Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 10 min ago
Peer-reviewedCC BY 4.0PLOS One

Crack identification and detection in mine boreholes using deep learning: A case study of hexi coal mine

  • Ruifeng Huang1
  • Wanshun He2
  • Lu Chen3
  • Yanbin Xiang4
  • Wenzhe Li5
5 affiliations
  1. 1School of Emergency Technology and Management, North China Institute of Science & Technology, Langfang, China
  2. 2CCTEG Chongqing Research Institute, Chongqing, China
  3. 3State Key Laboratory for Tunnel Engineering, China University of Mining & Technology, Beijing, China
  4. 4China National Administration of Coal Geology No.173 Exploration Team, Baoding, China
  5. 5Sinosteel Shijiazhuang Engineering Design and Research Institute Co., Ltd., Shijiazhuang, China
Open at sourceDOICite

Abstract

The internal cracks in deep rock masses are an important factor determining the safety of coal mining. The borehole peeping technology is an important method for obtaining the distribution of coal and rock fractures in deep geological engineering. However, there are often problems such as strong background interference and complex joints in real mines, which bring greater challenges to obtaining the distribution of cracks. Therefore, this study proposes a deep learning-based method for identifying internal cracks, which is used for the intelligent identification and analysis of cracks in drilled rock masses. The experimental verification was carried out based on the real borehole peeping images of the tunnels in Hexi Coal Mine as the data set. By embedding the ResCBAM attention mechanism into the YOLOv8 head network, the reliability and accuracy of identifying internal cracks in rock were further enhanced. The test results show that, the proposed Res-YOLOv8 algorithm can more accurately suppress the interference of complex backgrounds and present the morphological characteristics of rock cracks to compare with the fusion of typical attention mechanisms SE and CBAM with YOLOv8. The ResCBAM-YOLOv8 algorithm demonstrates strong performance in the evaluation indicators of confusion matrix, loss rate, precision, recall and MPA. The proposal of method has improved the efficiency of detecting and identifying cracks in coal and rock masses in real mines, and provided more reliable technical support for the stability evaluation of coal mine roof.

Related

  1. Counterfeit Citri Reticulatae Pericarpium Identification: Multi‐Class Detection Using Vis/ NIR Spectroscopy and Residual Neural Networks
    Chao Ma, Mingkun Zhang, Jianwei Ma +4
    Food Science & NutritionPeer-reviewedCC BY8 citedAnalytical chemistryOpenAlex
  2. Integrated machine learning, pharmacophore screening, and structure-based computational approaches for the identification of novel JAK3 inhibitors
    Muhammad Yasir, Jinyoung Park, Eun-Taek Han +4
    Future Medicinal ChemistryPeer-reviewedLicence not statedFull textMedicinal chemistry & drug discoveryPMC
  3. Seasonal variation in water quality and evaluation of optimal iron removal conditions in acid mine drainage at A mine, Japan
    Shigeshi Fuchida, Aoi Nakamura, Seiya Kato +5
    Scientific ReportsPeer-reviewedCC BY 4.0Full textEnvironmental chemistryCrossref
  4. Potential and limits of Fe-SMA for asphalt crack self-repair: a critical review on thermal FIT & active reinforcement
    Michel Muanda Ntoto
    RSC advancesPeer-reviewedCC BYFull textGeneral chemistryEurope PMC
  5. Crack-Width Threshold-Guided Design of Self-Healing Polyethylene Fiber-Reinforced Engineered Cementitious Composites (ECCs)
    Zhigang Zhang, Xiangwen Lei, Jamal A. Abdalla +3
    PolymersPeer-reviewedCC BYFull textMaterials & polymersEurope PMC

Cite

BibTeXRIS
BibTeX
@article{huang2026crack,
  title = {{Crack identification and detection in mine boreholes using deep learning: A case study of hexi coal mine}},
  author = {Ruifeng Huang and Wanshun He and Lu Chen and Yanbin Xiang and Wenzhe Li},
  journal = {PLOS One},
  year = {2026},
  month = nov,
  doi = {10.1371/journal.pone.0353249},
  url = {https://doi.org/10.1371/journal.pone.0353249},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Crack identification and detection in mine boreholes using deep learning: A case study of hexi coal mine
AU  - Ruifeng Huang
AU  - Wanshun He
AU  - Lu Chen
AU  - Yanbin Xiang
AU  - Wenzhe Li
PY  - 2026
DA  - 2026/11/05
JO  - PLOS One
DO  - 10.1371/journal.pone.0353249
UR  - https://doi.org/10.1371/journal.pone.0353249
AB  - The internal cracks in deep rock masses are an important factor determining the safety of coal mining. The borehole peeping technology is an important method for obtaining the distribution of coal and rock fractures in deep geological engineering. However, there are often problems such as strong background interference and complex joints in real mines, which bring greater challenges to obtaining the distribution of cracks. Therefore, this study proposes a deep learning-based method for identifying internal cracks, which is used for the intelligent identification and analysis of cracks in drilled rock masses. The experimental verification was carried out based on the real borehole peeping images of the tunnels in Hexi Coal Mine as the data set. By embedding the ResCBAM attention mechanism into the YOLOv8 head network, the reliability and accuracy of identifying internal cracks in rock were further enhanced. The test results show that, the proposed Res-YOLOv8 algorithm can more accurately suppress the interference of complex backgrounds and present the morphological characteristics of rock cracks to compare with the fusion of typical attention mechanisms SE and CBAM with YOLOv8. The ResCBAM-YOLOv8 algorithm demonstrates strong performance in the evaluation indicators of confusion matrix, loss rate, precision, recall and MPA. The proposal of method has improved the efficiency of detecting and identifying cracks in coal and rock masses in real mines, and provided more reliable technical support for the stability evaluation of coal mine roof.
SN  - 1932-6203
ER  -