Fire size and response time predictions in underground coal mines using neural networks.

Details

• Personal Author:
  Barros-Daza MJ ; Hodges JL ; Lattimer BY ; Luxbacher, Kray D.
• Description:
  The prediction of the coal mine fire response time, defined as the remaining time before conditions at attack positions grow untenable for firefighters, plays a vital role in the decision-making process during a mine fire scenario. The knowledge of the response time along with the fire size, fire location, and arrival time could allow for the most suitable decision regarding direct or remote approach to the fire in the mine, mine evacuation planning, and remote attack from the surface. For this reason, this paper presents a data-driven approach to predict the response time and fire size based on available and measurable parameters during underground coal mine fires using two interconnected artificial neural networks (ANNs). A total of 300 fire dynamic simulator (FDS) and fire and smoke simulator (FSSIM) simulations of a straight and flat mine entry (replicating a belt entry) with different fire sizes, air velocities, and dimensions were used in training and testing the ANNs. The results showed that 95% of fire size and response time predictions should be within +/- 29 kW and +/- 4 s of true values obtained in the fire models, respectively. The approach presented in this work can provide instantaneous predictions of response time and fire size during ongoing mine fires. Additionally, this approach can be utilized in other mine fire locations as well as in different types of tunnels. [Description provided by NIOSH]
• Subjects:
  Emergencies Firefighters Mining Occupational Health Safety
• Keywords:
  Author Keywords: ANN Neural Network; Mine Frefghters; Response Time; Fire Size Mining; Underground Mines; Coal Mines; Mine Fires; Fire Fighters; Artificial Intelligence; Neural Networks; Emergency Response; Simulation Methods;
• ISSN:
  2524-3462
• Document Type:
  Text
• Funding:
  Contract
• Genre:
  Journal Article
• Place as Subject:
  OSHA Region 3 ; Virginia
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Volume:
  39
• Issue:
  3
• NIOSHTIC Number:
  nn:20065254
• Citation:
  Min Metall Explor 2022 Jun; 39(3):1087-1098
• Contact Point Address:
  Manuel J. Barros-Daza, Virginia Tech (Mining and Minerals Engineering), Blacksburg, VA, USA
• Email:
  manuel1@vt.edu
• Federal Fiscal Year:
  2022
• Performing Organization:
  Virginia Polytechnic Institute & State University
• Peer Reviewed:
  True
• Start Date:
  20140901
• Source Full Name:
  Mining, Metallurgy & Exploration
• End Date:
  20190831
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:f1dc41447f3ce37de8763cfdd45b462b3248dfa9bf396087bc93b352ab39e059934a85060dbe56f672aecf222eecf061be4268da1ccc3ba8e9ed94c561769a90
• Download URL:
  https://stacks.cdc.gov/view/cdc/248890/cdc_248890_DS1.pdf
• File Type:
  [PDF - 1.45 MB ]