基于传感器阵列与神经网络的气体检测系统  

A Gas Testing System Based on the Gas Sensor Array and the Neural Network

作　　者：马戎[1] 周王民[2] 陈明[1] 

机构地区：[1]西北工业大学自动化学院,西安710072 [2]西北工业大学应用物理系,西安710072

出　　处：《传感技术学报》2004年第3期395-398,共4页Chinese Journal of Sensors and Actuators

摘　　要：在分析研究电子鼻理论和系统组成的基础上 ,设计构建了一套传感器阵列与人工神经网络相结合的混合气体检测系统。并采用该系统对三种气体传感器 (一氧化碳CO、二氧化硫SO2 和二氧化氮NO2 )进行了实验 ,对实验数据用神经网络 (BP和RBF)进行了分析、识别和气体体积分数的计算。结果显示该检测系统识别准确 ,不仅能够解决气体传感器交叉敏感问题 ,提高器件的选择性 ,而且具有智能化和多功能化等优点。Based on the study of the theory and constituent of the electronic nose system, a set of combined gas sensor array system with artificial neural network, for detection of gas mixture is designed and constructed. Three gas sensors(CO,SO 2,NO 2) are experimented by the system, and the data are analyzed,identified by using artificial neural network(BP: back propagation and RBF: radial basis function), from which the volume fractions of gases are calculated.The research results show that the identification of the system is precise.It solves the problem of the gas cross sensitivity, helping to improve the gas sensor selective, realize the artificial intelligence and multifunction.

关 键 词：传感器阵列 神经网络 交叉敏感 识别 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP212[自动化与计算机技术—控制科学与工程]