A Novel Pipeline Leak Detection Technique Based on Acoustic Emission Features and Two-Sample Kolmogorov–Smirnov Test

Rai, Akhand; Ahmad, Zahoor; Hasan, Junayed

doi:10.3390/s21248247

Cited by 14 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The structural discontinuity or leak in the pipeline (irrespective of the cause) will disturb the flow of the fluid or gas inside the pipeline. However, the intramolecular interactions or chemical bonding of the fluid will force the fluid to keep its flow consistent [ 29 ]. Thus, for the fluid to keep its flow consistent inside the pipeline, the molecule of the fluid will exert pressure on the position of pipeline structural discontinuity or leak, which will result in the short, rapid release of energy in the form of an elastic wave.…”

Section: The Proposed Architecture and Methodologymentioning

confidence: 99%

Pipeline Leakage Detection Using Acoustic Emission and Machine Learning Algorithms

Ullah

Ahmad

Kim

2023

Sensors

Self Cite

View full text Add to dashboard Cite

Pipelines play a significant role in liquid and gas resource distribution. Pipeline leaks, however, result in severe consequences, such as wasted resources, risks to community health, distribution downtime, and economic loss. An efficient autonomous leakage detection system is clearly required. The recent leak diagnosis capability of acoustic emission (AE) technology has been well demonstrated. This article proposes a machine learning-based platform for leakage detection for various pinhole-sized leaks using the AE sensor channel information. Statistical measures, such as kurtosis, skewness, mean value, mean square, root mean square (RMS), peak value, standard deviation, entropy, and frequency spectrum features, were extracted from the AE signal as features to train the machine learning models. An adaptive threshold-based sliding window approach was used to retain the properties of both bursts and continuous-type emissions. First, we collected three AE sensor datasets and extracted 11 time domain and 14 frequency domain features for a one-second window for each AE sensor data category. The measurements and their associated statistics were transformed into feature vectors. Subsequently, these feature data were utilized for training and evaluating supervised machine learning models to detect leaks and pinhole-sized leaks. Several widely known classifiers, such as neural networks, decision trees, random forests, and k-nearest neighbors, were evaluated using the four datasets regarding water and gas leakages at different pressures and pinhole leak sizes. We achieved an exceptional overall classification accuracy of 99%, providing reliable and effective results that are suitable for the implementation of the proposed platform.

show abstract

Section: The Proposed Architecture and Methodologymentioning

confidence: 99%

Pipeline Leakage Detection Using Acoustic Emission and Machine Learning Algorithms

Ullah

Ahmad

Kim

2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…A holistic algorithm for localizing leakages in pipelines was presented in [23]. A method for detecting leakages in pipelines was proposed that was based on acoustic emission event characteristics and a Kolmogorov-Smirnov test (KS).…”

Section: Related Workmentioning

confidence: 99%

“…Some of the developed algorithms in this paper use the ideas of a piecewise linear model [18] and linear regression for outlier detection from [20]. Further algorithms use ideas of kernel-based detection from [21], the Bayesian method from [22], and the KS test from [23]. The applied algorithms use the same ideas and methods as in [18,[20][21][22][23].…”

Section: Related Workmentioning

confidence: 99%

Application and Optimization of Algorithms for Pressure Wave Evaluation Based on Measurement Data

et al. 2022

View full text Add to dashboard Cite

Leakages can occur in a district heating network, resulting in high economical damage. The propagating pressure wave resulting from large, spontaneous leakages reaches sensors at different locations in the network. This leads to pressure drops registered at each sensor at a different point in time. The time differences help to localize the leakage. Different algorithms are presented and applied in this paper to estimate the pressure drop time points based on non-uniform, time-discrete sensor signals. Five of the nine algorithms are self-developed with, e.g., parts of linear regression, whereas the other four algorithms have already been described in the literature, such as change-point detection. In this paper, several recorded events were investigated, and the algorithms were applied to real measurement data. After detection, leakage localization was performed to determine the affected exclusion area. A performance criterion was used as a measure to compare the algorithms. For practical application, the best-performing algorithm was identified. Furthermore, the events were classified according to how well they could be evaluated.

show abstract

“…Furthermore, to determine the severity of the leak, a Gaussian mixture model was used. Kim et al [16] developed a pipeline leak indicator by utilizing AE waveform features and a two-sample KS test. The study showed that the proposed leak indicator outperformed the traditional feature (i.e., mean, variance, and root mean square)-based leak indicators.…”

Section: Introductionmentioning

confidence: 99%

A Method for Pipeline Leak Detection Based on Acoustic Imaging and Deep Learning

Ahmad

Kim

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

This paper proposes a reliable technique for pipeline leak detection using acoustic emission signals. The acoustic emission signal of a pipeline contains leak-related information. However, the noise in the signal often obscures the leak-related information, making traditional acoustic emission features, such as count and peaks, less effective. To obtain leak-related features, first, acoustic images were obtained from the time series acoustic emission signals using continuous wavelet transform. The acoustic images (AE images) were the wavelet scalograms that represent the time–frequency scales of the acoustic emission signal in the form of an image. The acoustic images carried enough information about the leak, as the leak-related information had a high-energy representation in the scalogram compared to the noise. To extract leak-related discriminant features from the acoustic images, they were provided as input into the convolutional autoencoder and convolutional neural network. The convolutional autoencoder extracts global features, while the convolutional neural network extracts local features. The local features represent changes in the energy at a finer level, whereas the global features are the overall characteristics of the acoustic signal in the acoustic image. The global and local features were merged into a single feature vector. To identify the pipeline leak state, the feature vector was fed into a shallow artificial neural network. The proposed method was validated by utilizing a data set obtained from the industrial pipeline testbed. The proposed algorithm yielded a high classification accuracy in detecting leaks under different leak sizes and fluid pressures.

show abstract

A Novel Pipeline Leak Detection Technique Based on Acoustic Emission Features and Two-Sample Kolmogorov–Smirnov Test

Cited by 14 publications

References 30 publications

Pipeline Leakage Detection Using Acoustic Emission and Machine Learning Algorithms

Pipeline Leakage Detection Using Acoustic Emission and Machine Learning Algorithms

Application and Optimization of Algorithms for Pressure Wave Evaluation Based on Measurement Data

A Method for Pipeline Leak Detection Based on Acoustic Imaging and Deep Learning

Contact Info

Product

Resources

About