基于BP神经网络和遗传算法优化茺蔚子水苏碱提取工艺的研究  

Optimization of Preparation Technology of Stachydrine in Fructus Leonuri Based on Back-propagation Neural Network and Genetic Algorithm

作　　者：周苏娟[1] 赵斌[2] 孟江[1] 蒋世忠[1] 贾天柱[3] 梁生旺[1] 

机构地区：[1]广东药学院,广东广州510006 [2]中山火炬职业技术学院,广东中山528436 [3]辽宁中医药大学,辽宁大连116600

出　　处：《广州中医药大学学报》2015年第4期735-738,744,共5页Journal of Guangzhou University of Traditional Chinese Medicine

基　　金：2015版中国药典项目;国家中医药管理局中医药行业科研专项(编号:201207004-7)

摘　　要：【目的】优化茺蔚子中水苏碱的提取工艺。【方法】采用正交设计,应用误差反向后传(BP)人工神经网络建立茺蔚子水苏碱提取时间、乙醇浓度、料液比与盐酸水苏碱含量之间的关系模型,再结合遗传算法优化提取工艺参数。【结果】提取工艺优化参数为:提取时间62 min、乙醇浓度体积分数69%、料液比11倍,网络模型优化结果稍优于正交试验结果。【结论】BP神经网络结合遗传算法寻优,能较好地实现茺蔚子水苏碱提取工艺参数的优化,可为解决多维非线性系统的工艺参数优化问题提供崭新而有效的途径。Objective To optimize the preparative procedure for stachydrine in Fructus Leonuri. Methods The preparation was screened by orthogonal experiment, and a mathematical model of relationship of extraction time,methanol concentration, and solid-liquid ratio with the content of stachydrine hydrochloride was established by using back-propagation（BP） neural network. And the process parameters were optimized with genetic algorithm（GA）. Results The optimum process parameters were as follows： extraction with 69% of methanol concentration and with solid-liquid ratio being 11 times for 62 min. The content of stachydrine obtained by BP neural network modeling and GA was higher than that achieved by orthogonal experiment. Conclusion The optimum preparative procedure could be achieved by combining BP modeling with GA. The model developed in this study was proved to be predictable and feasible for the optimization of process parameters of multi-dimension nonlinear system.

关 键 词：BP神经网络 遗传算法 茺蔚子/化学 水苏碱/分析 工艺优化 色谱法 高压液相 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术] R284.2[自动化与计算机技术—计算机科学与技术]