Method for predicting maximum size of second-phase particles of bearing steel based on image recognition

Abstract

The invention discloses a method for predicting the maximum size of second-phase particles of bearing steel based on image recognition, and the method comprises the steps: firstly collecting a large number of microscopic morphology images of the bearing steel, carrying out the graying, binaryzation, image noise reduction, morphological opening and closing operation, reconstruction and other batch processing, and extracting the second-phase particles in the microscopic morphology images; and fitting the size and quantity of the second-phase particles by using an elliptic curve to obtain the equivalent size, equivalent area, proportion and size distribution curve of the second-phase particles, and speculating the maximum size of the second-phase particles by using an extreme value analysis method so as to optimize the size distribution curve of the second-phase particles. The method can accurately fit the boundary curve of the second phase of the bearing steel and extract corresponding data, automatically process a large amount of data and predict the maximum size of the second phase particles, thereby judging the comprehensive mechanical properties of the bearing steel.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to a technology for identifying and analyzing second phases in metal materials by using image processing technology, in particular to a method for predicting the maximum size of particles of the second phase of bearing steel based on image identification. Background technique [0002] The second phase in bearing steel includes MnS, Al 2 O 3 Such as non-metallic inclusions and carbides represented. With the continuous progress of modern smelting technology, the impact of inclusions on bearing steel has been minimal. The number, type, particle shape and size, distribution uniformity and other factors of the second phase of bearing steel represented by carbide have more and more prominent effects on the quality and performance of bearing steel. For example, coarse carbide particles, shape deviation from ellipsoid, uneven distribution, etc., will reduce the performance of bearing steel,...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a statistical method for the particle size of the second phase of bearing steel based on image recognition technology to solve the problems of poor accuracy, poor reproducibility and low efficiency of the current method for manually measuring the second phase particles

At the same time, it also provides a post-identification processing method to predict the maximum size of the second phase particles in bearing steel, so as to solve the problem that the large size second phase particles are difficult to find and effectively statistically analyze.

Images