Quantitative analysis of different volatile organic compounds using an improved electronic nose

摘要: This paper sets up an improved electronic nose with automatic sampling mode, large volumetric vapors and constant temperature for headspace gas sensor array. In order to facilitate the fast recovery good repeatability of sensors, steps taken include (A) short-time contact odors measured; (B) long-time purification using environmental air; (C) exact calibration clean air before sampling. We employ multiple single-output perceptrons discriminate quantify kinds odors. task is first regarded as two-class discrimination problems then quantification problems, accomplished by followed perceptrons. The experimental results measuring quantifying 12 volatile organic compounds changing concentrations show that type a hierarchical perceptron model has simple structure, easy operation, performance.