Real-time neural network application to mine fire-nuisance emissions discrimination.
Edwards JC; Franks RA; Friel GF; Lazzara CP; Opferman JJ
Mine ventilation: Proceedings of the 10th U.S./North American Mine Ventilation Symposium, Anchorage, Alaska, May 16-19, 2004. Lisse, Netherlands: Balkema, 2004 May; :425-431
The National Institute for Occupational Safety and Health (NIOSH) implemented a real-time neural network system that can discriminate mine fires from nuisance diesel emissions as part of an atmospheric mine monitoring system in NIOSH's Safety Research Coal Mine. The real-time response of a neural network to fire sensor outputs was demonstrated for coal and belt combustion in the presence of diesel emissions. The fire sensors consisted of an optical path smoke sensor, a carbon monoxide sensor, and two types of metal oxide semiconductor sensors. The real-time neural network was trained with coal, wood, and belt fire experiments with and without diesel emissions background. The trained neural network successfully predicted mine fires with these combustibles in the smoldering stage before the onset of flames.
Mine-fires; Diesel-emissions; Sensors; Underground-mining; Coal-mining; Safety-research
NIOSH Pittsburgh Research Laboratory, P.O. Box 18070, Pittsburgh, PA 15236
Conference/Symposia Proceedings; Book or book chapter
Ganguli R; Bandopadhyay S
Mine ventilation: Proceedings of the 10th U.S./North American Mine Ventilation Symposium