Natural Gas Pipeline Leakage Research Articles

Diffusion Characteristics and Influencing Factors for Large-Hole Natural Gas Pipeline Leakage in Utility Tunnels

Diffusion Characteristics and Influencing Factors for Large-Hole Natural Gas Pipeline Leakage in Utility Tunnels

An intelligent monitoring approach for urban natural gas pipeline leak using semi-supervised learning generative adversarial networks

Traditional gas pipeline leak monitoring methods are subjected to the long response times and high false alarm rates. Deep learning can enhance the accuracy and real-time performance of pipeline leak monitoring. This paper develops an intelligent monitoring approach for urban gas pipeline leaks based on a semi-supervised learning Generative Adversarial Network (SGAN). First, the Isolation Forest algorithm is used to classify anomalies in the collected process parameter data of urban natural gas pipelines. One-Hot Encoding is used to label a small amount of sample data of pipeline leak. Second, both the labeled and unlabeled data are input into SGAN model for semi-supervised learning and classification to monitor the state of urban gas pipeline leak. The methodology addresses the imbalance between pipeline leak status data and normal data. The comparison with GAN and MLP shows that the methodology reaches the highest values in all evaluation metrics (precision = 94.1%, accuracy = 95.63%, recall = 93.93%, F1 score = 94.32%). The superior performance and accuracy make it more effective for urban natural gas pipeline leak monitoring.

Leak aperture recognition of natural gas pipeline based on variational mode decomposition and mutual information

The acoustic emission (AE) signals generated by natural gas pipeline leaks are affected by various noises, making the accurate extraction of feature signals a challenging task. Therefore, this paper introduces a novel adaptive signal denoising approach utilizing Variational Mode Decomposition (VMD).and mutual information (MI). Firstly, the parameters K and α of VMD are optimized using the energy difference. Simultaneously, the correlation coefficient between adjacent IMF components is used as the evaluation criterion to determine the optimal values of K and α. Then, based on MI, a screening criterion is proposed to select effective IMF components for reconstruction. Finally, the ISSA-SVM model was established by introducing Tent chaotic mapping and inertia weight adjustment strategy on the basis of the traditional sparrow search algorithm (SSA). Experimental results demonstrate that the proposed method effectively eliminates noise from pipeline leak AE signals, with a recognition accuracy reaching up to 96.09%.

Vulnerability assessment of buildings adjacent to natural gas pipelines under explosion accident

ABSTRACT Natural gas pipeline leak may lead to explosion accidents, which may threaten the safety of the adjacent buildings. This paper conducts a vulnerability assessment of buildings adjacent to natural gas pipeline under explosion, which is implemented by Copula Bayesian network (CBN) model. The incident escalations and evolution nodes were identified based on the accident reports. The correlation between nodes is calculated using the Kendall correlation coefficient to develop a CBN model of natural gas pipeline accidents. The weaknesses in the buildings adjacent to pipelines are identified using spider diagrams. The vulnerability of building adjacent to pipelines is characterized by the damage degree. The model is verified by a case study. The results indicate that the occurrence probability of the explosion accident reaches 85%. The identified weaknesses are ignition sources and confined spaces. The occurrence probability of a delayed ignition within buildings is 0.23, and the explosion overpressure is estimated to be 84.25 kPa. The vulnerability degree of building 1 is higher than building 2. These findings can help to understand the system weaknesses and support the safety improvement of buildings in the case of natural gas pipeline explosion.

Analysis of Leakage and Diffusion Characteristics and Hazard Range Determination of Buried Hydrogen-Blended Natural Gas Pipeline Based on CFD.

