VISUAL MEASURING AUTOMATION CONTROL

2021

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.21685/2307-4205-2021-4-13
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Background. Practice shows that accidents and disasters occurring during the destruction of structural elements of objects, machines and products are almost always associated with the presence of defects in them. This article proposes the automation of the process of the visual measuring method (VIM) of non-destructive testing. The purpose of this work is to develop a software package that allows you to automate the work of a specialist conducting visual measurement control (VIC). Materials and methods. The option of creating a database of 3D models of the tested samples is being considered for further obtaining the trajectory of the electron microscope for creating images. Results. A database of reference images of material surfaces without defects, images of material surfaces with examples of various types of defects has been created. Conclusions. The formed base will make it possible to analyze by comparing the results obtained by artificial intelligence methods with images obtained during flaw detection with an electron microscope. This, in turn, will make it possible to predict possible equipment failures, as well as to work out the process of forming the final image, indicating the locations of possible defects.