CO and CO2 sensors using magnitude and slope information, and background subtraction were used to evaluate a fire alarm algorithm based on a probabilistic neural network [6]. Flaming fires were identified correctly, but smoldering fires were problematic. A fire detection system having a multi-criteria alarm algorithm and multi-component sensor system has the potential to reduce false alarms generated by individual fire detectors, and to reduce the time to alarm in the presence of fires.
A potential method to reduce or eliminate false alarms generated by aircraft smoke detector operating alone and to reduce the time to alarm is described here. The fire detection system combines the simultaneous measurements of smoke, carbon monoxide, and carbon dioxide. A simple fire alarm algorithm, based on the rates of increase of these three components, is developed and assessed using fire tests of combustible materials, liquid fuels, and nuisance sources.