A new embedded e-nose system to identify smell of smoke

Abstract

This work examines the important applications of modern electronic noses and focus on fire detection system due to advantages over classical method of detections. The three components of an electronic nose consist of sample handling; detection and data processing system are designed. These devices are typically array of sensors used to detect and distinguish odors precisely in complex samples and at low cost and capable of classifying smoke based on neural networks. The potential advantages of such an approach include, the ability to characterize complex mixtures without the need to identify and quantify individual components, Five commercial gas sensors (Figaro) with interesting cross sensitivity and low power consumption are used in sensor array; a micro-controller equipped with a compact flash memory assures data acquisition, analyzing procedures in real time. Signals from this sensor array have unique pattern and applied to the embedded system as inputs. The proposed method in this paper has 97.2% efficiency in smoke classification.