Gas Recognition Using Artificial Neural Networks
摘要
In the framework of air environment monitoring the paper considers the method of gas recognition with compensation of the results of measurement transformation of the last readings of gas sensors with compensation of the influence of temperature and humidity on the determination of the composition of the studied environment on the basis of artificial neural networks. When applying an artificial neural network (ANN) at the stage of network training it is proposed to use a set of sensor characteristics in a given range of temperature and humidity. The results of experimental recognition of the surrounding air environment are discussed.