Skip to the main content

Original scientific paper

https://doi.org/10.17559/TV-20150314123705

Study on pipeline leaking detection and location based on intuitionistic fuzzy set theory

Wei Liu ; (1) School of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, Shaanxi, China; (2) Department of Computer and Electronic Information, Shaanxi Xueqian Normal University, Xi’an 710100, Shaanxi, China
Hong-Zhao Liu ; School of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, Shaanxi, China


Full text: croatian pdf 554 Kb

page 685-693

downloads: 544

cite

Full text: english pdf 554 Kb

page 685-693

downloads: 611

cite


Abstract

From the view of time sequence, a petroleum pipeline leak detection and location method is proposed based on intuitionistic fuzzy set theory. The method uses wavelet decomposition and semi-hard-and-soft thresholding method to remove the noise of signal. Secondly, selecting fixed-length normal dynamic pressure wave signal sequences as the template sequence, and the same-length sub-sequence of acquisition signals is selected as matching sequence, the intuitionistic fuzzy sets of two sub-sequences signals corresponding to power spectrum are constructed, and their intuitionistic fuzzy similarity and entropy calculated. In the end, according to the similarity degree between normal and acquisition signals sequences, whether there is leakage of petroleum pipeline can be automatically judged. If leakage occurs, the leaking location can be determined by means of the intuitionistic fuzzy entropy difference. The experimental results show that the proposed intuitionistic fuzzy set theory for oil pipeline leak detection and location method is simple, effective and has high locating accuracy.

Keywords

anomaly detection; dynamic pressure wave; intuitionistic fuzzy entropy; intuitionistic fuzzy similarity; pipeline leaking

Hrčak ID:

160125

URI

https://hrcak.srce.hr/160125

Publication date:

19.6.2016.

Article data in other languages: croatian

Visits: 2.572 *