人工神经网络-近红外光谱法非破坏监测芦丁药品的质量  

NONDESTRUCTIVE QUALITY CONTROL OF RUTIN PHARMACEUTICALS BY NEAR INFRARED REFLECTANCE SPECTROSCOPY AND ARTIFICIAL NEURAL NETWORK

作　　者：刘福强[1] 赵文萃[1] 刘革[1] 汤真[1] 窦英[2] 任玉林[2] 

机构地区：[1]中国人民解放军208医院,长春130061 [2]吉林大学化学学院,长春130023

出　　处：《化学分析计量》2003年第3期11-13,共3页Chemical Analysis And Meterage

摘　　要：用近红外漫反射光谱法非破坏监测芦丁药品的质量。利用人工神经网络化学计量学分类技术,建立三层神经元的神经网络,时网络参数进行优化选择以建立最佳网络模型。根据芦丁药品的近红外漫反射光谱,成功地分辨出合格药品和不合格药品。The possibility of using near infrared reflectance spectroscopy for the quality control of rulin pharmaceuticals was investigated. The artificial neural network chemometrics technique was used to set up a neural network with three layers of neural elements , the parameters were optimized to produce the best network model, and the qualified pharmaceuticals of rutin were successfully identified from the poor based on the near infrared reflectance spectras.

关 键 词：人工神经网络 近红外光谱法 非破坏监测 芦丁药品 质量监测 

分 类 号：TQ460.72[医药卫生—药物分析学] R927[化学工程—制药化工]