Prediction of Toxic Gases Using Intelligent Multi-sensors Combined with Artificial Neural Networks

摘要

The security of monitor indoor air quality using sensors is not yet widespread. However, it is an efficient way to control the toxic gazes coming from large industrial facilities when traditional instrument are not usable especially in low concentration. This paper presents the prediction's power of toxic gases using neural networks MLP off-line type. Back propagation algorithm was used to train a multi-layer feed-forward network (descent gradient algorithm). The data used in this work are stemming from a system of intelligent multi-sensors analysis and signal processing in order to detect hydrogen sulfide(H_2S), NO_2 (nitrogen dioxide) and their mixture (H2S-NO_2) in low concentration (one ppm). The successful results based on different accuracy in terms of statistical criteria, approve the robustness of our developed model that gives a certain power for electronic nose prediction.