| OGSA结合RBF网络数据融合技术在红外气体分析中的应用 |
| |
| 引用本文： | 张永怀,刘君华,林继鹏. OGSA结合RBF网络数据融合技术在红外气体分析中的应用[J]. 仪器仪表学报, 2005, 26(1): 67-71 |
| |
| 作者姓名： | 张永怀 刘君华 林继鹏 |
| |
| 作者单位： | 西安交通大学电气学院,西安,710049 |
| |
| 基金项目： | 国家自然科学基金资助 (60 2 760 3 7) |
| |
| 摘 要： | 针对红外气体分析存在的问题 ,提出光学气体传感器阵列 (OGSA )和径向基函数 (RBF)神经网络技术相结合的方法 ,并将其应用于 SO2 、CO2 浓度检测。该方法利用 RBF网络非线性逼近功能和 OGSA的信息冗余特性 ,消除非目标参量和目标量之间的交叉干扰。结果表明 ,SO2 引用误差由融合处理前的 3.1%降至 2 .0 % ,CO2 由 39%降至 8.6 %。为红外气体分析提供了一种有效的途径 ,具有实用前景。
|
| 关 键 词： | RBF神经网络 光学气体传感器阵列 (OGSA) 交叉敏感 数据融合 |
| 修稿时间： | 2003-02-01 |
A Data Fusion Method Combining OGSA with RBF Neural Network Technology and Its Application in Infrared Multi-gas Analysis |
| |
| Zhang Yonghuai Liu Junhua Lin Jipeng. A Data Fusion Method Combining OGSA with RBF Neural Network Technology and Its Application in Infrared Multi-gas Analysis[J]. Chinese Journal of Scientific Instrument, 2005, 26(1): 67-71 |
| |
| Authors: | Zhang Yonghuai Liu Junhua Lin Jipeng |
| |
| Abstract: | To the problems that exist in infrared gas analysis,a method that OGSA (optical gas sensor array) combines with RBF (radial basis function) neural network technology is suggested and applied to measure the concentration of SO 2 and CO 2.This method can eliminate the cross-interference between non-aim parameter and aim parameter adopting nonlinear approach function of RBF neural network and information redundancy of OGSA.The result indicates that fiducial error of SO 2 decreases from 3 1% before data fusion to 2 0% and that of CO 2 decreases from 39% to 8 6%.The method provides an effective approach for infrared gas analysis and exhibits practical prospect. |
| |
| Keywords: | Radial base function Neural network Optical gas sensor array Cross sensitive Data fusion |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
