Unlock instant, AI-driven research and patent intelligence for your innovation.

Pipeline abnormal signal positioning detection method and device based on heterogeneous sensor

A heterogeneous sensor and abnormal signal technology, applied in the direction of measuring devices, machine/structural component testing, pipeline systems, etc., can solve problems such as human health damage, avoid external noise interference, improve accuracy and ease of use Effect

Inactive Publication Date: 2020-12-15
苏州聆听智能科技有限公司
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of method has high requirements on the operating environment, and is generally carried out at night when the ambient noise is relatively weak. In addition, the listening method has a strong dependence on the experience of the operator, and long-term audio-visual work will also cause harm to human health. damage

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Pipeline abnormal signal positioning detection method and device based on heterogeneous sensor
  • Pipeline abnormal signal positioning detection method and device based on heterogeneous sensor
  • Pipeline abnormal signal positioning detection method and device based on heterogeneous sensor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] Such as Figure 1-2 As shown, a kind of heterogeneous sensor-based buried pipeline location detection method of the present invention includes:

[0071] S10. Acquire the acoustic vibration signals collected by the heterogeneous sensor array, and perform preprocessing to obtain preprocessed data.

[0072] Step S10 includes acquiring the acoustic vibration signal collected by the heterogeneous sensor array, and preprocessing the original acoustic vibration signal by using a time-frequency analysis method to obtain preprocessed data; wherein the time-frequency analysis method includes Fourier transform or wavelet packet decomposition.

[0073] Traditional vibration signal analysis and processing methods generally use Fourier transform. Wavelet packet decomposition is a time-frequency localization analysis method with a fixed window area but its shape can be changed, that is, both time and frequency windows can be changed. In the process of decomposition, only the low-freq...

Embodiment 2

[0138] The present invention also provides a buried pipeline location detection device based on heterogeneous sensors, including:

[0139] The preprocessing module 10 is configured to acquire the acoustic vibration signals collected by the heterogeneous sensor array, and perform preprocessing to obtain preprocessed data.

[0140] It is specifically used to obtain the acoustic vibration signal collected by the heterogeneous sensor array, and the time-frequency analysis method is used to preprocess the original acoustic vibration signal to obtain the preprocessed data; wherein, the time-frequency analysis method includes Fourier transform or wavelet packet decomposition.

[0141] The heterogeneous sensor array includes at least four heterogeneous acoustic vibration sensors. The at least four heterogeneous acoustic vibration sensors include at least one ground pickup sensor and an auxiliary sensor. The at least four heterogeneous acoustic vibration sensors are different sensors. ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a pipeline abnormal signal positioning detection method based on a heterogeneous sensor. The method comprises the steps of obtaining an acoustic vibration signal collected through the heterogeneous sensor array, and preprocessing the acoustic vibration signal; fusing preprocessed data to obtain fusion feature data of a fusion sound source; obtaining position information andfeature information of the fusion sound source; obtaining ideal feature data of normal sound source signals in a sample library in an ideal environment; obtaining similarity according to the fusion feature data and the ideal feature data; and judging whether the acoustic vibration signal is abnormal or not according to the similarity and the feature information of the fusion sound source. According to the pipeline abnormal signal positioning detection method based on the heterogeneous sensor provided by the invention, different heterogeneous sensors are adopted for signal collection, the preprocessed data are fused through a fusion algorithm, sound source signals outside the ground are removed, coordinates and sound intensity of the fusion sound source are obtained according to a sound source positioning algorithm, and subsequent troubleshooting is facilitated; and whether the signal is abnormal or not is judged according to the similarity and the sound intensity of the fusion sound source, and the accuracy of buried pipeline anomaly detection and positioning is improved.

Description

technical field [0001] The invention relates to the field of abnormal detection of buried pipelines, in particular to a method and device for detecting abnormal signals of pipelines based on heterogeneous sensors. Background technique [0002] According to different principles, water supply pipeline leakage detection can be roughly classified into two categories: passive detection and active detection. The passive detection method is the most direct and primitive method. Generally, it is discovered after the leaking water body of the pipeline overflows the ground and then repaired. Leaks need to be detected and repaired by active detection methods. The active detection method is aimed at hidden leaks that cannot be directly discovered by humans, using instruments and control methods of different principles to search for artificial leaks, mainly including: sound leak detection method, correlation analysis leak detection method, regional leak detection method, Tracer gas met...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): F17D5/06G01M3/24
CPCF17D5/06G01M3/243
Inventor 蔡绍滨王宇昊
Owner 苏州聆听智能科技有限公司