Leakage identification method of gas-liquid two-phase flow pipeline based on acoustic emission signal

Abstract

For the problem that the conventional oil pipeline detection system cannot effectively detect the leakage of the two-phase flow pipelines, a leakage identification method based on the acoustic emission signal was proposed for the gasliquid two-phase flow pipelines. According to the basic principles of acoustic emission detection technology, the leakage detection tests were carried out for the three flow patterns of laminar flow, slug flow and annular flow at a gas pressure of 0.1 to 0.4 MPa in three different orientations of leak holes with two different diameters. The main signal components extracted by wavelet packet decomposition combined with local mean decomposition were taken as the input of pattern recognition, and the BP artificial neural network pattern recognition was also performed. The test results show that the average accuracy of the leakage identification of the three two-phase flow pipelines of laminar flow, slug flow and annular flow is 83.5%, which is high in accuracy. Further, the proposed method has a reference value for the leakage detection of gas-liquid twophase flow pipelines.

Keywords

• pipeline leakage
• gas-liquid two-phase flow
• acoustic emission
• non-destructive testing
• bp neural network