CN111912910A - Intelligent identification method for polyethylene pipeline hot-melt weld joint hybrid ultrasonic scanning defects - Google Patents
Intelligent identification method for polyethylene pipeline hot-melt weld joint hybrid ultrasonic scanning defects Download PDFInfo
- Publication number
- CN111912910A CN111912910A CN202010808907.6A CN202010808907A CN111912910A CN 111912910 A CN111912910 A CN 111912910A CN 202010808907 A CN202010808907 A CN 202010808907A CN 111912910 A CN111912910 A CN 111912910A
- Authority
- CN
- China
- Prior art keywords
- scanning
- ultrasonic
- defects
- scanning image
- defect
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 21
- 239000012943 hotmelt Substances 0.000 title claims abstract description 17
- 239000004698 Polyethylene Substances 0.000 title claims abstract description 15
- -1 polyethylene Polymers 0.000 title claims abstract description 15
- 229920000573 polyethylene Polymers 0.000 title claims abstract description 15
- 238000003466 welding Methods 0.000 claims abstract description 17
- 238000001514 detection method Methods 0.000 claims abstract description 16
- 238000013528 artificial neural network Methods 0.000 claims abstract description 8
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 6
- 238000003384 imaging method Methods 0.000 claims abstract description 5
- 239000000523 sample Substances 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000001788 irregular Effects 0.000 abstract description 2
- 230000002950 deficient Effects 0.000 description 4
- 229920001903 high density polyethylene Polymers 0.000 description 4
- 239000004700 high-density polyethylene Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4454—Signal recognition, e.g. specific values or portions, signal events, signatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4481—Neural networks
Landscapes
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
A polyethylene pipeline hot-melt welding line hybrid ultrasonic scanning defect intelligent identification method comprises the following steps: (1) scanning a detected workpiece through ultrasonic waves to obtain an ultrasonic signal A, a scanning image B and a scanning image C, and inputting the ultrasonic signal A, the scanning image B and the scanning image C into a depth convolution neural network to perform target detection on possible defects in the detected workpiece; (2) segmenting and denoising the detected defects, and inputting the data of the ultrasonic signal A, the scanning image B and the scanning image C corresponding to the segmented defects into the depth convolution neural network at the 2 nd stage; (3) comparing the confidence coefficient of the deep convolutional neural network with a threshold gamma, if the confidence coefficient exceeds the threshold gamma, identifying the defect, otherwise, identifying the defect as a non-defect; the intelligent nondestructive detection device can complete the processes of detection, imaging, defect analysis and the like at one time, has high detection efficiency and simple and convenient operation, can carry out intelligent nondestructive detection on various workpieces with irregular shapes, has wide application range and reduces the cost.
Description
Technical Field
The invention relates to an intelligent defect identification method, in particular to a hybrid ultrasonic scanning intelligent defect identification method for a hot-melt welding seam of a polyethylene pipeline.
Background
In the welding process of a High Density Polyethylene (HDPE) hot-melt pipeline welding seam, defects such as air holes, slag inclusion, cold welding and the like are easy to generate, and with the adoption of HDPE pipelines in nuclear three-level and non-nuclear-level systems in domestic nuclear power stations to replace steel pipelines, the synchronous development of a quality detection technology of HDPE pipeline hot-melt welding joints is urgent. The detection tests show that the ultrasonic detection technology is an effective detection technical means, can effectively detect various defects generated in the production or use process of the hot-melt welding line, mainly relies on manual identification at present, has very high requirements on the experience of data analysts, and is easy to cause the phenomena of defect missing judgment and error judgment in the manual data analysis process.
Therefore, a method for intelligently identifying the defect of the polyethylene pipeline hot-melt welding line hybrid ultrasonic scanning is particularly needed to solve the existing problems.
Disclosure of Invention
The invention aims to provide an intelligent identification method for hot-melt welding seam hybrid ultrasonic scanning defects of a polyethylene pipeline, effectively overcomes the defects of manual defect identification aiming at the defects of the prior art, and can be widely applied to other industrial nondestructive testing.
The technical problem solved by the invention can be realized by adopting the following technical scheme:
the intelligent recognition method for the polyethylene pipeline hot-melt welding seam hybrid ultrasonic scanning defects is characterized by comprising the following steps of:
(1) scanning a detected workpiece through ultrasonic waves to obtain an ultrasonic signal A, a scanning image B and a scanning image C, and inputting the ultrasonic signal A, the scanning image B and the scanning image C into a depth convolution neural network to perform target detection on possible defects in the detected workpiece;
(2) segmenting and denoising the detected defects, and inputting the data of the ultrasonic signal A, the scanning image B and the scanning image C corresponding to the segmented defects into the depth convolution neural network at the 2 nd stage;
(3) and comparing the confidence coefficient of the deep convolutional neural network with a threshold gamma, and identifying the defect if the confidence coefficient exceeds the threshold gamma, or identifying the defect if the confidence coefficient does not exceed the threshold gamma.
