Home Journals Articles Updates About
CN
image
收藏切换
Recognition of Rock Fracture in Open-Pit Mines by Borehole Imaging Based on Improved U-Net Model
收藏切换
PDF
Wenyao SONG1, Mei ZHANG2, Lianjun GUO1, Ding DENG1, Chong GAO3, Xin ZHAO4
Mining and Metallurgical Engineering | 2025, 45(4) : 47 - 51
Less
收藏切换
Mining and Metallurgical Engineering | 2025, 45(4): 47-51
• MINING •
Recognition of Rock Fracture in Open-Pit Mines by Borehole Imaging Based on Improved U-Net Model
Full
Wenyao SONG1, Mei ZHANG2, Lianjun GUO1, Ding DENG1, Chong GAO3, Xin ZHAO4
Affiliations
  • 1.School of Architecture and Civil Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning, China
  • 2.Xuanhua Vocational College of Science and Technology, Zhangjiakou 075100, Hebei, China
  • 3.China Railway 19th Bureau Group Co., Ltd., Beijing 100176, China
  • 4.Mining Investment Co., Ltd., China Railway 19th Bureau Group, Beijing 100161, China
Published: 2025-08-01 doi: 10.3969/j.issn.0253-6099.2025.04.008
Outline
收藏切换

To improve the accuracy of fracture recognition in borehole images, a borehole fracture recognition approach for open-pit mine was proposed. First, borehole images of an open-pit mine is obtained with an intelligent borehole inspection camera, and then data augmentation is performed by using random cropping and image flipping, while median filtering is used for noise reduction and images are converted to grayscalere, so as to eliminate noise and reduce computational complexity. Next, spatial attention and channel attention mechanisms are integrated into the U-Net model to improve the semantic segmentation model for fractures, forming an AU-Net model, which can enhance the model′s ability to extract features from both overall and local image information. Experimental results show that compared to the original U-Net model, the AU-Net model can achieve lower loss and higher accuracy in the fracture recognition dataset by borehole imaging. Specifically, the mean intersection over union is improved by 4.38 percentage points, up to 82.34%, bringing better image segmentation effect.

borehole imaging  /  fracture recognition  /  U-Net network  /  attention mechanism  /  fracture extraction  /  machine learning  /  semantic segmentation  /  image recognition
Wenyao SONG, Mei ZHANG, Lianjun GUO, Ding DENG, Chong GAO, Xin ZHAO. Recognition of Rock Fracture in Open-Pit Mines by Borehole Imaging Based on Improved U-Net Model[J]. Mining and Metallurgical Engineering, 2025 , 45 (4) : 47 -51 . DOI: 10.3969/j.issn.0253-6099.2025.04.008
Appendix
Less
Year 2025 volume 45 Issue 4
PDF
61
27
Cite this Article
BibTeX
Article Info
doi: 10.3969/j.issn.0253-6099.2025.04.008
  • Receive Date：2025-01-28
  • Online Date：2026-03-05
  • Published：2025-08-01
Article Data
Affiliations
History
  • Received：2025-01-28
Funding
Affiliations
    1.School of Architecture and Civil Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning, China
    2.Xuanhua Vocational College of Science and Technology, Zhangjiakou 075100, Hebei, China
    3.China Railway 19th Bureau Group Co., Ltd., Beijing 100176, China
    4.Mining Investment Co., Ltd., China Railway 19th Bureau Group, Beijing 100161, China
References
Share
https://castjournals.cast.org.cn/joweb/kygczz/EN/10.3969/j.issn.0253-6099.2025.04.008
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