Artificial neural network techniques to predict the moisture ratio content during hot air drying and vacuum drying of Radix isatidis extract

Background:To predict the moisture ratio of Radix isatidis extract during drying.Methods:Artificial neural networks were designed using the MATLAB neural network toolbox to produce a moisture ratio prediction model of Radix isatidis extract during hot air drying and vacuum drying,where regression values and mean squared error were used as evaluation indexes to optimize the number of hidden layer nodes and determine the topological structure of artificial neural networks model.In addition,the drying curves for the different drying parameters were analyzed.Results:The optimal topological structure of the moisture ratio prediction model for hot air drying and vacuum drying of Radix isatidis extract were“4-9-1”and“5-9-1”respectively,and the regression values between the predicted value and the experimental value is close to 1.This indicates that it has a high prediction accuracy.The moisture ratio gradually decreases with an increase in the drying time,reducing the loading,initial moisture content,increasing the temperature,and pressure can shorten the drying time and improve the drying efficiency.Conclusion:Artificial neural networks technology has the advantages of rapid and accurate prediction,and can provide a theoretical basis and technical support for online prediction during the drying process of the extract.

A valid evaluation method for UPLC fingerprint analysis and moisture ratio prediction model:application to microwave vacuum drying of Radix isatidis extract

Background:Drying is a necessary component of traditional Chinese medicine extracts.The heating principle of microwave vacuum drying is different from that of the conventional heat method.However,at present,there is paucity of information on the drying process of traditional Chinese medicine extract by microwave vacuum drying,and the results of such process are unclear.Methods:To study the dynamic changes in the chemical characteristics of microwave vacuum drying under different drying conditions,ultrahigh-performance liquid chromatography fingerprint profiles were established using Radix isatidis extract as a model drug and analyzed using similarity analysis,partial least squares-discriminant analysis,and semi-quantitative analysis.In addition,a backpropagation artificial neural network model was developed to predict the moisture ratio of the drying process.Results:Qualitative results showed that the similarity between different drying conditions was greater than 0.95,and 2 amino acid components(peaks 5 and 6)affected by process fluctuations were screened out.The quantitative results showed that the mass concentration of component 1 fluctuated after drying,while that of component 2 increased.The optimal backpropagation artificial neural network model structure used to predict the moisture ratio was 5-4-1,with regression and mean squared error values of 0.996 and 0.0003,respectively,after training,which were well fitted and had a strong approximation ability.Conclusion:Upon comparison of fingerprints and the evaluation of statistical methods,common components of Radix isatidis extract had little variation under different drying conditions,and the selected components provided a reference for the establishment of process evaluation indexes.The establishment of backpropagation artificial neural network provides a theoretical basis for the application of microwave vacuum drying technology and online monitoring of moisture ratio.