Injecting hydrogen into natural gas pipelines is an economical and efficient method of hydrogen transportation. However, the addition of hydrogen leads to significant hydrogen corrosion and embrittlement in the pipelines, especially in harsh and concealed underground conditions, where leak accidents are frequent and difficult to detect. This Article uses Le Chatelier's Principle to determine the hazardous range of hydrogen-blended natural gas (HBNG) by employing numerical simulation, it examines the gas leakage and diffusion characteristics before and after hydrogen injection as well as under different hydrogen blending ratio (HBR). Additionally, considering the density of the mixed gas, a prediction model for the diffusion hazard range of hydrogen-mixed natural gas is established based on multivariate regression theory. The results show that after a leakage occurs in HBNG the diffusion range in soil is wider compared to methane, with higher corresponding pressure and velocity values. Moreover, as the HBR increases, the farthest danger range (FDR) of the HBNG also increases. When the leakage of the buried HBNG pipeline occurs for 1 min, the difference in FDR between HBR 25% and HBR 5% is 0.005 m. After 30 min, this difference increases to 0.019 m, indicating that with longer leakage duration, the potential explosion risk resulting from increased HBR becomes greater. Factors such as pipeline pressure increase, larger leak hole size, and decreased burial depth all contribute to an increase in FDR, with pipeline pressure change having the greatest impact and burial depth change having the smallest impact. The maximum error of the predicted model for the diffusion hazard range of hydrogen-mixed natural gas is 9.385%, and the average error is 2.376%, demonstrating the accuracy of the prediction results. This study provides guidance for monitoring underground hydrogen-blended natural gas pipeline leaks, offers a basis for determining the repair range of pipelines, and ensures the safe transportation of hydrogen-mixed natural gas pipelines.

Application of Acoustic Signal Hybrid Filtering with 1D-CNN for Fault Diagnosis of Natural Gas Pipeline Leakage

Application of Acoustic Signal Hybrid Filtering with 1D-CNN for Fault Diagnosis of Natural Gas Pipeline Leakage

Natural gas pipeline leak diagnosis based on manifold learning

Natural gas pipeline leakage is a common safety hazard, which can have a great impact on the economy and the environment. This paper proposed a novel manifold learning-enabled feature extraction method for natural gas pipeline leakage diagnosis. Firstly, the natural gas pipeline working condition signal is decomposed and denoised by Variational mode decomposition (VMD). Secondly, the denoised pipeline signals were constructed into a form expressed by the Symmetric positive definite matrix (SPD) using the VMD reconstruction technique, and the geodesic distance measurement method was applied to the SPD matrix to make the data located on the SPD manifold. Then feature extraction is carried out by Local linear embedding (LLE) method based on asymmetric distance. Finally, pattern recognition of the features extracted in this paper by Support vector machine (SVM) can achieve 100% recognition accuracy. By enabling faster and more accurate leak detection, the method minimizes gas loss, as well as mitigating the environmental risks caused by this potent greenhouse gas.

Two-Stage Optimal Dispatch of Electricity-Natural Gas Networks Considering Natural Gas Pipeline Leakage and Linepack

Two-Stage Optimal Dispatch of Electricity-Natural Gas Networks Considering Natural Gas Pipeline Leakage and Linepack

Research on the hydraulic parameters and leak rate of natural gas flow in natural gas pipelines based on the methods of characteristic line and successive approximation

Pressure and flow rate are the most important hydraulic parameters in natural gas pipeline flow, and leak rate is the most crucial parameter after a leak accident occurs. The study of these parameters is vital to the safey of natural gas pipelines and risk assessment after accidents. In this research, based on the conservation laws universally applicable to the motion of objects, we establish the fundamental control equation group for natural gas flow. Then, for both normal and leak conditions of pipelines, we use the characteristic line method to derive the corresponding difference equations for the fundamental control equations, thereby providing calculation methods for pressure and flow rate. Finally, we investigate the calculation method of natural gas pipeline leak rate under different leak aperture sizes, and validate the accuracy of this method through simulation examples.

