Modeling vertical roller mill raw meal residue by implementing neural network

Hendri Fernandes, Abdul Halim, Wahidin Wahab

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publication2nd IEEE International Conference on Innovative Research and Development, ICIRD 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728128252
DOIs
Publication statusPublished - Jun 2019
Event2nd IEEE International Conference on Innovative Research and Development, ICIRD 2019 - Depok, Indonesia
Duration: 28 Jun 201930 Jun 2019

Publication series

Name2nd IEEE International Conference on Innovative Research and Development, ICIRD 2019

Conference

Conference2nd IEEE International Conference on Innovative Research and Development, ICIRD 2019
Country/TerritoryIndonesia
CityDepok
Period28/06/1930/06/19

Keywords

  • BPNN
  • Loss Function
  • Model
  • Optimizer
  • Residue
  • VRM

Fingerprint

Dive into the research topics of 'Modeling vertical roller mill raw meal residue by implementing neural network'. Together they form a unique fingerprint.

Cite this