孟德尔多目标简单遗传算法在药物提取条件优化中的应用

The Application of Mendelian Multi-objective Simple Genetic Algorithms in the Optimization of Extraction Conditions of Medicine

目的研究孟德尔多目标简单遗传算法(MMOSGA)在均匀试验设计的药物提取条件优化中的应用。方法对微波辅助萃取刺五加试验数据建立以浸膏得率、异秦皮啶含量、总皂苷含量为子目标的回归模型;利用课题组成员英国Glasgow大学软件工程师陈益编写的Matlab2009a外挂SGALAB工具箱beta5008进行遗传算法寻优,分别采用单目标遗传算法和MMOSGA对其进行单目标优化和三目标优化,并比较优化结果。结果单目标遗传算法优化得到各子目标最大时的最优提取条件,MMOSGA进行三目标优化时,在主要目标上达到了单目标最大函数值的71%以上,确定的最优提取条件的效果高于均匀试验中的任何一个方案。结论 MMOSGA搜索的Pareto非劣解是合理的,达到了较好的效果,为均匀试验设计最优条件选择提供了合理的方法,可推广到正交试验设计、析因试验设计的最优条件选择。

Objective Study the application of optimization analysis of Mendelian Multi-objective Simple Genetic Algorithms in drug extraction. Methods Using microwave extraction Radix acanthopanacis senticosi data in uniform design establish three-objective function. Using SGALAB beta5008 of the Matlab 2009a plug-in tool-box, which was written by ChenYi in the United Kingdom University of Glasgow, achieves the genetic algorithm optimization. Applying simple genetic algorithm and MMOSGA explore the optimal extracting conditions. Compare their optimal extracting conditions. Results Single-objective genetic algorithm optimization can obtain the optimal extraction conditions of each objective. MMOSGA for three-objective optimi- zation, which can achieve 71% of the maximum value of single objective function in the main goals, thus we can get optimal ex- traction conditions, the effect of which is best. Conclusion MMOSGA provides reasonable pareto optimal solutions. It is a reasonable method for selecting optimal conditions for Uniform Experimental Design. This method can be extended to the selection of the optimal conditions in the orthogonal experimental design and factorial design.