Modeling Vertical Roller Mill Raw Meal Residue by Implementing Neural Network

摘要

This study proposes a method for modeling the Vertical Roller Mill (VRM) to predict residue 90 micron and residue 200 micron of the raw meal product using Back Propagation Neural Network (BPNN). The modelling step is input preparation, Artificial Neural Network (ANN) structure determination, optimizer and loss function selection, training ANN and model evaluation. In this research, RMSprop optimizer and MSE loss function are used, and show better modelling results than others to predict residue data quality of the VRM raw meal products.