Feature extraction based on variational mode decomposition and support vector machine for natural gas pipeline leakage

Lu, Jingyi; Yue, Jikang; Jiang, Chunlei; Liang, Hongwei; Zhu, Lijuan

doi:10.1177/0142331219874161

Cited by 9 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lu et al [9] proposed a model that can extract the features of pipelines to detect leakage. The continuous expansion of pipeline networks and the lack of research in the field of pipeline leakage recognition using leak features were the two main driving factors in this study.…”

Section: Related Workmentioning

confidence: 99%

An Anomaly Detection Model for Oil and Gas Pipelines Using Machine Learning

et al. 2022

View full text Add to dashboard Cite

Detection of minor leaks in oil or gas pipelines is a critical and persistent problem in the oil and gas industry. Many organisations have long relied on fixed hardware or manual assessments to monitor leaks. With rapid industrialisation and technological advancements, innovative engineering technologies that are cost-effective, faster, and easier to implement are essential. Herein, machine learning-based anomaly detection models are proposed to solve the problem of oil and gas pipeline leakage. Five machine learning algorithms, namely, random forest, support vector machine, k-nearest neighbour, gradient boosting, and decision tree, were used to develop detection models for pipeline leaks. The support vector machine algorithm, with an accuracy of 97.4%, overperformed the other algorithms in detecting pipeline leakage and thus proved its efficiency as an accurate model for detecting leakage in oil and gas pipelines.

show abstract

Section: Related Workmentioning

confidence: 99%

An Anomaly Detection Model for Oil and Gas Pipelines Using Machine Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…related safety and environmental protection concerns are of paramount importance [2,3]. Incidents or leaks can result in severe consequences, including casualties, property loss, and environmental pollution [4]. Hence, it is critical to promptly acquire leak information and accurately locate leak sites to expedite pipeline repair and mitigate the harm caused by leaks.…”

Section: Introductionmentioning

confidence: 99%

Pipeline leak location method based on SSA-VMD with generalized quadratic cross-correlation^*

Peng,

Hu,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Natural gas pipelines are an essential part of the economy. Natural gas pipelines may leak after aging, strong vibration signals may be generated in the pipeline when leakage occurs, and vibration signals may be noisy. Traditional variational mode decomposition (VMD) noise reduction methods need to set parameters in advance, and so may not achieve the best decomposition effect. To solve this problem, this paper proposes a method for pipeline leakage location based on the sparrow search algorithm (SSA) optimization of VMD combined with generalized quadratic cross-correlation. The method first calculates the original signal-to-noise ratio, and if the signal-to-noise ratio is low, wavelet threshold denoising is used to process the signal. Then, SSA optimization is used to refine the two key parameters of VMD (penalty parameter α and mode decomposition number K) based on sample entropy. Subsequently, the signal undergoes decomposition into K intrinsic mode function (IMF) components through VMD according to the obtained analysis parameter combination. Then, the IMF components are screened to obtain the reconstructed signal. Finally, the noise reduction signal is obtained. The signal delay after noise reduction is obtained through a generalized quadratic cross-correlation and the accurate leakage position is obtained using the delay. Experiments showed that the minimum relative error of this method could reach 0.6%, which was more accurate than the traditional VMD method, and effectively improved the accuracy of noisy signals in pipeline leakage locations.

show abstract

“…These feature extraction methods rely on human experience, and the model generalization ability is poor. Lu et al (2020b) proposed to use variational mode decomposition (VMD) to decompose leakage signals, cloud model characteristic entropy to extract fault information, and finally use SVM for classification, with an accuracy rate of 96%. Pe´rez-Pe´rez et al (2021) used ANN technology to measure pipeline operating pressure and flow to detect and locate pipeline leaks.…”

Section: Introductionmentioning

confidence: 99%

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

Yan

Liu

et al. 2023

Transactions of the Institute of Measurement and Control

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Feature extraction based on variational mode decomposition and support vector machine for natural gas pipeline leakage

Cited by 9 publications

References 31 publications

An Anomaly Detection Model for Oil and Gas Pipelines Using Machine Learning

An Anomaly Detection Model for Oil and Gas Pipelines Using Machine Learning

Pipeline leak location method based on SSA-VMD with generalized quadratic cross-correlation^*

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

Contact Info

Product

Resources

About

Feature extraction based on variational mode decomposition and support vector machine for natural gas pipeline leakage

Cited by 9 publications

References 31 publications

An Anomaly Detection Model for Oil and Gas Pipelines Using Machine Learning

An Anomaly Detection Model for Oil and Gas Pipelines Using Machine Learning

Pipeline leak location method based on SSA-VMD with generalized quadratic cross-correlation*

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

Contact Info

Product

Resources

About

Pipeline leak location method based on SSA-VMD with generalized quadratic cross-correlation^*