Study on vibration signals identification method for pipeline leakage detection based on deep learning technology

For natural gas pipeline leakage systems based on distributed feedback fiber laser vibration sensors (DFB-FL), a novel neural network model (mCNN-LFLBs) integrating multi-scale convolutional neural networks (mCNN) with local feature extraction blocks (LFLBs) is proposed in this study. To address the problem of feature loss in the traditional signal image transfer process, the one-dimensional original signal is directly used as the input of the model, effectively maintaining the time-domain correlation of the leaked signal. The time-domain correlation of the leakage signal is preserved. To address the problem that traditional pattern recognition algorithms have a weak ability to extract deep features and local features, mCNN is established by this model, which realizes the use of convolution kernels of different scales to extract features of different frequency bands in one-dimensional signals. Additionally, LFLBs are introduced, which enhances the local expression ability of the model, further improves the feature mining quality of the model, and better presents the deep features of leaked signals. Experimental results demonstrate that the mCNN-LFLBs model has a classification accuracy of up to 98.6%, with a testing response time of approximately 10 ms, and outstanding performance in terms of convergence speed. These results highlight the potential practical application of the mCNN-LFLBs model in natural gas leak detection.

ECNet: Network Based on Encoder With Local Convolutional Attention and Cross Layer Information Fusion for Natural Gas Pipeline Leakage Detection

ECNet: Network Based on Encoder With Local Convolutional Attention and Cross Layer Information Fusion for Natural Gas Pipeline Leakage Detection

Investigation of Hydrogen-Blended Natural Gas Pipelines in Utility Tunnel Leakage and Development of an Accident Ventilation Strategy for the Worst Leakage Conditions

The development of hydrogen-blended natural gas (HBNG) increases the risk of gas transportation and presents challenges for pipeline security in utility tunnels. The objective of this study is to investigate the diffusion properties of HBNG in utility tunnels and evaluate the effectiveness of various ventilation mechanisms. The numerical simulation software Fluent 2023 R1 is applied to simulate and analyze the leakage of small holes in a HBNG pipeline in the natural gas compartment. By examining the leaking behavior of HBNG through small holes in different circumstances, we aimed to identify the most unfavorable operational situation for leakage. Subsequently, we analyzed the ventilation strategy for sub-high-pressure pipes at various pressure levels in this unfavorable condition. This study’s findings demonstrate that blending hydrogen improves the gas diffusion capacity and increases the likelihood of explosion. The primary factors that influence the pattern of leakage are the size of the leaking holes and the pressure of the pipeline. The gas compartment experiences the most unfavorable working conditions for natural gas pipeline leaks when there are higher pressures, wider leak openings, higher hydrogen blending ratios (HBRs), and leaks in close proximity to an air inlet. When the HBR is 20%, the minimum accident ventilation rates for pressures of 0.4 MPa and 0.8 MPa are 15 air changes per hour and 21 air changes per hour, respectively. The maximum allowable wind speed for accident ventilation is 5 m/s, as regulated by China’s national standard, GB 50838-2015. This regulation makes it difficult to minimize the risk of leakage in a 1.6 MPa gas pipeline. It is recommended to install a safety interlock device to quickly shut off the pipeline in the event of a leak in order to facilitate the dispersion of the substance.

Gas pipeline leakage detection and location by using w-FBG array based micro-strain sensing technology

In addressing the significant security concerns associated with urban natural gas transportation, particularly the potential catastrophic consequences of leaks, this paper introduces a novel approach for detecting and locating leaks in natural gas pipelines using weak fiber Bragg grating (w-FBG) array micro-strain sensing technology. The field pipeline model is established, w-FBG array is applied to pipeline leakage experiment, and the pipeline leakage is detected by analyzing the change trend of micro-strain. The pipeline leakage experiments under different pressures were carried out. The experimental results show that there is a good linear relationship between the pipeline leakage pressure and the wavelength change of w-FBG, and the linearity is greater than 0.99, which is consistent with the theoretical analysis and verifies the applicability of w-FBG. According to the characteristics of micro-strain transfer in pipeline leakage process, a ‘abrupt change point’ capturing method based on peak to peak slope and threshold judgment is proposed. Results indicate that the proposed algorithm effectively detects pipeline leaks and accurately locates the point of leakage, with a positioning error of approximately 0.5 m. Compared with the traditional method, the proposed method has higher precision.

