| 基于人工神经网络的气体定性分析方法 |
| |
| 引用本文： | 高峰,崔金宝,曲建岭,王艺兵.基于人工神经网络的气体定性分析方法[J].青岛大学学报(工程技术版),2000,15(1):6-9. |
| |
| 作者姓名： | 高峰 崔金宝 曲建岭 王艺兵 |
| |
| 作者单位： | 1. 海军航空工程学院,青岛,266041
2. 青岛大学,青岛,266071 |
| |
| 摘 要： | 提出将气体传感器阵列与交馈神经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，结果表明利用气体传感器阵列和前馈神经网络进行气体定性分析是可行的。
|
| 关 键 词： | 交叉敏 交馈神经网络 气体传感器阵列 定性分析 |
RESEARCH ON QUALITATIVE ANALYSIS OF GASES BASED ON ARTIFICIAL NEURAL NETWORK |
| |
| GAO Feng,CUI Jin-bao,QU Jian-ling,WANG Yi-bing.RESEARCH ON QUALITATIVE ANALYSIS OF GASES BASED ON ARTIFICIAL NEURAL NETWORK[J].Journal of Qingdao University(Engineering & Technology Edition),2000,15(1):6-9. |
| |
| Authors: | GAO Feng CUI Jin-bao QU Jian-ling WANG Yi-bing |
| |
| Abstract: | 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. |
| |
| Keywords: | cross sensitivity feed forward neural networks gas sensor array qualitative analysis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
