| 红外和神经网络无损分析VC 银翘片中二组分含量 |
| |
| 引用本文： | 白英奎,申铉国,丁 东.红外和神经网络无损分析VC 银翘片中二组分含量[J].激光与红外,2004,34(5):354-356. |
| |
| 作者姓名： | 白英奎 申铉国 丁 东 |
| |
| 作者单位： | 1. 吉林大学通信工程学院
2. 吉林大学物理学院,吉林,长春,130025 |
| |
| 基金项目： | 教育部高等学校骨干教师资助计划资助(2000931)。 |
| |
| 摘 要： | 应用近红外光谱和BP 神经网络对VC 银翘片进行非破坏定量分析,讨论了神经网络
输入点数的选择和影响神经网络各参数的确定。采用了贝叶斯规范化的网络训练方法,解决了BP 神经网络稳定性较差的问题,提高了网络的预测精度。实验及数据处理结果表明,应用本文方法对VC 银翘片进行非破坏定量分析方法是可行和有效的。
|
| 关 键 词： | VC 银翘片 无损分析 近红外光谱 BP 神经网络 |
| 文章编号： | 1001-5078(2004)05-0354-03 |
Two-component Nondestructive Analysis of VC Yinqiao Tablets with NIR And Bp Neural Network |
| |
| BAI Ying-kui,SHEN Xuan-guo,DING Dong.Two-component Nondestructive Analysis of VC Yinqiao Tablets with NIR And Bp Neural Network[J].Laser & Infrared,2004,34(5):354-356. |
| |
| Authors: | BAI Ying-kui SHEN Xuan-guo DING Dong |
| |
| Affiliation: | BAI Ying-kui~1,SHEN Xuan-guo~2,DING Dong~1 |
| |
| Abstract: | The application of NIR and artificial neural network for Vc Yinqiao tablet nondestructive quantitative analysis were investigated.The choice of ANN inputting node number and ANN's parameters affecting network were discussed,used Bayesian Regularization mode to train Bp Neural Network.With this mode,the question of Bp Neural Network's weak stalility were resolved,improved the forecasting precision of Neural Network.The experiment and the result of data process shows the application of Bp Neural Network In the nondestructive quantitative Analysis of Vc Yinqiao Tablets is effective and viable. |
| |
| Keywords: | VC yinqiao tablet nondestructive analysis NIR BP neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《激光与红外》浏览原始摘要信息 |
|
点击此处可从《激光与红外》下载全文 |
