Nuclear safety shell surface defect automatic detection method and system

Abstract

The invention provides a nuclear safety shell surface defect automatic detection method and system, and provides a systematic and effective technical scheme to overcome the defects in a nuclear safety shell surface, including cracks, corrosion and seepage. The method comprises: image preprocessing, and then utilizing a contour expansion filtering algorithm to perform denoising enhancement to obtain pretreated binary images; feature extraction comprising utilizing a linear weighting tensor voting algorithm, extracting cracks from discrete noises through detecting high light degree to obtain a result probability graph; and performing object tracking to obtain a crack center line, back-projecting positioning to extract real crack information, measuring crack length and stable width, crack integration and other defect detection and storing information. The invention further provides utilizing an adaptive width template method and an iterative method to respectively binarize images, and obtaining final binary images by performing AND operation on two results. The technical scheme creates an own system, and can meet real engineering demands, and guarantee nuclear shell safety.

Description

technical field [0001] The invention belongs to the field of digital image processing, in particular to a method and system for automatic detection of surface defects of nuclear containment shells. Background technique [0002] The reactor containment of a nuclear power plant is a building with a very high level of safety, and it is the last safety barrier to prevent the spillage of radioactive materials produced by nuclear fission. The reactor containment of a nuclear power plant must undergo an overall pressure test after the completion of construction, the first commercial operation, and every ten years thereafter to test the ability of the containment to withstand LOCA conditions. Part of the overall compression test is to check the appearance of the containment structure. Appearance inspection refers to the inspection of surface defects on the outer side of the containment structure. The overall containment is a prestressed concrete structure, and the external surface ...

AI Technical Summary

Problems solved by technology

Analysis of the image shows that the area occupied by the defect is much smaller than the area of ​​the background, and the magnitude of the noise pixel is at the same level as that of the defect pixel, but most of the defects are planar aggregate targets, and the noise is mostly point-like discrete targets;

[0009] 5) Due to historical inspection, most of the defects are marked with eye-catching colors (red or blue) paint, and the existence of dotted line boxes, English letters and numbers will interfere with the defect extraction, so it needs to be ch

Images