Research on Prediction Model of Basic Sintering Characteristics of Mixed Iron Ore and Sinter Quality

DOI

10.2991/mcei-15.2015.50How to use a DOI?

Keywords

Basic sintering characteristics; Sinter quality; Support vector machines; BP neural network; GRNN

Abstract

In order to solve the rapid decision of ore blending scheme in iron ore sintering process, the prediction model of the basic sintering characteristics of mixed iron ore and sinter quality has been established by three algorithms including the support vector machines, BP neural network and general regression neural network. The results show, the model based on support vector machine algorithm is better, which can accurately predict the basic sintering characteristics and sinter quality indexes; the accuracy of prediction for assimilation temperature, liquid fluidity and the binding phase strength are 90 , 93 and 91 respectively, based on the physical and chemical properties of raw material, and the accuracy of prediction for the drum strength and productivity are 89 and 88 , based on the basic sintering characteristics of mixed iron ore and technical parameters.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Song Liu
AU  - Fumin Li
AU  - Jianguang Lu
AU  - Qing Lu
PY  - 2015/06
DA  - 2015/06
TI  - Research on Prediction Model of Basic Sintering Characteristics of Mixed Iron Ore and Sinter Quality
BT  - Proceedings of the International Conference on Management, Computer and Education Informatization
PB  - Atlantis Press
SP  - 187
EP  - 190
SN  - 2352-538X
UR  - https://doi.org/10.2991/mcei-15.2015.50
DO  - 10.2991/mcei-15.2015.50
ID  - Liu2015/06
ER  -