浏览全部资源
扫码关注微信
1.宁波大学 机械工程与力学学院,宁波 315211
2.浙江省零件轧制成形技术研究重点实验室,宁波 315211
3.宁波银球科技股份有限公司,宁波 315207
孙瑞明,男,1993年生,河南鹤壁人,硕士研究生;主要研究方向为机械结构强度;E-mail:15658028610@163.com。
李淑欣,女,1975年生,宁夏中卫人,博士,教授,博士研究生导师;主要研究方向为机械结构强度;E-mail:lishuxin@nbu.edu.cn。
收稿日期:2023-11-23,
修回日期:2024-01-16,
纸质出版日期:2025-08-15
移动端阅览
孙瑞明,李淑欣,鲁思渊,等. 基于深度学习模型Mask R-CNN对M50轴承钢中碳化物的研究[J]. 机械强度,2025,47(8):19-27.
SUN Ruiming,LI Shuxin,LU Siyuan,et al. 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.
孙瑞明,李淑欣,鲁思渊,等. 基于深度学习模型Mask R-CNN对M50轴承钢中碳化物的研究[J]. 机械强度,2025,47(8):19-27. DOI: 10.16579/j.issn.1001.9669.2025.08.003.
SUN Ruiming,LI Shuxin,LU Siyuan,et al. 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.
M50轴承钢中主要的碳化物类型为MC、M
2
C和M
23
C
6
。扫描电子显微镜(Scanning Electron Microscopy
SEM)下,3种碳化物的形状、尺寸和在材料中的分布存在明显的区别。有些碳化物的尺寸较大且分布不均匀。轴承受载过程中,这些碳化物会成为应力集中的区域,对轴承疲劳性能产生负面影响。为了高效地获得材料中的碳化物信息,提出一种改进的掩膜基于区域的卷积神经网络(Mask Region-based Convolutional Neural Network
Mask R-CNN)模型,可批量鉴别SEM图像中3种碳化物的种类,确定其尺寸大小及分布。网络模型输出的图像和数值结果显示,M50轴承钢中M
2
C型碳化物尺寸大且分布不均匀,但总体尺寸最大的MC型碳化物和尺寸最小的M
23
C
6
型碳化物分布相对均匀。
The main types of carbides in M50 bearing steel are MC
M
2
C and M
23
C
6
. 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 M
2
C carbide in M50 bearing steel is large and unevenly distributed
but the distribution of MC carbide with the largest size and M
23
C
6
with the smallest size is reasonably uniform.
BHADESHIA H K D H . Steels for bearings [J]. Progress in Materials Science , 2012 , 57 ( 2 ): 268 - 435 .
KINKUS T J , OLSON G B . Microanalytical evaluation of a prototype stainless bearing steel [J]. Surface Science , 1992 , 266 ( 1/2/3 ): 391 - 396 .
BARROW A T W , RIVERA-DÍAZ-DEL-CASTILLO P E J . Nanoprecipitation in bearing steels [J]. Acta Materialia , 2011 , 59 ( 19 ): 7155 - 7167 .
KANG J H , RIVERA-DÍAZ-DEL-CASTILLO P E J . Carbide dissolution in bearing steels [J]. Computational Materials Science , 2013 , 67 : 364 - 372 .
GUETARD G , TODA-CARABALLO I , RIVERA-DÍAZ-DEL-CASTILLO P E J . Damage evolution around primary carbides under rolling contact fatigue in VIM-VAR M50 [J]. International Journal of Fatigue , 2016 , 91 : 59 - 67 .
GUAN J , WANG L Q , ZHANG Z Q , et al . Fatigue crack nucleation and propagation at clustered metallic carbides in M50 bearing steel [J]. Tribology International , 2018 , 119 : 165 - 174 .
JELITA RYDEL J , TODA-CARABALLO I , GUETARD G , et al . Understanding the factors controlling rolling contact fatigue damage in VIM-VAR M50 steel [J]. International Journal of Fatigue , 2018 , 108 : 68 - 78 .
DU N Y , LIU H H , CAO Y F , et al . In situ investigation of the fracture of primary carbides and its mechanism in M50 steel [J]. Materials Characterization , 2022 , 186 : 111822 .
LIU W F , GUO Y F , CAO Y F , et al . Transformation behavior of primary MC and M 2 C carbides in Cr 4 Mo 4 V steel [J]. Journal of Alloys and Compounds , 2021 , 889 : 161755 .
侯志远 , 刘威峰 , 徐斌 , 等 . 热加工过程中M50轴承钢一次碳化物的形成与演化 [J]. 热加工工艺 , 2024 , 53 ( 1 ): 105 - 110 .
