Optimization of extraction process for Qishao Guijiu decoction based orthogonal test and GA-BP neural network
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.
万方数据
维普
