Abstract

Indoor fire detection using gas chemical sensing has been a subject of investigation since the early nineties. This approach leverages the fact that, for certain types of fire, chemical volatiles appear before smoke particles do. Hence, systems based on chemical sensing can provide faster fire alarm responses than conventional smoke-based fire detectors. Moreover, since it is known that most casualties in fires are produced from toxic emissions rather than actual burns, gas-based fire detection could provide an additional level of safety to building occupants. In this line, since the 2000s, electrochemical cells for carbon monoxide sensing have been incorporated into fire detectors. Even systems relying exclusively on gas sensors have been explored as fire detectors. However, gas sensors respond to a large variety of volatiles beyond combustion products. As a result, chemical-based fire detectors require multivariate data processing techniques to ensure high sensitivity to fires and false alarm immunity. In this paper, we the survey toxic emissions produced in fires and defined standards for fire detection systems. We also review the state of the art of chemical sensor systems for fire detection and the associated signal and data processing algorithms. We also examine the experimental protocols used for the validation of the different approaches, as the complexity of the test measurements also impacts on reported sensitivity and specificity measures. All in all, further research and extensive test under different fire and nuisance scenarios are still required before gas-based fire detectors penetrate largely into the market. Nevertheless, the use of dynamic features and multivariate models that exploit sensor correlations seems imperative.

Highlights

  • Nowadays, the most popular and widespread fire alarm systems are based on the detection of smoke

  • We may take as reference the values contained in the ISO13571 standard [30]. This standard is used in the estimation of the toxic potency of mixtures and it considers different reference values to weight the effects of the different constituents of the fumes, namely LC50,hydrogen chloride (HCl) = 1000 ppm, LC50,hydrogen fluoride (HF) = 500 ppm, LC50,hydrogen bromide (HBr) = 1000 ppm, where LC50 represents the gas concentration that is lethal for half of the exposed population during a time period

  • In scenarios with limited ventilation, an open fire rapidly consumes available oxygen and it transits to under-ventilation conditions (φ > 1) that typically lead to the emission of toxic gases at high concentration levels

Read more

Summary

Introduction

The most popular and widespread fire alarm systems are based on the detection of smoke. Chemical-based fire detection could offer additional safety to building occupants as it is known that most casualties in fires are produced from toxic emissions rather than actual burns [1]. The reliability of fire predictions was successfully improved when heat and CO sensing was added to smoke detectors and they were combined with dedicated calibration models Standardized tests for such kind of multisensor systems are available. These non-standardized systems have been subject of investigation by the community as they can detect more toxicants and combustion products and can provide faster detection, they suffer from low specificity.

Fire Detectors Based on Smoke Detection
Gas Emission in Fires
Main Toxicants from Fire Emissions
Carbon Dioxide
Carbon Monoxide
Hydrogen Cyanide
Nitrogen Oxides
Sulphur Dioxide
Halogen Acids
Organic Irritants
Toxicity of Released Gases in Fire
Asphyxiant Gases
Irritant Emissions
Combined Toxic Effects
Toxicant Production Depending on Fire Scenarios and Burning Materials
Example time evolutionofofOO andCO
Standards for Fire Detectors
Concentration and exposure the different interferent gases appear
Gas Sensors for Combustion Products
Decision Tree and Hard Rules
The coupling
Neural Networks
Probabilistic Neural Network
Hierarchical LDA
Single Sensor
Hard Rules
Fuzzy Logic Rules
Principal Component Analysis and Nearest Neighbours Classifiers
Other Approaches
Findings
Summary and Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call