|
|
A deep learning-based method for segmentation and quantitative characterization of microstructures in weathering steel from sequential scanning electron microscope images |
Bing Han1,2, Wei-hao Wan1,3, Dan-dan Sun1,2, Cai-chang Dong1,2, Lei Zhao1,3, Hai-zhou Wang1,3 |
1 Beijing Advanced Innovation Center for Materials Genome Engineering, Central Iron & Steel Research Institute, Beijing 100081, China 2 Qingdao NCS Testing & Corrosion Protection Technology Co., Ltd., Qingdao 266071, Shandong, China 3 Beijing Key Laboratory of Metal Materials Characterization, Central Iron & Steel Research Institute, Beijing 100081, China |
|
|
Abstract Microstructural classification is typically done manually by human experts, which gives rise to uncertainties due to subjectivity and reduces the overall efficiency. A high-throughput characterization is proposed based on deep learning, rapid acquisition technology, and mathematical statistics for the recognition, segmentation, and quantification of microstructure in weathering steel. The segmentation results showed that this method was accurate and efficient, and the segmentation of inclusions and pearlite phase achieved accuracy of 89.95% and 90.86%, respectively. The time required for batch processing by MIPAR software involving thresholding segmentation, morphological processing, and small area deletion was 1.05 s for a single image. By comparison, our system required only 0.102 s, which is ten times faster than the commercial software. The quantification results were extracted from large volumes of sequential image data (150 mm2, 62,216 images, 1024 × 1024 pixels), which ensure comprehensive statistics. Microstructure information, such as three-dimensional density distribution and the frequency of the minimum spatial distance of inclusions on the sample surface of 150 mm2, were quantified by extracting the coordinates and sizes of individual features. A refined characterization method for two-dimensional structures and spatial information that is unattainable when performing manually or with software is provided. That will be useful for understanding properties or behaviors of weathering steel, and reducing the resort to physical testing.
|
|
|
|
|
Cite this article: |
Bing Han,Wei-hao Wan,Dan-dan Sun, et al. A deep learning-based method for segmentation and quantitative characterization of microstructures in weathering steel from sequential scanning electron microscope images[J]. Journal of Iron and Steel Research International, 2022, 29(5): 836-845.
|
|
|
|
[1] |
Shao-jie Lv, Shui-ze Wang, Gui-lin Wu, Jun-heng Gao, Xu-sheng Yang, Hong-hui Wu, Xin-ping Mao. Application of phase-field modeling in solid-state phase transformation of steels[J]. JOURNAL OF IRON AND STEEL RESEARCH,INTERNATIONAL, 2022, 29(6): 867-880. |
[2] |
Kai Wang, Chao-jie Yan, Chen-hua Yuan, Xi-chen Yang, Li-jia Zhao, Qiang Wang. Progress in research on diffusional phase transformations of Fe–C alloys under high magnetic fields[J]. JOURNAL OF IRON AND STEEL RESEARCH,INTERNATIONAL, 2022, 29(5): 707-718. |
[3] |
Xiao-xiao Liu, Zheng Zhang, Jie Zhang, Ran Yang, Cheng-shuang Yu, Jun-wei Qiao, Li-na Han. Enhanced strength and toughness in 40CrNiMo steels by austempering below martensite start temperature[J]. JOURNAL OF IRON AND STEEL RESEARCH,INTERNATIONAL, 2022, 29(5): 810-818. |
[4] |
Xin-pan Yu, Hui-bin Wu, Yang Gu, Rui Yuan, You-you Zhang, Yu-hui Feng. Effect of prior martensite on bainite transformation and microstructure of high-carbon nano-bainitic steel[J]. JOURNAL OF IRON AND STEEL RESEARCH,INTERNATIONAL, 2022, 29(4): 647-654. |
[5] |
Run-feng Peng, Min Zhang, Yu-hang Li, Yue-long Yu, Ying-chun Guan, Zhun-li Tan. Microstructural development and wear properties analyses of Fe-based coatings on bainitic steel by laser cladding[J]. JOURNAL OF IRON AND STEEL RESEARCH,INTERNATIONAL, 2022, 29(4): 687-697. |
[6] |
Shi-ping Xi, Xin-liang Gao, Wei Liu, Yan-lu Lu, Gui-qin Fu, Hui-cheng Tao, Yong-chang Zang. Hot deformation behavior and processing map of low-alloy offshore steel[J]. JOURNAL OF IRON AND STEEL RESEARCH,INTERNATIONAL, 2022, 29(3): 474-483. |
|
|
|
|