Optimization Of Process Parameters Of Single Drug And Compound Drugs By Dual-frequency Ultrasound

The extracts of active ingredients of traditional Chinese medicine are widely used in the field of medicine,health care products and cosmetics.Therefore,the extraction of traditional Chinese medicine has a wide range of practical scope and application prospects.In the extraction process of traditional Chinese medicine,the selection of process parameters has a significant impact on the extraction rate of active ingredients.Therefore,studying how to select process parameters to make the extraction be more efficient is important.In this paper,the extraction process parameters of active ingredients from single drug licorice and compound drugs Shaoyaogancao decoction by dual-frequency ultrasound were studied.The ultrasonic extraction process of traditional Chinese medicine always includes numerous complex physical reactions,which brings difficulties in modeling.Data-driven modeling methods mainly focus on processing data rather than the complicated process mechanism.It is necessary to build an accurate and robust data-driven model of the optimal process parameters,which can help analyze the process of extracting the active ingredients of traditional Chinese medicine.In the process of the ultrasonic extraction of traditional Chinese medicine,the extraction rate of the active ingredients require to be measured manually by the off-line way.Therefore,the available sample dataset is limited,resulting in the low accuracy and poor generalization performance of the established model.To solve this problem,this paper proposes a virtual sample generation method based on Response Surface Method(RSM)and Extreme Learning Machine(ELM).The reasonable and effective virtual samples are obtained to improve the accuracy of the prediction model.The experimental results show that the prediction model established with virtual samples has significantly reduced the prediction error,and each evaluation index is better than the prediction models established by other methods.The learning ability and generalization ability of the model are improved.The optimal process parameters are determined by the established prediction model and the cuckoo search(CS)algorithm.In order to make the results be more consistent with the Chinese medicine mechanism,while ensuring the extraction effect of effective components,the ratio of effective components is taken as the constraint condition of the optimization process.The optimal ultrasonic extraction process parameters of single drug and compound drugs are obtained respectively,and the experimental results show that the optimal process parameters are accurate and reliable,which could provide a certain theoretical basis and reference for the industrialization of the plant medicine extraction.