Coal and Rock Classification with Rib Images and Machine Learning Techniques

Details

• Personal Author:
  Xue Y
• Description:
  Classification of rock and coal is one preliminary problem for fully automated or intelligent mining. It assists for the automated rib stability analysis and enables the shearer to adjust the drums without human intervention. In this paper, the classification of rock from coal on rib images has been studied with machine learning techniques. A database of rock and coal image has been created by filtering photographs taken by NIOSH researchers in gateroad during site visits and only the images with fresh areas of rock and coal on the rib were selected. Machine learning was conducted on patches with a determined size, which are smaller images randomly extracted from each rock or coal image. After training, the classifier was validated with the testing dataset and an accuracy score of 0.9 was obtained. The influence of patch size and classifier was also investigated. The trained classifier was then applied to classify rock and coal on a new rib image with three rock layers of different thicknesses and good agreement was achieved. [Description provided by NIOSH]
• Subjects:
  Automation Computers Database Mining Occupational Health Photography Safety
• Keywords:
  Algorithms Artificial Intelligence Author Keywords: Rock Classifcation Coal Mines Databases Image Processing Machine Learning Neural Networks Patch Random Forest Rock Mechanics SVM Visual Images

  More +
• Series:
  Mining Publications
• ISSN:
  2524-3462
• Document Type:
  Text
• Genre:
  Journal Article
• Place as Subject:
  OSHA Region 3 ; Pennsylvania
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Division:
  PMRD - Pittsburgh Mining Research Division
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Pages in Document:
  453-465
• Volume:
  39
• Issue:
  2
• NIOSHTIC Number:
  nn:20064412
• Citation:
  Min Metall Explor 2022 Apr; 39(2):453-465
• Contact Point Address:
  Yuting Xue, CDC, NIOSH, Pittsburgh Mining Research Division, Pittsburgh, PA, USA
• Email:
  qcj1@cdc.gov
• Federal Fiscal Year:
  2022
• Peer Reviewed:
  True
• Source Full Name:
  Mining, Metallurgy & Exploration
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:dde259e7a0341e22db66a2786a091feec60bbb4e3f0986ebb8a9125290436964961a3b861f7806458019e2642d156fd0abcd5c7fbb847d0c95a451196597041c
• Download URL:
  https://stacks.cdc.gov/view/cdc/215516/cdc_215516_DS1.pdf
• File Type:
  [PDF - 1.65 MB ]