Minimisation of the capping tendency by tableting process optimisation with the application of artificial neural networks and fuzzy models

The pharmaceutical industry is increasingly aware of the advantages of implementing a quality-by-design (QbD) principle, including process analytical technology, in drug development and manufacturing. Although the implementation of QbD into product development and manufacturing inevitably requires larger resources, both human and financial, large-scale production can be established in a more cost-effective manner and with improved efficiency and product quality. The objective of the present work was to study the influence of particle size (and indirectly, the influence of dry granulation process) and the settings of the tableting parameters on the tablet capping tendency. Artificial neural network and fuzzy models were used for modelling the effect of the particle size and the tableting machine settings on the capping coefficient. The suitability of routinely measured quantities for the prediction of tablet quality was tested. Results showed that model-based expert systems based on the contemporary routinely measured quantities can significantly improve the trial-and-error procedures; however, they cannot completely replace them. The modelling results also suggest that in cases where it is not possible to obtain sufficient number of measurements to uniquely identify the model, it is beneficial to use several modelling techniques to identify the quality of model prediction.