Home Journals Articles Updates About
CN
image
收藏切换
Research on carbides in M50 bearing steel based on Mask R-CNN deep learning model
收藏切换
PDF
Ruiming SUN1, 2, Shuxin LI1, 2, Siyuan LU1, 2, Yongsheng JIN3, Huahai XIAO3
Journal of Mechanical Strength | 2025, 47(8) : 19 - 27
Less
收藏切换
Journal of Mechanical Strength | 2025, 47(8): 19-27
• Experimental Research·Testing Technology •
Research on carbides in M50 bearing steel based on Mask R-CNN deep learning model
Full
Ruiming SUN1, 2, Shuxin LI1, 2, Siyuan LU1, 2, Yongsheng JIN3, Huahai XIAO3
Affiliations
  • 1.Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China
  • 2.Part Rolling Key Laboratory of Zhejiang Province, Ningbo 315211, China
  • 3.Ningbo Silver-ball Technology Co., Ltd., Ningbo 315207, China
Published: 2025-08-15 doi: 10.16579/j.issn.1001.9669.2025.08.003
Outline
收藏切换

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.

Deep learning  /  Mask R-CNN  /  M50 bearing steel  /  Carbide
Ruiming SUN, Shuxin LI, Siyuan LU, Yongsheng JIN, Huahai XIAO. Research on carbides in M50 bearing steel based on Mask R-CNN deep learning model[J]. Journal of Mechanical Strength, 2025 , 47 (8) : 19 -27 . DOI: 10.16579/j.issn.1001.9669.2025.08.003
Funding
Less
  • Natural Science Foundation of China(52075271)
  • Major Science and Technology Task Tackling Project of Ningbo(2022Z050)
  • Cixi Industry-Specific Technology Research and Development Project(CZ2022009)
Appendix
Less
Year 2025 volume 47 Issue 8
PDF
68
33
Cite this Article
BibTeX
Article Info
doi: 10.16579/j.issn.1001.9669.2025.08.003
  • Receive Date：2023-11-23
  • Online Date：2026-03-19
  • Published：2025-08-15
Article Data
Affiliations
History
  • Received：2023-11-23
  • Revised：2024-01-16
Funding
Natural Science Foundation of China(52075271)
Major Science and Technology Task Tackling Project of Ningbo(2022Z050)
Cixi Industry-Specific Technology Research and Development Project(CZ2022009)
Affiliations
    1.Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China
    2.Part Rolling Key Laboratory of Zhejiang Province, Ningbo 315211, China
    3.Ningbo Silver-ball Technology Co., Ltd., Ningbo 315207, China

Corresponding:

LI Shuxin, E-mail：
References
Share
https://castjournals.cast.org.cn/joweb/jxqd/EN/10.16579/j.issn.1001.9669.2025.08.003
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62199257
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House