In an embodiment of the present invention, the ultrasonic signal a is triggered by the phased array board or the ultrasonic probe to generate an ultrasonic wave and acquire ultrasonic data.
In an embodiment of the present invention, the scan image B is a color image obtained by converting the data of the ultrasonic signal a into color values and plotting the color values, wherein the ultrasonic signal a is collected from a plurality of scan points.
In an embodiment of the present invention, the scan image C is a color image that is drawn by extracting each ultrasonic signal a as one data by using an imaging algorithm and then according to the number of scanning points and the number of steps.
In one embodiment of the invention, a threshold γ of 0-1, i.e. greater than the threshold γ, is defective, otherwise non-defective.
Compared with the prior art, the intelligent identification method for the defect of the polyethylene pipeline by the hybrid ultrasonic scanning can complete the processes of detection, imaging, defect analysis and the like at one time, has high detection efficiency and simple and convenient operation, can carry out intelligent nondestructive detection on various irregular workpieces, has wide application range, integrates acquisition and intelligent detection, reduces the cost and realizes the aim of the invention.
The features of the present invention will be apparent from the accompanying drawings and from the detailed description of the preferred embodiments which follows.
Drawings
FIG. 1 is a schematic diagram of an intelligent identification method for defects of polyethylene pipeline hot-melt welding line hybrid ultrasonic scanning.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further explained below by combining the specific drawings.
Examples
As shown in FIG. 1, the intelligent identification method for the defect of the polyethylene pipeline hot-melt welding line hybrid ultrasonic scanning comprises the following steps:
(1) scanning a detected workpiece through ultrasonic waves to obtain an ultrasonic signal A, a scanning image B and a scanning image C, and inputting the ultrasonic signal A, the scanning image B and the scanning image C into a depth convolution neural network to perform target detection on possible defects in the detected workpiece;
(2) segmenting and denoising the detected defects, and inputting the data of the ultrasonic signal A, the scanning image B and the scanning image C corresponding to the segmented defects into the depth convolution neural network at the 2 nd stage;
(3) and comparing the confidence coefficient of the deep convolutional neural network with a threshold gamma, and identifying the defect if the confidence coefficient exceeds the threshold gamma, or identifying the defect if the confidence coefficient does not exceed the threshold gamma.
In this embodiment, the ultrasonic signal a is triggered by the phased array board or the ultrasonic probe to generate an ultrasonic wave and acquire ultrasonic data.
In this embodiment, the scan image B is a color image obtained by converting the data of the ultrasonic signal a into color values and drawing the color values, wherein the ultrasonic signal a is collected from a plurality of scan points.
In this embodiment, the scan image C is a color image that is drawn by extracting each ultrasonic signal a as one data by using an imaging algorithm and then according to the number of scan points and the number of steps.
In this embodiment, the algorithm of the deep convolutional neural network and the algorithm of the deep convolutional neural network in the phase 2 are both known algorithms in the art, and are not described herein again.
In this embodiment, the threshold γ is 0-1, i.e., greater than the threshold γ is defective, otherwise it is non-defective.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are merely illustrative of the principles of the present invention, but that various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined by the appended claims and their equivalents.
Claims (5)
1. The intelligent recognition method for the polyethylene pipeline hot-melt welding seam hybrid ultrasonic scanning defects is characterized by comprising the following steps of:
(1) scanning a detected workpiece through ultrasonic waves to obtain an ultrasonic signal A, a scanning image B and a scanning image C, and inputting the ultrasonic signal A, the scanning image B and the scanning image C into a depth convolution neural network to perform target detection on possible defects in the detected workpiece;
(2) segmenting and denoising the detected defects, and inputting the data of the ultrasonic signal A, the scanning image B and the scanning image C corresponding to the segmented defects into the depth convolution neural network at the 2 nd stage;
(3) and comparing the confidence coefficient of the deep convolutional neural network with a threshold gamma, and identifying the defect if the confidence coefficient exceeds the threshold gamma, or identifying the defect if the confidence coefficient does not exceed the threshold gamma.
2. The intelligent polyethylene pipeline hot-melt welding line hybrid ultrasonic scanning defect identification method according to claim 1, wherein the ultrasonic signal A is triggered by a phased array board card or an ultrasonic probe to generate an ultrasonic wave and acquire ultrasonic data.
