Pipeline pitting corrosion damage intelligent identification method based on image identification and acoustic identification

An image recognition and intelligent recognition technology, which is applied to scientific instruments, processing detection response signals, and optical testing of flaws/defects, etc., can solve problems such as pipeline corrosion and leakage, threats to people's lives and property safety, and achieve good background noise and convenience The effect of data processing

Pending Publication Date: 2021-06-15
CHANGZHOU UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with the rapid increase of pipelines in recent years, the growth of pipeline age, and the inevitable natural or man-made damages such as corrosion and wear, pipeline corrosion and leakage accidents have occurred one after another, posing a serious threat to people's lives and property safety.

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 pitting corrosion damage intelligent identification method based on image identification and acoustic identification
  • Pipeline pitting corrosion damage intelligent identification method based on image identification and acoustic identification
  • Pipeline pitting corrosion damage intelligent identification method based on image identification and acoustic identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0012] In order to further explain the technical solution of the present invention, the present invention is described in detail below.

[0013] The invention proposes a pipeline pitting signal EEMD analysis and a pitting severity comprehensive recognition method based on two-dimensional convolution image analysis. The first is the analysis of pitting acoustic signal data based on EEMD theory. The first step is to perform Z-score standardization on the original data to obtain x * , to ensure that the input variables of different physical quantities and dimensions are equal to use the formula as follows:

[0014]

[0015] is the mean of the original data, and σ is the standard deviation of the original data.

[0016] The second step is to use the EEMD algorithm to extract the center frequency of the strongest intrinsic mode (IMF) of the pipeline pitting signal as a characteristic parameter. The specific steps are as follows:

[0017] (1) Add white noise N times to the ac...

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 discloses a pipeline pitting corrosion damage intelligent identification method based on image identification and acoustic identification, and belongs to the field of pipeline acoustic emission signal processing. Different from the traditional wavelet transform and fast Fourier transform for processing the acoustic emission data, an algorithm provided by the invention breaks through the limitations of the wavelet transform and fast Fourier transform, the primary function of the EEMD can be automatically generated and has adaptive filtering characteristics, and the properties of the original signal can be obtained by adding the decomposed components. The background noise of various corrosion sound signals in the pitting corrosion state of the pipeline can be better removed, and data processing is facilitated. And relatively detailed features in the corrosion signal can be conveniently extracted. In addition, a DIC imaging technology and an acoustic emission technology are combined for analysis, and the purpose of intelligent recognition is achieved through extracted image features and acoustic signal features.

Description

technical field [0001] The invention belongs to the field of pipeline acoustic emission signal processing, in particular to the pitting acoustic signal processing of pipelines. Background technique [0002] As the main channel for transporting liquid and gaseous media, pipelines play a huge role in the national economy. However, with the rapid increase of pipelines in recent years, the growth of pipeline age, and the inevitable corrosion, wear and other natural or man-made damages, pipeline corrosion and leakage accidents have occurred one after another, posing a serious threat to people's lives and property safety. Among them, pitting corrosion of pipelines is particularly common, and this process is often accompanied by corrosion fatigue damage. Therefore, it is of great significance to fully understand the mechanism of pitting corrosion fatigue of pipelines through acoustic emission technology for actual engineering production. [0003] As a common non-destructive testin...

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): G01N29/44G01N29/14G01N21/88
CPCG01N21/8851G01N29/14G01N29/4427G01N29/4454G01N29/4481G01N2021/8887
Inventor 张颖丛蕊许世林张潇王雪琴张延兵杨锦冯芊
Owner CHANGZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap