New Leak Localization Approach in Pipelines Using Single-Point Measurement

Ozevin, Didem; Yalcinkaya, Hazim

doi:10.1061/(asce)ps.1949-1204.0000163

Cited by 27 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These results open opportunities for implementing the algorithm for pipelines used to constitute e.g. industrial heat exchangers, or to improve reliability of normal pipelines [16].…”

Section: Discussionmentioning

confidence: 99%

Leak Detection in Waterworks: Comparison Between STFT and FFT with an Overcoming of Limitations

Lay-Ekuakille

Griffo

Visconti

et al. 2017

Metrology and Measurement Systems

View full text Add to dashboard Cite

Detection of leakages in pipelines is a matter of continuous research because of the basic importance for a waterworks system is finding the point of the pipeline where a leak is located and − in some cases − a nature of the leak. There are specific difficulties in finding leaks by using spectral analysis techniques like FFT (Fast Fourier Transform), STFT (Short Term Fourier Transform), etc. These difficulties arise especially in complicated pipeline configurations, e.g. a zigzag one. This research focuses on the results of a new algorithm based on FFT and comparing them with a developed STFT technique. Even if other techniques are used, they are costly and difficult to be managed. Moreover, a constraint in the leak detection is the pipeline diameter because it influences accuracy of the adopted algorithm. FFT and STFT are not fully adequate for complex configurations dealt with in this paper, since they produce ill-posed problems with an increasing uncertainty. Therefore, an improved Tikhonov technique has been implemented to reinforce FFT and STFT for complex configurations of pipelines. Hence, the proposed algorithm overcomes the aforementioned difficulties due to applying a linear algebraic approach.

show abstract

“…These results open opportunities for implementing the algorithm for pipelines used to constitute e.g. industrial heat exchangers, or to improve reliability of normal pipelines [16].…”

Section: Discussionmentioning

confidence: 99%

Leak Detection in Waterworks: Comparison Between STFT and FFT with an Overcoming of Limitations

Lay-Ekuakille

Griffo

Visconti

et al. 2017

Metrology and Measurement Systems

View full text Add to dashboard Cite

show abstract

“…The plant model is a pipeline length of 500 m with a diameter of 42 in, and the material of the chromium‐metal pipe and the flow of methane gas at a pressure of 90/7 times at 55°C in the South Pars Gas Complex. Flow values which are inputs of the neural network are got from two ultrasonic flow meters model ALTOSONIC V12 under the new standard OIML R137 class 0.5, which installed at the beginning and the end of the modeled pipeline (Figure ), moreover, three portable ultrasonic flow meters are installed along the pipeline at a distance of 125 m from each other …”

Section: Leak Detection Designmentioning

confidence: 99%

Modeling of gas pipeline in order to implement a leakage detection system using artificial neural networks based on instrumentation

Rahmati

2018

Int J Numerical Modelling

View full text Add to dashboard Cite

In this paper, by using of gas flow pattern, a novel neural network-based fault detection method is presented to detect the leakage in the gas pipeline. The pipe is divided into four segments, and each segment is modeled by using input/output pressure of the gas flow. For this purpose, the acquired practical data from the real life gas pipeline are gathered and utilized for training a neural network to model the process. Some of the data are used for training set to adjust the neural network weights, and others are used to evaluate the performance of the neural network-based fault detection system. Gathered practical data from a real life pipeline made sure that the proposed method is prominent and applicable for practical implementations. The model was verified with the data obtained from the test in the actual pipeline and compared with leakage mode. KEYWORDS artificial neural network (ANN), gas pipeline, leakage detection, pattern recognition, wireless sensor network (WSN)

show abstract

“…Moreover they found the effectiveness of the correlation technique was affected by the selection of sensors and the cut-off frequencies of high and low pass digital filters used to remove noises. Ozevin et al [15] proposed a new leak localization approach. They detect the leak from a single point measurement with two sensors designed to be sensitive to the wave motions generated in two orthogonal directions.…”

Section: Introductionmentioning

confidence: 99%

Continuous leakage location in noisy environment using modal and wavelet analysis with one AE sensor

Mostafapour

Davoodi

2015

Ultrasonics

View full text Add to dashboard Cite

New Leak Localization Approach in Pipelines Using Single-Point Measurement

Cited by 27 publications

References 16 publications

Leak Detection in Waterworks: Comparison Between STFT and FFT with an Overcoming of Limitations

Leak Detection in Waterworks: Comparison Between STFT and FFT with an Overcoming of Limitations

Modeling of gas pipeline in order to implement a leakage detection system using artificial neural networks based on instrumentation

Continuous leakage location in noisy environment using modal and wavelet analysis with one AE sensor

Contact Info

Product

Resources

About