Soft modelling of the Hardgrove grindability index of bituminous coals: An overview

James C. Hower; Amir H. Bagherieh; Saeid R. Dindarloo; Alan S. Trimble; Saeed Chehreh Chelgani

doi:10.1016/j.coal.2021.103846

Soft modelling of the Hardgrove grindability index of bituminous coals: An overview

James C. Hower, Amir H. Bagherieh, Saeid R. Dindarloo, Alan S. Trimble, Saeed Chehreh Chelgani

Earth and Environmental Sciences

Research output: Contribution to journal › Review article › peer-review

2 Scopus citations

Abstract

Predictions of the Hardgrove grindability index, a predictor of the crushing and pulverization propensity of coal, have been made using both regression and neural network techniques. All techniques suffer from shortcomings. In general, input parameters must be selected based on a sound knowledge of coal chemistry and petrology, with avoidance of redundant parameters, avoidance of closure in the data sets that add to 100% (individually the proximate and ultimate analyses, petrology, and (approximately) major oxides), and a constrained coal rank and provenance setting. Predictions based on a specific set of coals are not necessarily translatable to different ranks or maceral suites. In general, for high volatile bituminous coals, combinations of coal rank (vitrinite reflectance or volatile matter), liptinite content, and ash percentage produce the best predictions.

Original language	English
Article number	103846
Journal	International Journal of Coal Geology
Volume	247
DOIs	https://doi.org/10.1016/j.coal.2021.103846
State	Published - Nov 1 2021

Bibliographical note

Funding Information:
We thank all of our colleagues who have guided us in these studies. In particular, Hower acknowledges the guidance of the late Ralph Gray whose commentary of the mid-1980's studies helped us to refine our experimental designs.

Publisher Copyright:
© 2021 Elsevier B.V.

Keywords

Artificial intelligence
Coal rank
HGI
Maceral
Statistics

ASJC Scopus subject areas

Fuel Technology
Geology
Economic Geology
Stratigraphy

Access to Document

10.1016/j.coal.2021.103846

Cite this

@article{9b3e3ca9ec8f49a0b8429e0b61bf2138,

title = "Soft modelling of the Hardgrove grindability index of bituminous coals: An overview",

abstract = "Predictions of the Hardgrove grindability index, a predictor of the crushing and pulverization propensity of coal, have been made using both regression and neural network techniques. All techniques suffer from shortcomings. In general, input parameters must be selected based on a sound knowledge of coal chemistry and petrology, with avoidance of redundant parameters, avoidance of closure in the data sets that add to 100% (individually the proximate and ultimate analyses, petrology, and (approximately) major oxides), and a constrained coal rank and provenance setting. Predictions based on a specific set of coals are not necessarily translatable to different ranks or maceral suites. In general, for high volatile bituminous coals, combinations of coal rank (vitrinite reflectance or volatile matter), liptinite content, and ash percentage produce the best predictions.",

keywords = "Artificial intelligence, Coal rank, HGI, Maceral, Statistics",

author = "Hower, {James C.} and Bagherieh, {Amir H.} and Dindarloo, {Saeid R.} and Trimble, {Alan S.} and Chelgani, {Saeed Chehreh}",

note = "Funding Information: We thank all of our colleagues who have guided us in these studies. In particular, Hower acknowledges the guidance of the late Ralph Gray whose commentary of the mid-1980's studies helped us to refine our experimental designs. Publisher Copyright: {\textcopyright} 2021 Elsevier B.V.",

year = "2021",

month = nov,

day = "1",

doi = "10.1016/j.coal.2021.103846",

language = "English",

volume = "247",

}

TY - JOUR

T1 - Soft modelling of the Hardgrove grindability index of bituminous coals

T2 - An overview

AU - Hower, James C.

AU - Bagherieh, Amir H.

AU - Dindarloo, Saeid R.

AU - Trimble, Alan S.

AU - Chelgani, Saeed Chehreh

N1 - Funding Information: We thank all of our colleagues who have guided us in these studies. In particular, Hower acknowledges the guidance of the late Ralph Gray whose commentary of the mid-1980's studies helped us to refine our experimental designs. Publisher Copyright: © 2021 Elsevier B.V.

PY - 2021/11/1

Y1 - 2021/11/1

N2 - Predictions of the Hardgrove grindability index, a predictor of the crushing and pulverization propensity of coal, have been made using both regression and neural network techniques. All techniques suffer from shortcomings. In general, input parameters must be selected based on a sound knowledge of coal chemistry and petrology, with avoidance of redundant parameters, avoidance of closure in the data sets that add to 100% (individually the proximate and ultimate analyses, petrology, and (approximately) major oxides), and a constrained coal rank and provenance setting. Predictions based on a specific set of coals are not necessarily translatable to different ranks or maceral suites. In general, for high volatile bituminous coals, combinations of coal rank (vitrinite reflectance or volatile matter), liptinite content, and ash percentage produce the best predictions.

AB - Predictions of the Hardgrove grindability index, a predictor of the crushing and pulverization propensity of coal, have been made using both regression and neural network techniques. All techniques suffer from shortcomings. In general, input parameters must be selected based on a sound knowledge of coal chemistry and petrology, with avoidance of redundant parameters, avoidance of closure in the data sets that add to 100% (individually the proximate and ultimate analyses, petrology, and (approximately) major oxides), and a constrained coal rank and provenance setting. Predictions based on a specific set of coals are not necessarily translatable to different ranks or maceral suites. In general, for high volatile bituminous coals, combinations of coal rank (vitrinite reflectance or volatile matter), liptinite content, and ash percentage produce the best predictions.

KW - Artificial intelligence

KW - Coal rank

KW - HGI

KW - Maceral

KW - Statistics

UR - http://www.scopus.com/inward/record.url?scp=85114414388&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85114414388&partnerID=8YFLogxK

U2 - 10.1016/j.coal.2021.103846

DO - 10.1016/j.coal.2021.103846

M3 - Review article

AN - SCOPUS:85114414388

VL - 247

M1 - 103846

ER -

Soft modelling of the Hardgrove grindability index of bituminous coals: An overview

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this