Investigation of urban natural gas pipeline leak and resulting dispersion in a semi-closed space: A case of accident in Shiyan, China

Pipeline is the most common way for delivering natural gas to the urban areas. Nevertheless, pipeline leak accidents can pose significant threats to human life and property safety. This paper investigates the characteristics of urban natural gas pipeline leaks and the resulting gas dispersion in a semi-closed space using a 3D Computational Fluid Dynamics (CFD) model. The characteristics of a pipeline leak is examined considering the impact of shape, dimensions, and location of the aperture. The migration of natural gas in a semi-closed space is tracked, considering the impact of leak location and orientation. To illustrate the model, a real-life case study is conducted to simulate flammable gas release and dispersion resulting from an urban natural gas pipeline leak. The outcome can guide the monitoring and mitigating the consequences of urban natural gas pipeline leaks.

An exploration of novel natural gas leak detection based on the efficient CH4/N2 separation of polymer blend membrane

The CH4/N2 high-efficiency membrane separation technology is capable of effectively enriching CH4 from natural gas, and holds great potential for application in the fields of biogas purification and natural gas pipeline leak detection. However, preparing high-performance separation membranes is challenging due to the similarity between CH4 and N2 molecules. To enhance the CH4/N2 separation performance, block polyetheramide copolymer (Pebax)/EVA blended membranes were fabricated in this study. Additionally, a novel gas leakage detection tube was prepared. The EVA14 (14 wt% VA) membrane exhibits an optimal transport-facilitated channel among a series of pure EVA membranes, resulting in a CH4 permeability of 21.41 Barrer and CH4/N2 selectivity reaches 1.80 under mixed-gas feed conditions at 35 °C. The CH4 permeability of Pebax/EVA (30 wt%) reaches 120.5 Barrer by physical blending, and the CH4 permeability is increased by 191 % in comparison with pure EVA14 membrane. The Pebax/EVA (10 wt%) membrane exhibits the optimum CH4/N2 selectivity, and compared with pure EVA membrane increased by 35.5 %. EVA and Pebax polymers are blended for the first time for CH4/N2 separation, and the blending of block polyetheramide copolymer intensifies the membrane's separation performance comprehensively. The natural gas leak detection tube was fabricated with a membrane, offering a new and efficient CH4/N2 separation strategy.

Optimization of Emergency Resource Dispatch for Overseas Long-distance Natural Gas Pipeline Leaks

Overseas long-distance natural gas pipelines usually span across multiple regions or even countries, facing more severe environmental conditions and more prone to leakage and other accidents, and the study of the optimization method of emergency resource scheduling for overseas long-distance natural gas pipeline leakage accidents can help to reduce the casualties and property losses. Therefore, this paper establishes an emergency resource scheduling model in line with the emergency disposal mechanism of overseas long-distance natural gas pipeline leakage accidents, takes into account the variability of the operating ability of maintenance personnel, and improves the accuracy of the scheduling program to a certain extent, and also considers the actual environment of overseas long-distance natural gas pipelines, takes into account the impact of landslides on the emergency scheduling time, and calculates the probability of landslides occurring in the landslide point by using the interpolated value of rainfall The rainfall interpolation is used to calculate the probability of landslide at the landslide point, and the emergency dispatching time is corrected to make the dispatching program more in line with the actual demand. The analysis of the results shows that the emergency resource scheduling time is dominant in the case of small amount of maintenance and repair work and short total maintenance and repair time.

Simulation and experimental study of buried natural gas pipeline leak detection based on sound source characteristics

Buried pipe-line leakage will affect the thermal characteristics of the soil environment, leading to a poor soil environment. In addition, leakage of natural gas possibly produces an explosion and subsequent fire, which has fatal harm. Sustainable detection of underground gas pipe-line leaks is a significant part of current research. In this study, a method for leak detection of buried natural gas polyethylene pipe-lines based on sound source characteristics is investigated. The simulation software was applied in analyzing the variation of leakage rate and sound source in buried pipes under different leakage conditions including mainly different leakage apertures and pipe pressures. Also, an experiment platform was built to verify the simulation results. These results can provide help for gas pipe-line leakage detection and safety protection.

