CONTROL OF MOISTURE-CONTENT IN FLUIDIZED-BED GRANULATION BY NEURAL-NETWORK

This paper describes a practical method for moisture control in fluidi zed bed granulation by means of a neural network. Wet granulation of p harmaceutical powder was conducted using an agitation fluidized bed, a nd moisture content was continuously measured by IR (infrared) moistur e sensor. A neural network system for moisture control was developed u sing moisture content and its changing rate as input variables, and th e moisture control characteristics were investigated by the neural net work system with a back propagation learning. Good response and stabil ity without overshoot were achieved by adopting the developed systems. This system also maintained favorable stability under various operati ng conditions.