| 基于广义回归神经网络的COD在线检测方法研究 |
| |
| 引用本文： | 张荣标,冯俊,谢志超. 基于广义回归神经网络的COD在线检测方法研究[J]. 仪器仪表学报, 2008, 29(11) |
| |
| 作者姓名： | 张荣标 冯俊 谢志超 |
| |
| 作者单位： | 汀苏大学电气信息工程学院,镇江,212013 |
| |
| 基金项目： | 国家“863”高技术研究发展计划(2006AA10Z258)资助项目 |
| |
| 摘 要： | 采用化学分析法检测污水中COD值的现有技术,检测过程复杂、测取速度慢,难以实现在线检测。根据紫外光谱对有机污染物的敏感特性,结合神经网络对非线性模型的良好辨识能力,研究出一种COD快速检测的方法。采用多波长在线扫描技术获取被测污水COD的光谱数据,通过特征提取简化样本数据,运用广义回归神经网络(GRNN)建立COD值预测模型。采用多种建模方法对具有不同COD值的水样光谱数据进行分析比较结果表明:GRNN比BP网络和多元线性回归方法建模具有更好的相关性、更强的泛化能力和更高的检测精度。
|
| 关 键 词： | 广义回归神经网络 特征提取 紫外光谱 COD |
Study on COD on-line detection method based on general regression neural network |
| |
| Zhang Rongbiao,Feng Jun,Xie Zhichao. Study on COD on-line detection method based on general regression neural network[J]. Chinese Journal of Scientific Instrument, 2008, 29(11) |
| |
| Authors: | Zhang Rongbiao Feng Jun Xie Zhichao |
| |
| Affiliation: | School of Electrical and Information Engineering;Jiangsu University;Zhenjiang 212013;China |
| |
| Abstract: | Standard chemical analysis method has been used for detecting chemical oxygen demand(COD)value of wastewater for a long time.It's difficult to realize on-line measurement because of the complex detection process and slow test speed.Based on the sensitive characteristic of ultraviolet spectrum to organic pollutants,combining with the excellent non-linear model identification ability of artificial neural network,a rapid COD detection method is put for- ward.Multi-wavelength on-line scanning technique is used ... |
| |
| Keywords: | GRNN feature extraction UV spectrum COD |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
