Feature extraction based on variational mode decomposition and support vector machine for natural gas pipeline leakage. (February 2020)

• Record Type: Journal Article
• Authors: Lu, Jingyi; Yue, Jikang; Jiang, Chunlei; Liang, Hongwei; Zhu, Lijuan
• Other Names: Tan Chao guest-editor.
• Is Part Of: Transactions of the Institute of Measurement and Control. Volume 42:Number 4(2020)
• Page Start: 759
• Page End: 769
• Publication Date: 2020-02
• Subjects: Variational mode decomposition -- cloud model characteristic entropy -- root mean square -- correlation coefficient -- support vector machine; Automatic control -- Periodicals; Measuring instruments -- Periodicals; Commande automatique -- Périodiques; Mesure -- Instruments -- Périodiques; 681.2
• DOI: 10.1177/0142331219874161
• Languages: English
• ISSNs: 0142-3312

Abstract

Issues concerning natural gas pipeline leakage are becoming more prominent than ever because of the continuing expansion of natural gas pipeline networks. Although many scholars have extensively investigated generation and detection methods for pipeline leakage acoustic signals, systematic research on the characteristics of leakage and interference signals remains insufficient. Results show that the method based on the RBF kernel function is feasible for pipeline fault diagnosis, yielding 100% sensitivity, 92% specificity, and 96% accuracy.