食品科学 ›› 2007, Vol. 28 ›› Issue (3): 70-72.

• 基础研究 • 上一篇    下一篇

遗传算法对红景天苷缓释微囊制作参数优化的研究

 赵武奇, 殷涌光, 仇农学   

  1. 陕西师范大学食品工程系; 吉林大学生物与农业工程学院; 陕西师范大学食品工程系 陕西西安710062; 吉林长春130022; 陕西西安710062;
  • 出版日期:2007-03-15 发布日期:2011-12-31

Optimization of Salidroside Slow Release Microcapsules Manufacturing Process Based on Genetic Algorithm

 ZHAO  Wu-Qi, YIN  Yong-Guang, CHOU  Nong-Xue   

  1. 1.Department of Food Engineering, Shaanxi Normal University, Xi’an 710062, China; 2.College of Biological and Agricultural Engineering, Jilin University, Changchun 130022, China
  • Online:2007-03-15 Published:2011-12-31

摘要: 本文在建立适应度函数、选择编码方案、确定遗传操作、选取控制参数的基础上,研究了缓释微囊神经网络模型的遗传算法优化。得到的最佳工艺参数为海藻酸钠与红景天苷质量比为2,海藻酸钠浓度为3%,壳聚糖浓度为0.5%,氯化钙浓度为1%,pH6.35,该工艺参数下载药量、包埋率和决定系数的加权和明显大于试验的结果,比最好的大14%;且最佳工艺参数下目标的预测值和试验值基本相符,可以满足实际需要。遗传算法用于缓释微囊神经网络模型的工艺参数寻优是可行的。

关键词: 遗传算法, 神经网络, 微胶囊, 优化

Abstract: The artificial neural network (ANN )model for Salidroside microcapsules was optimized by using genetic algorithm (GA) in the light of establishing fitness function, selecting coding method and determining genetic parameters. The highest performance, 14% greater than the biggest in experiments, is obtained when the ratio of alginate weight to Salidroside weight is 2, alginate concentration 3%, chitosan concentration 0.5%, calcium chloride concentration 1% and pH value 6.35. It is a practical method to optimize the ANN model by using GA.

Key words: genetic algorithm(GA), artificial neural network(ANN), microcapsules, optimization