首页 | 本学科首页   官方微博 | 高级检索  
检索        

人工神经元网络用于复方氯丙嗪的含量测定
引用本文:徐芬,孙立贤,刘焕文,梁建国,谭洁,梁逸曾,俞汝勤.人工神经元网络用于复方氯丙嗪的含量测定[J].药学学报,1994,29(10):767-772.
作者姓名:徐芬  孙立贤  刘焕文  梁建国  谭洁  梁逸曾  俞汝勤
作者单位:湖南师范大学化学系,湖南省药品检验所,湖南大学化学化工系
摘    要:将误差反向传播(BP)的人工神经元网络(ANN)模型,用于复方氯丙嗪紫外重叠光谱分 析。对ANN模型的参数进行了优化。采用f(x)二1/(1+e-x)作为网络节点的输入输出转换函数的三 层神经网络具有较佳性能,当取隐含节点数为15时,该网络预测结果的最小平均相对误差为1.22%, 将研制的ANN模型用于复方氯丙嗪含量测定,其结果与药品标准法和偏最小二乘法(PLs)一致。

关 键 词:人工神经元网络  多组分分析  盐酸氯丙嗪  盐酸异丙嗪
收稿时间:1993-09-08

ARTIFICIAL NEURAL NETWORK AS APPLIED TO THE ANALYSIS OF CHLORPROMAZINE TABLETS
F Xu,LX Sun,FW Liu,JG Liang,J Tan,YZ Liang and RQ Yu.ARTIFICIAL NEURAL NETWORK AS APPLIED TO THE ANALYSIS OF CHLORPROMAZINE TABLETS[J].Acta Pharmaceutica Sinica,1994,29(10):767-772.
Authors:F Xu  LX Sun  FW Liu  JG Liang  J Tan  YZ Liang and RQ Yu
Abstract:Three-layer artificial neural network(ANN )models with back propagation of error have been used to the analysis of chlorpromazine tablets. The networks architecture and parameters were optimized.The network gave an average relative error of 1.22%by using f(x)= 1/(1 e-x) as the input- output transformation function and setting the number of hidden nodes to 15.The network was used to determine the content of chlorpromazine in pharmaceutical preparations.The results were in fair agreement with those obtained by drug standard method and the PLS methods.
Keywords:Artificial    neural networks  Multicomponent analysis  Chlorpromazine      hydrochloride  Promethazine hydrochloride Human Provincial Institute    for Drug Control  Changsha 410001 Department of Chemistry and    Chemical Engineering  Human University  Changs
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《药学学报》浏览原始摘要信息
点击此处可从《药学学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号