Research on carbides in M50 bearing steel based on Mask R-CNN deep learning model
SUN Ruiming
LI Shuxin
LU Siyuan
JIN Yongsheng
XIAO Huahai
Abstract：The main types of carbides in M50 bearing steel are MC,M2C and M23C6.Under the scanning electron microscopy(SEM),they exhibit significant differences in the shape,size,and distribution.Some carbides have larger sizes and uneven distribution.They become areas of stress concentration under loading,which has a negative impact on the bearing fatigue performance.So an improved mask region-based convolutional neural network(Mask R-CNN)model was proposed which can batch identify the types of three kinds of carbides in SEM pictures,the diameters of carbides were measured,and the distribution of carbides was showed.The output images and histogram results show that the size of M2C carbide in M50 bearing steel is large and unevenly distributed,but the distribution of MC carbide with the largest size and M23C6 with the smallest size is reasonably uniform.
Keywords：Deep learningMask R-CNNM50 bearing steelCarbide
Publication Date：2025-08-15
Online Publishing Date：2026-09-12(First online date of this platform, not the publication date of the document)
Pages：9( 19-27 )