Abstract
Dry granulation via a roller compactor was simulated based on the artificial neural network (ANN) methodology. Two process parameters, including roll force and screw speed, were considered as input of the simulation whereas ribbon density was considered as output. Experimental work was carried out using an industrial-scale roller compactor. The results showed an excellent agreement between simulation and experiments. The findings were compared as well with the results obtained in a previous study employing the Johanson model, which is the predominant model for the simulation of a roller compaction process. The overall deviation observed for the developed ANN model was found to be significantly improved in comparison with the deviation obtained for the Johanson model. The results demonstrated a very good capability and robustness of the developed ANN model in design and optimization of the roller compaction process.
Original language | English |
---|---|
Pages (from-to) | 487-492 |
Number of pages | 6 |
Journal | Chemical Engineering and Technology |
Volume | 40 |
Issue number | 3 |
DOIs | |
Publication status | Published - 1 Feb 2017 |
Keywords
- Artificial neural network
- Granulation
- Ribbon density
- Roller compaction
- Simulation