Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Nuclear power pipeline defect detection system based on deep learning attention mechanism

A defect detection and deep learning technology, which is applied in the field of nuclear power pipeline defect detection system, can solve problems such as low accuracy, high manpower, material and financial resources, and increased production time and cost, so as to achieve rapid identification, improve detection efficiency, and save production The effect of time cost

Inactive Publication Date: 2020-11-06
烟台市计量所 +1
View PDF2 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Due to the need to compare each negative film with the standard sample during radiographic inspection, from the initial evaluation to the re-evaluation, the manual inspection method causes a huge workload for the relevant evaluation personnel, which not only consumes a lot of manpower, material and financial resources, but also increases the time cost of production. , but there is also a potential problem of low accuracy

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
  • Nuclear power pipeline defect detection system based on deep learning attention mechanism
  • Nuclear power pipeline defect detection system based on deep learning attention mechanism
  • Nuclear power pipeline defect detection system based on deep learning attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] The nuclear power pipeline defect detection system based on the deep learning attention mechanism of the present invention will be described in detail below in conjunction with the embodiments and the accompanying drawings.

[0014] The nuclear power pipeline defect detection system based on the deep learning attention mechanism of the present invention first constructs a training set and a test set after preprocessing by grayscale processing and median filtering, and uses a network with a backbone for training. The force mechanism can effectively aggregate image information, finely segment defect areas, and finally achieve accurate segmentation of defect areas.

[0015] The nuclear power pipeline defect detection system based on deep learning attention mechanism of the present invention comprises the following steps:

[0016] 1) Preprocessing the image of the radiographic flaw detection film; including:

[0017] (1) After obtaining the radiographic flaw image data set...

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 nuclear power pipeline defect detection system based on a deep learning attention mechanism. The method comprises the following steps: preprocessing a radiographic inspectionnegative image; constructing a full convolutional neural network which comprises an encoder module, an attention mechanism module and a decoder module which are connected in sequence, selecting an Adam optimizer to perform gradient updating on the constructed full convolutional neural network, and training the full convolutional neural network after gradient updating by using a Focal Loss loss function; and testing the trained full convolutional neural network to obtain a probability graph, and performing threshold binarization processing on the probability graph to obtain a binarized image of the defect area as a nuclear power pipeline defect detection result. The invention can be applied to assisting film judging personnel in industrial production to quickly detect defect areas for classification and evaluation, and the defect areas are quickly judged by analyzing digitally scanned flaw detection negative film images, so that the detection efficiency is improved, and the productiontime cost is saved.

Description

technical field [0001] The invention relates to a nuclear power pipeline defect detection. In particular, it involves a nuclear power pipeline defect detection system based on deep learning attention mechanism. Background technique [0002] Nuclear energy is an economical, safe, reliable, and clean energy that only needs natural uranium as a resource, and theoretically will not cause greenhouse gas emissions and environmental pollution. To develop nuclear power, the safety issues of nuclear power plants must be properly resolved. Although strict control is adopted during production, inspection and acceptance, and installation and welding, internal defects in the material and welding joints are still unavoidable, which will gradually germinate, expand and grow slowly, gradually forming surface and penetrating cracks. and eventually rupture. This will seriously threaten the safety of Zhou's building structure, nuclear power safety equipment and staff, and even bring serious...

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): G06T7/00G06K9/34G06K9/40G06K9/62G06N3/04F17D5/02
CPCG06T7/0004F17D5/02G06V10/30G06V10/267G06N3/045G06F18/214
Inventor 夏黎黎高忠科许文达安建鹏张文伟
Owner 烟台市计量所
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
Eureka Blog
Learn More
PatSnap group products