Studies of the relationship between petrography and grindability for Kentucky coals using artificial neural network

A. H. Bagherieh, James C. Hower, A. R. Bagherieh, E. Jorjani

Research output: Contribution to journalArticlepeer-review

43 Scopus citations

Abstract

Although there are several formulas available for predicting Hardgrove grindability of coal, most of them are linear and do not simultaneously take into consideration most of the relevant factors. The artificial neural network is an information processing tool that is capable of establishing an input-output relationship by extracting controlling features from a database presented to the network. In this paper, a neural network approach was proposed to deal with the grindability behavior of coal. 195 sets of experimental data were evaluated with artificial neural network to predict the HGI of Kentucky coals. Two different kinds of the trained artificial neural network were undertaken using the database created in this study. It is shown from the examples that the artificial neural network adequately recognized the characteristics of the coal experimental data sets, retaining a generality for further prediction. It is believed that an artificial neural network based prediction procedure shown in this paper can be further employed for Hardgrove grindability index prediction. The influence of liptinite, vitrinite, ash, and sulfur content on HGI was studied by a parametric study.

Original languageEnglish
Pages (from-to)130-138
Number of pages9
JournalInternational Journal of Coal Geology
Volume73
Issue number2
DOIs
StatePublished - Jan 21 2008

Keywords

  • Artificial neural network (ANN)
  • Coal
  • Coal petrography
  • Hardgrove grindability index (HGI)

ASJC Scopus subject areas

  • Fuel Technology
  • Geology
  • Economic Geology
  • Stratigraphy

Fingerprint

Dive into the research topics of 'Studies of the relationship between petrography and grindability for Kentucky coals using artificial neural network'. Together they form a unique fingerprint.

Cite this