Title :
Using fuzzy theory and information entropy to detect leakage for pipelines
Author_Institution :
Beijing Eng. Res. Center of Monitoring for Constr. Safety, Beijing Univ. of Civil Eng. & Archit., Beijing, China
Abstract :
When detect leakage for pipelines in complicated conditions it is difficult to determine reasons between pipeline fault symptoms and fault causes. In order to obtain the complicated subordinate relationships and to improve the accuracy of pipeline leakage fault diagnosis and other operations, a fault diagnosis method based on the fuzzy mathematics theory and the advantages of information entropy quantitative diagnostic method is proposed. In this study, fuzzy mathematics theory and some typical information entropy were introduced and how to establish fuzzy diagnosis matrix and extract characteristic information entropy is also analyzed in leakage detection for pipelines. Some imitation and field examples were given. The experiments showed that the mapping relationships between the pipeline fault symptoms and the fault causes was most consistent with the actual situation.
Keywords :
entropy; fault diagnosis; fuzzy set theory; inspection; leak detection; matrix algebra; pipelines; characteristic information entropy extraction; fuzzy diagnosis matrix; fuzzy mathematics theory; information entropy quantitative diagnostic method; leakage detection; pipeline fault causes; pipeline fault symptoms; pipeline leakage fault diagnosis; Data mining; Entropy; Fault diagnosis; Feature extraction; Information entropy; Mathematics; Pipelines; Feature extraction; Fuzzy theory; Information entropy; Leakage detection;
Conference_Titel :
Intelligent Control and Automation (WCICA), 2012 10th World Congress on
Conference_Location :
Beijing
Print_ISBN :
978-1-4673-1397-1
DOI :
10.1109/WCICA.2012.6358430