Development of an electronic nose for fire detection

We report the development of an electronic nose based on an array of eight conducting polymer (CP) sensors for fire detection. Gas chromatography-mass spectrometry (GC-MS) and Fourier transform infrared (FTIR) spectroscopy analyses of smoke from four test fires adapted from the EN54 standard and of cigarette smoke, a main source of nuisance in fire detection, were used to identify chemical markers for each type of smoke. Several sensors were tested individually with markers in order to select suitable sensors for the new array. Initial testing showed a broad selectivity of the array to five markers from each type of smoke. The electronic nose was also able to discriminate all five fire and non-fire events as demonstrated by principal component analysis (PCA). The results are promising and suggest that the e-nose technology is a good approach to reduce false alarms in fire detection. © 2006 Elsevier B.V. All rights reserved.