遗传算法-反向神经网络结合正交设计法优化芪芍桂酒汤的提取工艺

Optimization of extraction process for Qishao Guijiu decoction based orthogonal test and GA-BP neural network

目的通过正交试验和遗传算法(GA)优化的反向传播(BP)神经网络优化芪芍桂酒汤的提取工艺。方法采用HPLC法同时测定毛蕊异黄酮苷、芍药苷、桂皮醛的含量;以转移率和浸膏得率为评价指标,以溶剂倍量、煎煮时间、酒水比为正交试验的考察因素,建立GA-BP神经网络模型,预测最佳提取工艺。结果正交设计优选的提取工艺综合评分为87.11;GA-BP神经网络预测的最优工艺参数更佳,综合得分为90.62。结论GA-BP神经网络优化后的提取工艺所需溶剂较低,综合得分更高,说明所得工艺更理想。

OBJECTIVE To optimize the extraction technology of Qishao Guijiu decoction(QGD)using Orthogonal experiment combined with a genetic algorithm(GA)-back propagation(BP)neural network.METHODS The content of calycosin-7-glucoside,paeoniflorin,and cinnamaldehyde was simultaneously determined by HPLC.The effects of solvent volume,extraction time,and the ratio of bitters to water on the optimization of the QGD extraction process were investigated using multiple indicators comprehensive scoring and orthogonal design methodology.A GA-BP neural network model was established to optimize and predict the optimal extraction process.RESULTS The optimal parameters predicted by GA-BP neural network achieved a comprehensive score of 90.62.The optimal extraction process determined by Orthogonal design achieved a comprehensive score of 87.11.CONCLUSION The extraction process optimized by GA-BP neural network requires lower solvent and a higher comprehensive score,which shows that the extraction process is more ideal.