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

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...

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

Images