| 小波包分析-减法聚类-RBF网络同时测定痕量铁、锰 |
| |
| 引用本文： | 张运陶,程正军.小波包分析-减法聚类-RBF网络同时测定痕量铁、锰[J].分析测试学报,2005,24(5):30-34. |
| |
| 作者姓名： | 张运陶 程正军 |
| |
| 作者单位： | 西华师范大学,应用化学研究所,四川,南充,637002;西华师范大学,应用化学研究所,四川,南充,637002 |
| |
| 摘 要： | 提出一种解析分光光度吲时测定数据的小波色分析-减法聚类-RBF刚络新方法。该方法用小波包分析处理吸收光潜数据，滤除信号中的噪声；采用基于山峰函数的减法聚类算法，按照自适应聚类的结果构成预测各未知样的校正集，实现校准模型的优化；由此，使RBFM络在对未知样预测时能更有效地提取光潜数据中的特征信息，提高预测结果的准确性把该算法用于模拟汽油中铁、锰合成样预测，计算表明，该方法可以显著降低测定结果的相对误差，预测结果令人满意。
|
| 关 键 词： | 小波包分析 减法聚类 RBF网络 分光光度法 |
| 文章编号： | 1004-4957（2005）05-0030-05 |
| 收稿时间： | 2004-09-25 |
| 修稿时间： | 2005-05-08 |
Application of Wavelet Packets Analysis-Subtractive Cluster-RBF to Simultaneous Determination of Trace Fe and Mn |
| |
| ZHANG Yun-tao,CHENG Zheng-jun.Application of Wavelet Packets Analysis-Subtractive Cluster-RBF to Simultaneous Determination of Trace Fe and Mn[J].Journal of Instrumental Analysis,2005,24(5):30-34. |
| |
| Authors: | ZHANG Yun-tao CHENG Zheng-jun |
| |
| Abstract: | A new method for resolving the spectrophotometric spectrum is proposed.The noise in the visible spectrumwas eliminated by wavelet packets analysis and the calibration model was optimized by peak-subtraction cluster.The veracity of the predicted results was improved.The proposed method has been applied to predict the contents of Fe and Mn in simulated gasoline simultaneously by using the wavelet packets analysis-subtractive cluster-RBF(radial basis function)networks(WPA-subclust-RBF).The results showed that the method could reduce the relative error of the results significantly.The predicted results were satisfactory. |
| |
| Keywords: | Wavelet packets analysis Subtractive cluster Radial basis function networks Spectrophotometry |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