HOU Zhiyuan , LIU Weifeng , XU Bin , et al . Formation and evolution of primary carbides in M50 bearing steel during hot working [J]. Hot Working Technology , 2024 , 53 ( 1 ): 105 - 110 . (In Chinese)
吴玉成 , 姜宏伟 , 胡园 , 等 . 多向锻造对M50钢一次碳化物破碎机制的影响 [J]. 中国冶金 , 2020 , 30 ( 9 ): 98 - 103 .
WU Yucheng , JIANG Hongwei , HU Yuan , et al . Effect of multi-direction forging on carbide evolution of M50 steel [J]. China Metallurgy , 2020 , 30 ( 9 ): 98 - 103 . (In Chinese)
DECOST B L , HOLM E A . A computer vision approach for automated analysis and classification of microstructural image data [J]. Computational Materials Science , 2015 , 110 : 126 - 133 .
DURMAZ A R , MÜLLER M , LEI B , et al . A deep learning approach for complex microstructure inference [J]. Nature Communications , 2021 , 12 ( 1 ): 6272 .
YANG J Y , KANG G Z , KAN Q H . A novel deep learning approach of multiaxial fatigue life-prediction with a self-attention mechanism characterizing the effects of loading history and varying temperature [J]. International Journal of Fatigue , 2022 , 162 : 106851 .
李维刚 , 谌竟成 , 范丽霞 , 等 . 基于卷积神经网络的钢铁材料微观组织自动辨识 [J]. 钢铁研究学报 , 2020 , 32 ( 1 ): 33 - 43 .
LI Weigang , CHEN Jingcheng , FAN Lixia , et al . Automatic identification of microstructure of iron and steel material based on convolutional neural network [J]. Journal of Iron and Steel Research , 2020 , 32 ( 1 ): 33 - 43 . (In Chinese)
段献宝 , 何惠珍 , 李平平 , 等 . 基于深度卷积神经网络的钢材微观组织分类识别 [J]. 铁道车辆 , 2022 , 60 ( 1 ): 43 - 47 .
DUAN Xianbao , HE Huizhen , LI Pingping , et al . Classification and identification of steel microstructure based on deep convolution neural network [J]. Rolling Stock , 2022 , 60 ( 1 ): 43 - 47 . (In Chinese)
苏晨 , 任志俊 , 范彪 , 等 . 基于注意力机制与ResNet的残余奥氏体评级研究 [J]. 轻工机械 , 2023 , 41 ( 2 ): 78 - 84 .
SU Chen , REN Zhijun , FAN Biao , et al . Research on retained austenite rating based on attention mechanism and ResNet [J]. Light Industry Machinery , 2023 , 41 ( 2 ): 78 - 84 . (In Chinese)
彭凡 , 邹司农 , 任毅如 . 基于深度学习的复合材料螺栓连接失效预测 [J]. 机械强度 , 2023 , 45 ( 2 ): 447 - 453 .
PENG Fan , ZOU Sinong , REN Yiru . Failure prediction of bolted connection of composite materials based on deep learning [J]. Journal of Mechanical Strength , 2023 , 45 ( 2 ): 447 - 453 . (In Chinese)
HE K M , GKIOXARI G , DOLLAR P , et al . Mask R-CNN [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2020 , 42 ( 2 ): 386 - 397 .
WANG C Y , ZHONG C M . Adaptive feature pyramid networks for object detection [J]. IEEE Access , 2021 , 9 : 107024 - 107032 .
吴定海 , 任国全 , 王怀光 , 等 . 基于卷积神经网络的机械故障诊断方法综述 [J]. 机械强度 , 2020 , 42 ( 5 ): 1024 - 1032 .
WU Dinghai , REN Guoquan , WANG Huaiguang , et al . The review of mechanical fault diagnosis methods based on convolutional neural network [J]. Journal of Mechanical Strength , 2020 , 42 ( 5 ): 1024 - 1032 . (In Chinese)
KINGMA D P , BA J L . Adam:a method for stochastic optimization [C]// 3rd International Conference on Learning Representations , ICLR 2015⁃Conference Track Proceedings . Ithaca : ArXiv , 2015 : 1 - 15 .
HE G Q , HUO Y C , HE M Y , et al . A novel orthogonality loss for deep hierarchical multi-task learning [J]. IEEE Access , 2020 , 8 : 67735 - 67744 .
高楚寒 , 葛思楠 , 李万明 , 等 . 高速钢碳化物偏析的研究现状 [J]. 中国冶金 , 2019 , 29 ( 5 ): 1 - 5 .
GAO Chuhan , GE Sinan , LI Wanming , et al . Research status of carbide segregation in high speed steel [J]. China Metallurgy , 2019 , 29 ( 5 ): 1 - 5 . (In Chinese)
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构