最小二乘支持向量机优化芹菜总黄酮提取工艺  

Optimization of Extraction Technology of Total Flavonoids from Celery Based on Least Square Support Vector Machine

作　　者：曾燕[1] 成新文[1] 陈欲云[2] 王晓[1] 

机构地区：[1]四川理工学院计算机学院,四川自贡643000 [2]四川理工学院化学与制药工程学院,四川自贡643000

出　　处：《食品研究与开发》2015年第8期49-52,57,共5页Food Research and Development

基　　金：酿酒生物技术及应用四川省重点实验室开放基金项目(NJ2011-09);企业信息化与物联网测控技术四川省高校重点实验室开放基金项目(编号:2014WYJ08);四川理工学院科研项目资助(2013KY04)

摘　　要：为获得芹菜总黄酮的最佳提取工艺参数,在其单因素和正交试验的基础上,利用混合蛙跳算法(SFLA)优化参数的最小二乘支持向量机(LSSVM)建立预测模型,通过该模型对芹菜总黄酮正交试验数据进行仿真,优化提取工艺条件。结果表明,最小二乘支持向量机预测模型优化后的芹菜总黄酮提取工艺条件为:料液比1∶36 g/m L,乙醇浓度82%,超声波提取时间40 min,在该条件得到芹菜总黄酮提取含量为8.32 mg/g,高于正交试验工艺条件下所提取的总黄酮含量。In order to obtain the optimum extraction process parameters of total flavonoids in celery , the shuffled frog leaping algorithm （SFLA） which based on single factor and orthogonal test was applied to optimize the parameters of the least squares support vector machine （LSSVM）,then prediction model of least squares support vector machine was established. By using the model to simulate the data of orthogonal experiment , the extraction technology of total flavonoids from celery was optimized. The experiment result showed that the optimized extraction conditions of total flavonoids from celery were the material/liquid ratio as 1 ∶36, ethanol concentration of 82%, and ultrasonic extraction duration of 40 min , the extraction yield of total flavonoids as 8.32 mg/g. In conclusion, the content of total flavonoids extracted is higher than that of orthogonal test.

关 键 词：最小二乘支持向量机 总黄酮 正交试验 混合蛙跳算法 

分 类 号：TS255.3[轻工技术与工程—农产品加工及贮藏工程]