利用神经网络提高偏最小二乘法的NIR多组分分析精度

摘要
参考文献
相关文章 (15)

全文: PDF (803 KB)
输出: BibTeX | EndNote (RIS)

摘要：提出了一种神经网络(ANN)和偏最小二乘法(PLS)结合的新的近红外(NIR)多组分分析法。该方法首先把训练样本中待测组分涵盖的浓度区间分成若干个子区间，利用各个子区间的训练样本分别建立PLS校正模型，然后利用ANN对未知样本进行分类，判断其所属的浓度子区间，应用对应子区间上的校正模型计算预测样本的组分浓度。和传统的PLS比较，此方法改善了模型的适应性，显著地提高了预测精度。实验及数据处理结果证明了本方法的有效性。

关键词：偏最小二乘法;神经网络;近红外光谱

Abstract：The present paper presents a new NIR multi-component analysis method with Artificial Neural Network(ANN) and Partial Least Square Regression(PLS). First, this method divides the concentration range of training samples into some sub-ranges, and respectively computes a PLS correlation model in each sub-range with the sub-range’s training samples. Then, the authors classify prediction samples according to its concentration sub-range with ANN and judge which sub-range the prediction sample belongs to. Finally, the authors compute the concentration of prediction component with the PLS correlation model of the sub-range according to ANN. The experiment and the result of data processing show that this method improves the model’s applicability, and evidently enhances prediction precision compared to traditional PLS.

Key words：Partial least square regression;Artificial neural network;Near infrared spectroscopy

收稿日期: 2004-04-28 修订日期: 2004-09-12

中图分类号:

O235

通讯作者: 白英奎

引用本文:

白英奎¹，孟宪江¹，丁东¹，申铉国² . 利用神经网络提高偏最小二乘法的NIR多组分分析精度[J]. 光谱学与光谱分析, 2005, 25(03): 381-383.
BAI Ying-kui¹，MENG Xian-jiang¹，DING Dong¹，SHEN Xuan-guo² . Improving Partial Least Square Regression Precision in NIR Multi-Component Analysis Using Artificial Neural Network . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2005, 25(03): 381-383.

链接本文:

https://www.gpxygpfx.com/CN/Y2005/V25/I03/381