Method for automatically sorting and rating metallographic structures of different materials

Abstract

The invention provides a method for automatically sorting and rating metallographic structures of different materials, comprising the following steps: firstly creating a database of crystal grain series of three different materials (20CrMnTi, CF steel and 55 steel) at different multiples; reading in one metallographic structure image F with the size of M*N, wherein M and N are positive integers; recognizing metallographic materials in the read-in metallographic structure image F, and recognizing kinds of the materials by adopting a convolutional neural network; and then carrying out rough sorting and fine sorting on the database, and rating grain size scales of the recognized materials by adopting a data enhancement and transfer learning method. The method provided by the invention firstlyapplies a convolutional neural network algorithm and a transfer learning algorithm to recognition and rating of metallographic images and can realize automatic recognition and rating of the metallographic structures of different materials, and accuracy and efficiency of the method provided by the invention are also greatly improved.

Description

technical field [0001] The invention relates to the field of metallographic quantitative intelligent analysis of microscopic grain structures of different materials (20CrMnTi, CF steel and No. 55 steel), in particular to a method for automatic classification and rating of metallographic structures of different materials. Background technique [0002] Metallographic analysis is an important means of research and performance testing of metals. In order to obtain metallographic images, it is necessary to intercept, grind, polish and etch the target metal, and then put the prepared metal sample under a metallographic microscope. Observation under a metallographic microscope mainly detects the composition of metal materials and whether there are defects in the material. The main indicators include whether there are impurities, the number of grain size levels, the depth of the decarburization layer, and whether the grain boundaries are corroded. Among them, the series of grain si...

AI Technical Summary

Problems solved by technology

This method is not only very time-consuming and labor-intensive, but also the accuracy of the rating is very dependent on the professional quality of metallographic inspectors, with low precision and poor repeatability

[0003] In recent years, many people have begun to study the analysis and rating of metallographic images through the method of computer recognition of images, but there are certain limitations, because most of these studies manually set a single feature extractor for a certain A limited metallographic image is used for grading, which often results in a long time-consuming, narrow application range and low rating stability

Images