Strain clamp crimping defect degree judgment method based on X-ray image

Abstract

The invention discloses a strain clamp crimping defect degree judgment method based on an X-ray image. The method comprises the following steps: acquiring the X-ray image of a strain clamp; the method comprises the following steps of: framing a defect part of an X-ray image by using a detection frame through an improved target detection model faster-rcnn, the improved target detection model faster-rcnn is characterized in that an FPN network is adopted to obtain feature maps of different scales, RoI Align is adopted to obtain candidate feature maps, three cascaded R-CNN networks are adopted as detection network heads, and soft-nms are adopted to screen out target detection frames of all areas; and performing image processing and defect degree judgment on the target detection frame of each region according to the partitions. According to the invention, the defect degree of the strain clamp can be effectively and quickly identified and judged, so that the effect of replacing manual identification and judgment can be achieved.

Description

technical field [0001] The invention relates to the technical field of image pattern recognition and computer vision, in particular to a method for judging the crimping defect degree of tension clamps based on X-ray images. Background technique [0002] In overhead transmission lines, the connection of conductors is a key item. The quality of overhead wire crimping is very important, which ensures the normal operation of the transmission line and makes the transmission line have a certain resistance to damage. [0003] When installing large-section steel-cored aluminum stranded wires on overhead transmission lines, crimping type strain clamps are generally used for crimping installation. The function of the strain clamp is to fix the wire on the insulator string of the non-linear pole tower. It not only bears all the tension of the wire, but also undertakes the task of carrying current. Once this kind of metal is installed, it will not be dismantled. The quality of the cri...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art, and propose a method for judging the degree of crimping defects of tension clamps based on X-ray images, mainly using the improved target detection model faster-rcnn to detect Identify defects in multiple areas; redesign the image processing scheme, and judge the degree of defects in multiple areas according to the requirements of emergency repairs, so as to achieve the purpose of fast, accurate, batch identification and judgment of the degree of defects in tension clamps, so as to make up for manual Check and detect shortcomings

Images