A fire alarm judgment method using multiple smoke alarms based on Bayesian estimation

Smoke alarms are the most widely used fire sensors; however, their false-alarm rate is high. Owing to the difficulties in replacing all installed smoke alarms in a short period, improving the fire detection accuracy of the installed alarms is a significant challenge for the fire emergency response team. Therefore, this study proposes a fire alarm judgment method with multiple smoke alarms based on Bayesian estimation. To this end, we propose a novel criterion called fire alarm authenticity, wherein the alarm time intervals of multiple smoke alarms are used to calculate the posterior probability distribution of the location and intensity of the fire source without installing any other type of sensors. Subsequently, an alarm sequence classification method based on the proposed criterion is developed to judge a real fire and is validated through simulations of both real fires and false alarms. The results show that the proposed method can identify 77.5% of false alarms based on no real fires to be misjudged. Applications in real fire alarm systems are also discussed, which indicate that the false alarm recognition rate reaches 80%. The proposed method provides a theoretical basis for reducing the existing false-alarm rate with multiple same-type fire alarms or detectors.