【摘要】 采用高效液相色谱获得黄连上清片的色谱指纹图谱,利用基于主成分分析的投影判别法分析实验结果,并用反传人工神经网络对未知样品进行预报。结果表明,不同厂家生产的黄连上清片存在显著差异,主成分分析投影判别法能对样品进行正确分类,从而建立了识别不同厂家黄连上清片的方法,能有效地控制中药黄连上清片的质量。此外,主成分分析还用于优化反传人工神经网络,统计多次预报的结果,表明经过优化的反传人工神经网络能对未知样品的来源进行准确预报。更多还原

【Abstract】 High performance liquid chromatography (HPLC) was adopted to develop the fingerprint of Huanglianshangqing Tablets (HLSQT). In this study the technique of projection discriminant analysis based on principal component analysis (PCA) was applied to investigate the experimental data, and back-propagation network (BPN) was applied to predict the attribution of unknown samples. The results based on PCA showed that there were obvious differences among the HLSQT produced by different manufacturers, which established a method to distinguish HLSQT produced by different manufacturers, and the method developed can be effectively used to control the quality of traditional Chinese medicine HLSQT. And then, PCA was secondly adopted to optimize back-propagation network. The multiple predicted results manifested that PCA-BPN technology can be correctly used to predict the attribution of unknown samples.更多还原