deliver the same amount of energy as natural gas. Additionally, hydrogen's small molecular size and lower ignition energy make it more likely to permeate through pipeline materials and seals, leading to degradation, and its wider flammability limits make it a safety hazard when leaks occur. In this study, we investigate these potential issues through simulation and technical surveys. We develop a gas hydraulic model to simulate the physical characteristics of a transmission and a distribution pipeline. This model is used throughout the study to visualize the potential impacts of switching from natural gas to hydrogen, and to investigate potential problems and solutions. Furthermore, we develop a Real-Time Transient Model (RTTM) to address the compatibility of current computational pipeline monitoring (CPM) based leak detection methods with blended hydrogen. Finally, we suggest the optimal hydrogen concentration for this model, and investigate the amount of carbon reduction that could be achieved, while considering the energy needs of the system.

Leak detection method for the jet fuel pipeline based on IUPEMD and DTWSVM

Jet fuel pipeline leakage will cause environmental pollution and safety-related accidents; therefore, the leak detection of jet fuel pipeline is a crucial for pipeline management. Compared with negative pressure waves, acoustic waves exhibit better attenuation resistance and longer propagation distance. However, acoustic waves are easily disturbed by noise, causing the acoustic signals to mix with a large amount of noise and reducing the detection system’s accuracy to identify pipeline leaks. An improved uniform phase empirical mode decomposition (IUPEMD) denoising method is proposed in this paper. Compared with other denoising methods, intrinsic modal functions with more leakage information can be selected according to the similarity coefficient for signal reconstruction. The reconstructed signal retains the leak information to a greater extent, making the noise content extremely low, which can effectively improve the leak identification accuracy of the leak detection system. To accurately determine the leakage of pipeline and solve the problem of low accuracy of recognition model, this paper establishes a deep learning twin support vector machine (DTWSVM) for identifying the state of pipeline based on deep learning and twin support vector machine, which can automatically extract the leakage feature information and accurately determine the leakage of pipeline based on the feature information. The experimental analysis demonstrates that the IUPEMD denoising method can effectively filter the noise in the signal. The DTWSVM model showed very high recognition accuracy, and its leakage recognition accuracy can reach 99.6%.