基于BP神经网络的缓释制剂处方质量预测研究  

Study on Formulation Quality Forecast of Sustained Release Preparation Based on BP Neural Network

作　　者：金玉琴[1] 周金海[1] 赵群[2] 张兴德[2] 

机构地区：[1]南京中医药大学信息技术学院,南京210023 [2]南京中医药大学药学院,南京210023

出　　处：《世界科学技术-中医药现代化》2013年第7期1569-1575,共7页Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology

基　　金：江苏省科技厅科技支撑计划-工业部分(BE2011012):中药饮片信息化管理体系的物联控制与商业智能的研究;负责人:蔡宝昌;国家自然科学基金委青年基金项目(81001640):黄连酒炙后化学成分组合变化与药性改变相关性研究;负责人:张兴德

摘　　要：缓释制剂的处方优化属于多因素、多水平的复杂优化问题,人工神经网络很适于处理这类复杂的多变量非线性关系。本文在对缓释制剂特性及影响其处方设计质量的重要因素进行细致分析的基础上,应用BP人工神经网络建立缓释制剂处方质量预测模型。研究结果表明,BP神经网络可以有效地进行缓释制剂处方质量预测,是缓释制剂处方优化的有力工具。Optimization on sustained release preparation formulation is a multi-factor, multi-level complex optimiza-tion problem. Artificial neural network is very suitable for dealing with such complex multivariable nonlinear system. Based on analyzing the characteristics of sustained release preparation and the main influential factors of its quality, this paper focused on building a quality forecast model for sustained release preparation formulation by using BP neural network. The results showed that the BP neural network can effectively forecast the quality of sustained re-lease preparation formulation. It is a powerful optimization tool of sustained release preparation formulation.

关 键 词：BP神经网络 缓释制剂 处方质量预测 

分 类 号：R944[医药卫生—药剂学]