人工神经网络结合粒子群优化算法优化不同产地广藿香挥发油提取工艺  

Optimization of Extraction Technology for Volatile Oil of Pogostemon Cablin from Different Habitats Based on ANN-PSO Method

作　　者：张浩科[1] 高静 赵智龙 宫海燕[3] 唐莎莎 ZHANG Haoke;GAO Jing;ZHAO Zhilong;GONG Haiyan;TANG Shasha(The First Hospital of Xinjiang Medical University,Urumqi 830011,China;People’s Hospital of Tacheng City,Tacheng 834700,China;The Fifth Hospital of Xinjiang Medical University,Urumqi 830011,China;Training College of Traditional Chinese Medicine of Dazhou,Dazhou 635000,China)

机构地区：[1]新疆医科大学第一附属医院,新疆乌鲁木齐830011 [2]新疆塔城市人民医院,新疆塔城834700 [3]新疆医科大学第五附属医院,新疆乌鲁木齐830011 [4]达州中医药职业学院,四川达州635000

出　　处：《中国中医药信息杂志》2021年第5期83-87,共5页Chinese Journal of Information on Traditional Chinese Medicine

基　　金：新疆维吾尔自治区自然科学基金(2016D01C227)。

摘　　要：目的优化不同产地广藿香挥发油的提取工艺。方法以挥发油提取率为评价指标,构建反向传播人工神经网络模型,应用粒子群优化算法优化云南曲靖、广东化州产地的广藿香挥发油提取工艺。结果人工神经网络结合粒子群优化算法(ANN-PSO)优化的云南曲靖广藿香挥发油提取工艺为料液比1∶9、提取3.5 h、提取3次,提取率为1.98%,与预测值2.06%接近,高于正交试验结果(1.60%);广东化州广藿香挥发油提取工艺为料液比1∶3、提取时间4.5h、提取3次,提取率为2.46%,与预测值2.53%接近,高于正交试验结果(1.82%)。结论ANN-PSO可用于优化广藿香挥发油提取工艺。Objective To optimize extraction technology of volatile oil of Pogostemon cablin from different habitats.Methods Taking the extraction rate of volatile oil as the evaluation index,back propagation-artificial neural network(BP-ANN)model was established.Particle swarm optimization(PSO)was applied to optimize extraction technology of volatile oil of Pogostemon cablin from Qujing in Yunnan and Huazhou in Guangdong.Results The extraction process parameters of volatile oil of Pogostemon cablin(Qujing,Yunnan)optimized by ANN-PSO were as follows:the ratio of material to liquid was 1:9,extracted for 3.5 hours and 3 times;the optimum extraction rate was 1.98%,which was closed to predicted value of 2.06%and higher than the orthogonal test result(1.60%).Based on ANN-PSO,optimized extraction process parameters of volatile oil of Pogostemon cablin(Huazhou,Guangdong)were as follows:the ratio of material to liquid was 1:3,extracted for 4.5 hours and 3 times;the optimum extraction rate was 2.46%,which was closed to predicted value of 2.53%and higher than the orthogonal test result(1.82%).Conclusion ANN-PSO is an effective tool to optimize the yield of volatile oil of Pogostemon cablin.

关 键 词：广藿香 人工神经网络 粒子群优化算法 提取工艺 

分 类 号：R284.2[医药卫生—中药学]