• Home
  • About Journal
    Journal Introduction
    Editorial Board
    Youth Editorial Board
    Cooperating Institutions
    Editorial Department
  • Submission Guidelines
  • Policies & Statements
    Ethical Guidelines for Publication
    Academic Misconduct Statement
    Open Access (OA) Statement
    AIGC Use Statement
  • Journal Subscription
  • Download Center
  • 中文版
Cite this article:
WU Jianzhuo,PENG Jie,WANG Tingting,LI Xue.Study on titer prediction of erythromycin enteric coated tablets based on GA-BP artificial neural network[J].Journal Of Pharmaceutical Research,2022,41(5):312-315[Click to copy]
【Print this page】      【Download PDF Full Text】   【View/Add Comment】  【Download reader】  【 Close 】
←Previous|Next→ Archive    Advanced Search
This article has been viewed: 2383times   Download 2639次 QR Code for this article
Scan with your phone!
基于GA-BP人工神经网络的红霉素肠溶片效价预测研究
武建卓,彭洁,王婷婷,李雪
Font:Larger+|Default|Smaller-
(广东省药品检验所,国家药品监督管理局药品快速检验技术重点实验室,广东 广州 510663)
摘要:
目的 建立一种基于GA-BP人工神经网络模型,根据组分含量数据对红霉素肠溶片效价进行预测。方法 测定552个批次红霉素肠溶片的红霉素组分A、红霉素组分B、红霉素组分C、杂质A-F和总杂质的百分含量及效价,构建GA-BP 人工神经网络模型,预测红霉素肠溶片的效价。结果 预测效价误差百分率最高值为-4.61%,均未超过5%,误差百分率平均值为2.22%,优于一般仪器分析相对标准偏差2.50%。结论 GA-BP人工神经网络对红霉素肠溶片效价预测具有较高的精度,稳定性也较好,可以用于红霉素的质量控制。
关键词:  GA-BP人工神经网路  红霉素肠溶片  组分含量  效价预测
DOI:10.13506/j.cnki.jpr.2022.05.007
基金项目:广东省医学科学技术研究基金项目(No.A2019055)
Publication Date:May 25, 2022
Study on titer prediction of erythromycin enteric coated tablets based on GA-BP artificial neural network
WU Jianzhuo,PENG Jie,WANG Tingting,LI Xue
(Guangdong Institute for Drug Control,NMPA Key Laboratory for Rapid Testing Technology of Drugs,Guangzhou 510663,China)
Abstract:
Objective To establish a GA-BP artificial neural network model to predict the titer of erythromycin enteric coated tablets according to the component content data.Methods The contents and potency of erythromycin component A, erythromycin component B, erythromycin component C, impurity A-F and total impurities in 552 batches of erythromycin enteric coated tablets were determined, and the GA-BP artificial neural network model was constructed to predict the potency of erythromycin enteric coated tablets.Results The highest error percentage of predicted titer was - 4.61%, which was not more than 5%. The average error percentage was 2.22%, which was better than the relative standard deviation of general instrumental analysis by 2.50%. Conclusion GA-BP artificial neural network has high accuracy and stability in predicting the titer of erythromycin enteric coated tablets, and can be used for the quality control of erythromycin.
Key words:  GA-BP artificial neural network  Erythromycin enteric coated tablets  Component content  Potency prediction
Today's Visits:511    Total Visits:2383242
Website copyright:Editorial Board of Journal of Pharmaceutical Research     鲁ICP备17018036号-3     鲁公网安备 37010202001351号
Sponsored by:Shandong Institute for Food and Drug Control Shandong Pharmaceutical Association Address:No.2749 Xinluo Street,High-Tech Zone,Jinan,P.R.China Postcode:250101
Telephone Number:0531-81216586 Email :yaoxueyanjiu@163.com;yaoxueyanjiu@126.com
Technical Support:Beijing Qinyun Technology Co., Ltd.