Research on Detection and Location of Fluid-Filled Pipeline Leakage Based on Acoustic Emission Technology.

Shengshan Pan,Zhengdan Xu,Dongsheng Li,Dang Lu

doi:10.3390/s18113628

Abstract

Because of the inconvenience of installing sensors in a buried pipeline, an acoustic emission sensor is initially proposed for collecting and analyzing leakage signals inside the pipeline. Four operating conditions of a fluid-filled pipeline are established and a support vector machine (SVM) method is used to accurately classify the leakage condition of the pipeline. Wavelet decomposition and empirical mode decomposition (EMD) methods are initially used in denoising these signals to address the problem in which original leakage acoustic emission signals contain too much noise. Signals with more information and energy are then reconstructed. The time-delay estimation method is finally used to accurately locate the leakage source in the pipeline. The results show that by using SVM, wavelet decomposition and EMD methods, leakage detection in a liquid-filled pipe with built-in acoustic emission sensors is effective and accurate and provides a reference value for real-time online monitoring of pipeline operational status with broad application prospects.

Highlights

Pipeline transport has become the fifth largest transportation tool in modern society and offers great advantages in transporting fluid media
A support vector machine (SVM) method is used for leakage detection in a liquid-filled pipe with a built-in acoustic emission (AE) sensor and methods based on wavelet decomposition and empirical mode decomposition (EMD) are utilized to effectively denoise the leakage signal
The original nonstationary AE signal can be decomposed in time and frequency domains using

Summary

Introduction

Pipeline transport has become the fifth largest transportation tool in modern society and offers great advantages in transporting fluid media (e.g., oil, natural gas, water). On the basis of the propagation theory of guided waves in pipes, Jingpin Jiao et al [6] proposed a specific model of AE signal propagation in pipelines and introduced a new method to determine the leakage source. This study attempts to locate the AE sensors installed inside a pipeline to collect leakage signals and to verify the effectiveness of the method used. This provides a basis for subsequent built-in self-capacitive AE sensors to monitor the damage of fluid-filled pipelines. A support vector machine (SVM) method is used for leakage detection in a liquid-filled pipe with a built-in AE sensor and methods based on wavelet decomposition and EMD are utilized to effectively denoise the leakage signal. An optimal decision boundary function is established [19]

Optimal Hyperplane

Selection

Leakage

Schematic

Wavelet Decomposition and Threshold Denoising

Experimental

Laboratory

Technological

Test results based on Figure on the the model model with with the the RBF

10. Classification

Pipeline Leakage Location Based on Wavelet Decomposition and EMD

Wavelet Decomposition Denoising