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.
出处
《青岛大学学报（工程技术版）》
CAS
2000年第1期6-9,共4页
Journal of Qingdao University(Engineering & Technology Edition)
关键词
交叉敏
交馈神经网络
气体传感器阵列
定性分析
cross sensitivity
feed forward neural networks
gas sensor array
qualitative analysis
