基于GA-BP人工神经网络的红霉素肠溶片效价预测研究  

Study on titer prediction of Erythromycin Enteric Coated Tablets based on GA-BP artificial neural network

作　　者：武建卓[1] 彭洁[1] 王婷婷[1] 李雪[1] 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)

机构地区：[1]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

出　　处：《药学研究》2022年第5期312-315,共4页Journal of Pharmaceutical Research

基　　金：广东省医学科学技术研究基金项目(No.A2019055)。

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。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.

关 键 词：GA-BP人工神经网络 红霉素肠溶片 组分含量 效价预测 

分 类 号：R927.1[医药卫生—药学]