Predictive models of tensile strength and disintegration time for simulated Chinese herbal medicine extracts compound tablets based on artificial neural networks

Abstract The tensile strength (TS) and disintegration time (DT) are often used as important indexes to evaluate the quality of tablets. The TS and DT of Chinese herbal medicine compound tablets are affected by the properties of the herbal medicine extract powder. In this study, three predictive models of powder properties-tablet quality were established for simulated herbal medicine compound tablets. The models can be used to predict the TS and DT of tablets according to the powder properties. The models were based on combinations of principal component analysis (PCA) and radial basis function artificial neural network (RBF-ANN), back propagation artificial neural network (BP-ANN) and multiple regression analysis (MRA). The TS and DT prediction accuracy of the three models were ranked as follows: PCA-RBF-ANN > PCA-MRA > PCA-BP-ANN. The PCA-RBF-ANN model had the best predictive performance: the relative error for TS ranged from 1.51% to 6.31%, with a mean relative error of 3.91%; the relative error for DT ranged from 1.18% to 2.84%, with a mean relative error of 2.01%. The results demonstrated that the PCA-RBF-ANN model can be used to predict the quality of tablets and provide a reference for quality control of herbal medicine compound tablets.