Artificial Intelligence Tools for Scaling Up of High Shear Wet Granulation Process

详细信息    查看全文

• 作者：Mariana Landin ; ^{m.landin@usc.es}
• 关键词：granulation ; simulations ; solid dosage form ; tableting ; wetting
• 刊名：Journal of Pharmaceutical Sciences
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：106
• 期：1
• 页码：273-277
• 全文大小：494 K
• 卷排序：106

文摘

The results presented in this article demonstrate the potential of artificial intelligence tools for predicting the endpoint of the granulation process in high-speed mixer granulators of different scales from 25L to 600L. The combination of neurofuzzy logic and gene expression programing technologies allowed the modeling of the impeller power as a function of operation conditions and wet granule properties, establishing the critical variables that affect the response and obtaining a unique experimental polynomial equation (transparent model) of high predictability (R2 > 86.78%) for all size equipment. Gene expression programing allowed the modeling of the granulation process for granulators of similar and dissimilar geometries and can be improved by implementing additional characteristics of the process, as composition variables or operation parameters (e.g., batch size, chopper speed). The principles and the methodology proposed here can be applied to understand and control manufacturing process, using any other granulation equipment, including continuous granulation processes.