Method and device for pipeline leak detection

Abstract

The invention relates to a pipeline leakage detection method and device. The method includes the following steps that each N point sound wave sampled signal at the two ends of a detected pipeline is obtained; de-noising processing is conducted on each N point sound wave sampled signal to obtain positive and negative sound wave signals corresponding to the N point sound wave sampled signals; iterative computation is conducted on the positive and negative sound wave signals according to the preset iteration time, and the background noise standard deviation corresponding to the sound wave sampled signals is obtained; interval division is conducted on the positive and negative sound wave signals according to the time domain zero crossing point, and multiple interval sampled signals are obtained; each interval sampled signal is used as an independent signal, and the signal-to-noise ratio of each interval sampled signal is calculated according to the background noise standard deviation; the interval sampled signals with the signal-to-noise ratios larger than the signal-to-noise ratio threshold value are judged to be abnormal signals; and when the abnormal signals are detected in the N point sound wave sampled signals at both the two ends of the pipeline, pipeline leakage is positioned according to the obtained abnormal signals, and a pipeline leakage alarm is given if the positioned position is located between the two ends of the pipeline.

Description

technical field [0001] The invention relates to the technical field of pipeline detection, in particular to a method and device for pipeline leakage detection. Background technique [0002] The pipeline leakage detection technology based on the piezoelectric acoustic wave sensor has the advantages of high sensitivity and precise positioning, and has been widely used in the existing pipeline transportation monitoring of petroleum, chemical industry, natural gas, etc., effectively reducing the environmental pollution and safety accidents caused by pipeline leakage . [0003] At present, the leakage diagnosis method of time-frequency domain feature extraction combined with pattern recognition is generally used for the detection of pipeline leakage acoustic signals, and feature extraction methods of time-frequency domain combination such as wavelet packet energy analysis, EMD decomposition, LMD decomposition, and spectrum analysis are mostly used for feature extraction. , but t...

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to address the difficult problem of pipeline leakage detection and provide a system that can set the pipeline leakage detection sensitivity according to the requirements, so as to achieve the purpose of effectively detecting pipeline leakage according to the requirements.

Images