基于人工神经网络的气体定性分析方法  

RESEARCH ON QUALITATIVE ANALYSIS OF GASES BASED ON ARTIFICIAL NEURAL NETWORK

作　　者：高峰[1] 崔金宝[1] 曲建岭[1] 王艺兵[2] 

机构地区：[1]海军航空工程学院,青岛266041 [2]青岛大学,青岛266071

出　　处：《青岛大学学报（工程技术版）》2000年第1期6-9,共4页Journal of Qingdao University(Engineering & Technology Edition)

摘　　要：提出将气体传感器阵列与前馈神经网络模式识别技术相结合 ,解决气体传感器的“交叉敏”问题 ,从而完成气体的定性、定量分析 ;针对常规 BP算法的缺点 ,构造了基于自适应调整步长和加动量因子的改进 BP算法用于前馈神经网络的训练 ;通过实验对 H2 、CH4 、CO等三种气体进行了识别 。An artificial intelligent olfactory system, which is composed of a metal oxide semiconductor sensor array with a feed forward neural network, is designed to identify three kinds of gases (CO, H 2 and CH 4). An improved BP algorithm is used for training neural network. It can not only enhance a lot the convergence rate of learning, but also lessen in some cases the difficulty of being easily trapped in local minimum. Experiment results show clearly that the system can completely discriminate CO, H 2 and CH 4. Further study shows this system may make qualitative analysis of these gases of their mixtures.

关 键 词：交叉敏 交馈神经网络 气体传感器阵列 定性分析 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]