3. The intelligent identification method for the hot-melt welding seam hybrid ultrasonic scanning defects of the polyethylene pipeline as claimed in claim 1, wherein the scanning image B is an ultrasonic signal A collected from a plurality of scanning points, and the ultrasonic signal A is converted into a color value through data conversion and is drawn into a color image.
4. The intelligent identification method for the hot-melt welding seam hybrid ultrasonic scanning defects of the polyethylene pipeline as claimed in claim 1, wherein the scanning image C is a color image which is obtained by extracting each ultrasonic signal A into one data by using an imaging algorithm and then drawing according to the number of scanning points and the number of steps.
5. The intelligent identification method for the hot-melt welding seam hybrid ultrasonic scanning defects of the polyethylene pipeline as claimed in claim 1, wherein the threshold value gamma is 0-1, namely, the defects are determined when the threshold value gamma is larger than the threshold value gamma, and the defects are not determined if the threshold value gamma is not larger than the threshold value gamma.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010808907.6A CN111912910A (en) | 2020-08-12 | 2020-08-12 | Intelligent identification method for polyethylene pipeline hot-melt weld joint hybrid ultrasonic scanning defects |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010808907.6A CN111912910A (en) | 2020-08-12 | 2020-08-12 | Intelligent identification method for polyethylene pipeline hot-melt weld joint hybrid ultrasonic scanning defects |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111912910A true CN111912910A (en) | 2020-11-10 |
Family
ID=73282987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010808907.6A Pending CN111912910A (en) | 2020-08-12 | 2020-08-12 | Intelligent identification method for polyethylene pipeline hot-melt weld joint hybrid ultrasonic scanning defects |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111912910A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2610449A (en) * | 2021-09-06 | 2023-03-08 | Harbin Inst Technology | Efficient high-resolution non-destructive detecting method based on convolutional neural network |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4869109A (en) * | 1987-05-12 | 1989-09-26 | Thierry Miglianico | Automatic process for identification of defects by ultrasound and corresponding system |
| US20060130586A1 (en) * | 2003-01-14 | 2006-06-22 | Barry Messer | Configurations and methods for ultrasound time of flight diffraction analysis |
| CN101769728A (en) * | 2010-02-02 | 2010-07-07 | 浙江大学 | Method for detecting weld areas of hot-melting polythene pipe joints |
| CN101839895A (en) * | 2009-12-17 | 2010-09-22 | 哈尔滨工业大学 | Near-surface defect recognition method based on ultrasonic TOFD |
| CN102207490A (en) * | 2011-03-04 | 2011-10-05 | 哈尔滨工业大学 | Recognition method for weld defect signal in ultrasonic testing of austenitic stainless steel |
| US20120226159A1 (en) * | 2009-05-08 | 2012-09-06 | Anthony Sinclair | Ultrasonic scanning system and ultrasound image enhancement method |
| CN105891215A (en) * | 2016-03-31 | 2016-08-24 | 浙江工业大学 | Welding visual detection method and device based on convolutional neural network |
| CN107451997A (en) * | 2017-07-31 | 2017-12-08 | 南昌航空大学 | A kind of automatic identifying method of the welding line ultrasonic TOFD D scanning defect types based on deep learning |
| CN110243934A (en) * | 2019-05-30 | 2019-09-17 | 中国计量大学上虞高等研究院有限公司 | A kind of ultrasonic weld seam detection method based on wavelet convolution neural network |
| JP2020503509A (en) * | 2017-03-29 | 2020-01-30 | 富士通株式会社 | Defect detection using ultrasonic scan data |
-
2020
- 2020-08-12 CN CN202010808907.6A patent/CN111912910A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4869109A (en) * | 1987-05-12 | 1989-09-26 | Thierry Miglianico | Automatic process for identification of defects by ultrasound and corresponding system |
| US20060130586A1 (en) * | 2003-01-14 | 2006-06-22 | Barry Messer | Configurations and methods for ultrasound time of flight diffraction analysis |
| US20120226159A1 (en) * | 2009-05-08 | 2012-09-06 | Anthony Sinclair | Ultrasonic scanning system and ultrasound image enhancement method |
| CN101839895A (en) * | 2009-12-17 | 2010-09-22 | 哈尔滨工业大学 | Near-surface defect recognition method based on ultrasonic TOFD |
| CN101769728A (en) * | 2010-02-02 | 2010-07-07 | 浙江大学 | Method for detecting weld areas of hot-melting polythene pipe joints |