Application of pipeline leakage detection based on distributed optical fiber acoustic sensor system and convolutional neural network

Underwater pipelines are exposed to harsh environments, including high salinity, multi-modal vortex corrosion, and severe wave interference. Their safety is essential for the development and transportation of marine energy. Therefore, real-time safety monitoring of long-distance energy pipelines is of great strategic importance for ensuring the safety of life and property and energy security. With the rapid development of energy development, the corrosion and leakage mechanisms of natural gas pipelines, as well as their identification and early warning, have become the focus of attention. Optical fiber sensing technology has been applied to various energy safety monitoring fields. However, the mechanism of sound source fluctuations in pipeline leakage and the mutual coupling mechanism between distributed optical fiber sensing technology and leakage sound waves are not yet clear. This paper establishes a model based on sound wave propagation and leakage noise response, derives a quadratic fitting relationship between pipeline pressure fluctuations and leakage orifices and a relationship between leakage noise source standard deviation and orifices, and proposes a complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) permutation entropy underwater natural gas pipeline leakage signal recognition method based on distributed optical fiber acoustic sensing technology. The results of theoretical analysis are verified by experiments. It shows that the signal processing method of CEEMDAN permutation entropy is superior to traditional noise reduction methods, which can better preserve the features of the original signal; the radial basis function (RBF) neural network model can accurately identify four different leakage features with an accuracy of 88.15%, and its recognition stability and generalization ability are superior to convolutional neural network, backpropagation, and random forest. Therefore, the research results of this paper provide a new method for safety monitoring in the application of energy pipeline transportation engineering, and expand the potential application scenarios of distributed acoustic sensing sensor systems and RBF neural networks.

Research on leakage detection technology of natural gas pipeline based on modified Gaussian plume model and Markov chain Monte Carlo method

Natural gas pipeline leakage can cause significant economic losses and even jeopardize public safety. Therefore, leakage detection technology is crucial. In this study, the pipeline source term estimation method is proposed to identify the source of natural gas pipeline leakage. The method combines the modified Gaussian plume model, the unmanned aerial vehicle inspection technology equipped with laser methane sensors, and the Markov chain Monte Carlo method based on Bayesian inference. Different from traditional leak detection techniques, this method can simultaneously obtain the location and rate of pipeline leakage. The accuracy of the method is validated by using simulated data from the modified Gaussian plume model, which can be employed to replace experimental tests. Convergence diagnosis and model evaluation are performed on the inversion model in this method, verifying its rationality and feasibility. The impact of system errors on the pipeline source estimation method is analyzed, revealing that the accuracy of inversion can be improved by using prior information and ensuring the reliability of the forward gas dispersion model and monitoring data. The pipeline source term estimation method proposed in this paper can offer technical support for the emergency treatment of natural gas pipeline leakage accidents.

Miniaturized and Portable Laser Gas Sensor for Standoff Methane Detection With Non-Cooperative Targets.

A standoff methane (CH4) sensor with actual hard topographic targets (usually called non-cooperative targets) is essential for natural gas pipeline leakage inspection and many other practical applications. To address this requirement, a miniaturized and low-power-consumption gas sensor was developed based on tunable diode laser absorption spectroscopy for standoff CH4 detection with a non-cooperative target. Wavelength modulation spectroscopy with a 1f normalized 2f detection method was employed for calibration-free CH4 measurement. A Kalman filter algorithm was used to improve the precision of the detection. The performance of the standoff CH4 sensor was evaluated comprehensively under various conditions, including different incident angles, different hard topographic targets, and different standoff distances. The results show that the measurement precision is 0.107% and the sensitivity is 4.08 parts per million per meter (ppm·m) with a time resolution of 1 s and a standoff distance of 40 m. The detection limit can achieve 1.24 ppm·m at an optimal integration time of 70 s. This sensor can be easily integrated into mobile platforms, which lays the foundation for intelligent leak inspection.