Underground fire detection and nuisance alarm discrimination

The advantages of multiple fire sensors for early fire detection and nuisance alarm discrimination in underground coal mines was demonstrated at a fire detection research program the program was conducted at the National Institute for Occupational Safety and Health (NIOSH), Pittsburgh research laboratory. A neural network was developed by NIOSH to assess real time sensor data to discriminate nuisance alarm. The research showed that ionization and optical smoke fire sensors performed better than carbon monoxide (CO) sensors for small fire detection. Deployment of new detection devices with the traditional ones resulted in the determination of the material burning and discrimination of the nuisance alarm from the real ones.