| CN102207490A (en) * | 2011-03-04 | 2011-10-05 | 哈尔滨工业大学 | Recognition method for weld defect signal in ultrasonic testing of austenitic stainless steel |
| CN105891215A (en) * | 2016-03-31 | 2016-08-24 | 浙江工业大学 | Welding visual detection method and device based on convolutional neural network |
| JP2020503509A (en) * | 2017-03-29 | 2020-01-30 | 富士通株式会社 | Defect detection using ultrasonic scan data |
| CN107451997A (en) * | 2017-07-31 | 2017-12-08 | 南昌航空大学 | A kind of automatic identifying method of the welding line ultrasonic TOFD D scanning defect types based on deep learning |
| CN110243934A (en) * | 2019-05-30 | 2019-09-17 | 中国计量大学上虞高等研究院有限公司 | A kind of ultrasonic weld seam detection method based on wavelet convolution neural network |
Non-Patent Citations (4)
| Title |
|---|
| 张晓宝: "聚乙烯管道焊接接头超声相控阵检测研究", 《中国优秀硕士学位论文全文数据库 (工程科技Ⅰ辑)》 * |
| 王寿超: "聚乙烯燃气管道焊接缺陷检测方法试验研究", 《煤气与热力》 * |
| 蔡勤等: "聚乙烯燃气管道热熔接头主要缺陷及无损检测技术研究进展", 《化学工程与装备》 * |
| 郑志远: "焊缝典型缺陷的超声TOFD-D扫成像技术研究", 《中国优秀硕士学位论文全文数据库 (工程科技Ⅰ辑)》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2610449A (en) * | 2021-09-06 | 2023-03-08 | Harbin Inst Technology | Efficient high-resolution non-destructive detecting method based on convolutional neural network |
| GB2610449B (en) * | 2021-09-06 | 2023-09-20 | Wuhu State Owned Factory Machining | Non-destructive defect edge detecting method based on convolutional neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Miao et al. | Real-time defect identification of narrow overlap welds and application based on convolutional neural networks | |
| CN113362326B (en) | Method and device for detecting defects of welding spots of battery | |
| CN108665452B (en) | Pipeline-weld film scanning storage and identification of Weld Defects and its system | |
| CN102927448A (en) | Undamaged detection method for pipeline | |
| CN103323526A (en) | Welding line defect detection and identification method based on ultrasonic phased array and support vector machine | |
| CN111122705B (en) | Ultrasonic nondestructive testing method for wind turbine blade | |
| CN117173461A (en) | Multi-visual task filling container defect detection method, system and medium | |
| CN114799610A (en) | Welding quality real-time detection method and system based on inverse Fourier transform and self-encoder | |
| JPH059744B2 (en) | ||
| CN113256566A (en) | Pipeline weld defect identification method | |
| CN115601359A (en) | Welding seam detection method and device | |
| CN115656335A (en) | Method for quickly detecting and identifying internal defects of bearing ring | |
| CN111912910A (en) | Intelligent identification method for polyethylene pipeline hot-melt weld joint hybrid ultrasonic scanning defects | |
| CN116381053A (en) | Ultrasonic detection method and system for welding metal materials | |
| CN116973372A (en) | Defect detection system of building steel structure | |
| Zuo et al. | An X-ray-based automatic welding defect detection method for special equipment system | |
| CN104439747B (en) | A kind of method detecting identification P92 steel weld metal microcrack | |
| JP7553207B2 (en) | Ultrasonic flaw detection system and ultrasonic flaw detection method | |
| CN113588796B (en) | Marine pipeline monitoring and early warning method and system | |
| CN112347903B (en) | Multi-component pipeline identification method based on heterogeneous field signals | |
| CN111882535B (en) | Resistance welding shear strength identification method based on improved Unet network | |
| Zuo et al. | STMA-Net: A Spatial Transformation-Based Multi-Scale Attention Network for Complex Defect Detection with X-ray Images | |
| CN110082424A (en) | A kind of multiple dimensioned abnormal area recommender system of rapid pipeline magnetic flux leakage data and method | |
| CN110766707A (en) | Cavitation bubble image processing method based on multi-operator fusion edge detection technology | |
| Geng et al. | Classification Recognition of Long Distance Oil and Gas Pipeline Girth Welds MFL Signal Diagrams Based on VGG16 Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: No. 29 Hong Cao Road, Xuhui District, Shanghai Applicant after: Shanghai Nuclear Engineering Research and Design Institute Co.,Ltd. Applicant after: STATE NUCLEAR POWER PLANT SERVICE Co. Address before: No. 29 Hong Cao Road, Xuhui District, Shanghai Applicant before: SHANGHAI NUCLEAR ENGINEERING RESEARCH & DESIGN INSTITUTE Co.,Ltd. Applicant before: STATE NUCLEAR POWER PLANT SERVICE Co. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201110 |