Forecasting mass and metallurgical balance at a gold processing plant using modern multivariate statistics
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | REM - International Engineering Journal |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S2448-167X2020000400571 |
Resumo: | Abstract Knowing the quantity and the quality of products and tailings generated by a beneficiation plant, even before ore processing, can make the mining operations more sustainable, more profitable, and safer. To forecast these values, it is necessary to submit samples to batch tests which mimic the processing workflow used on an industrial scale. Then, the results need to be analysed with the aim of finding a statistical model able to comprehend how Run of Mine (ROM) characteristics impact the performance at the beneficiation. After developing a model, it is possible to apply it to blocks where the ROM characteristics are known, but the metallurgical information is not, making it possible to estimate these. With this goal, a geometallurgical model was developed with a neural network technique using 37 samples collected at two Brazilian gold mines. The Au and S grades in ROM, and the mine from where the sample was collected, were used as input variables. The model was able to forecast the following variables with a Pearson correlation coefficient on the cross validation test set equal to the value in parenthesis: mass (0.55) and metallurgical (0.54) recovery in the gravimetric concentrate, mass (0.80) and metallurgical (0.12) recovery in the flotation tailings, mass (0.77) and metallurgical (0.11) recovery in the leaching tailings, mass recovery (0.84) of gas sent to the sulphuric acid plant, and metallurgical recovery (0.65) in the leaching concentrate. The results obtained with neural networks were superior to the ones obtained when three alternative techniques were tested. |
id |
FG-1_bc014d737772cb6e738e91c3fb2205b4 |
---|---|
oai_identifier_str |
oai:scielo:S2448-167X2020000400571 |
network_acronym_str |
FG-1 |
network_name_str |
REM - International Engineering Journal |
repository_id_str |
|
spelling |
Forecasting mass and metallurgical balance at a gold processing plant using modern multivariate statisticsmass recoverymetallurgical recoverygeometallurgyneural networksgoldAbstract Knowing the quantity and the quality of products and tailings generated by a beneficiation plant, even before ore processing, can make the mining operations more sustainable, more profitable, and safer. To forecast these values, it is necessary to submit samples to batch tests which mimic the processing workflow used on an industrial scale. Then, the results need to be analysed with the aim of finding a statistical model able to comprehend how Run of Mine (ROM) characteristics impact the performance at the beneficiation. After developing a model, it is possible to apply it to blocks where the ROM characteristics are known, but the metallurgical information is not, making it possible to estimate these. With this goal, a geometallurgical model was developed with a neural network technique using 37 samples collected at two Brazilian gold mines. The Au and S grades in ROM, and the mine from where the sample was collected, were used as input variables. The model was able to forecast the following variables with a Pearson correlation coefficient on the cross validation test set equal to the value in parenthesis: mass (0.55) and metallurgical (0.54) recovery in the gravimetric concentrate, mass (0.80) and metallurgical (0.12) recovery in the flotation tailings, mass (0.77) and metallurgical (0.11) recovery in the leaching tailings, mass recovery (0.84) of gas sent to the sulphuric acid plant, and metallurgical recovery (0.65) in the leaching concentrate. The results obtained with neural networks were superior to the ones obtained when three alternative techniques were tested.Fundação Gorceix2020-12-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S2448-167X2020000400571REM - International Engineering Journal v.73 n.4 2020reponame:REM - International Engineering Journalinstname:Fundação Gorceix (FG)instacron:FG10.1590/0370-44672020730001info:eu-repo/semantics/openAccessNiquini,Fernanda Gontijo FernandesCosta,João Felipe Coimbra Leiteeng2020-09-28T00:00:00Zoai:scielo:S2448-167X2020000400571Revistahttps://www.rem.com.br/?lang=pt-brPRIhttps://old.scielo.br/oai/scielo-oai.php||editor@rem.com.br2448-167X2448-167Xopendoar:2020-09-28T00:00REM - International Engineering Journal - Fundação Gorceix (FG)false |
dc.title.none.fl_str_mv |
Forecasting mass and metallurgical balance at a gold processing plant using modern multivariate statistics |
title |
Forecasting mass and metallurgical balance at a gold processing plant using modern multivariate statistics |
spellingShingle |
Forecasting mass and metallurgical balance at a gold processing plant using modern multivariate statistics Niquini,Fernanda Gontijo Fernandes mass recovery metallurgical recovery geometallurgy neural networks gold |
title_short |
Forecasting mass and metallurgical balance at a gold processing plant using modern multivariate statistics |
title_full |
Forecasting mass and metallurgical balance at a gold processing plant using modern multivariate statistics |
title_fullStr |
Forecasting mass and metallurgical balance at a gold processing plant using modern multivariate statistics |
title_full_unstemmed |
Forecasting mass and metallurgical balance at a gold processing plant using modern multivariate statistics |
title_sort |
Forecasting mass and metallurgical balance at a gold processing plant using modern multivariate statistics |
author |
Niquini,Fernanda Gontijo Fernandes |
author_facet |
Niquini,Fernanda Gontijo Fernandes Costa,João Felipe Coimbra Leite |
author_role |
author |
author2 |
Costa,João Felipe Coimbra Leite |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Niquini,Fernanda Gontijo Fernandes Costa,João Felipe Coimbra Leite |
dc.subject.por.fl_str_mv |
mass recovery metallurgical recovery geometallurgy neural networks gold |
topic |
mass recovery metallurgical recovery geometallurgy neural networks gold |
description |
Abstract Knowing the quantity and the quality of products and tailings generated by a beneficiation plant, even before ore processing, can make the mining operations more sustainable, more profitable, and safer. To forecast these values, it is necessary to submit samples to batch tests which mimic the processing workflow used on an industrial scale. Then, the results need to be analysed with the aim of finding a statistical model able to comprehend how Run of Mine (ROM) characteristics impact the performance at the beneficiation. After developing a model, it is possible to apply it to blocks where the ROM characteristics are known, but the metallurgical information is not, making it possible to estimate these. With this goal, a geometallurgical model was developed with a neural network technique using 37 samples collected at two Brazilian gold mines. The Au and S grades in ROM, and the mine from where the sample was collected, were used as input variables. The model was able to forecast the following variables with a Pearson correlation coefficient on the cross validation test set equal to the value in parenthesis: mass (0.55) and metallurgical (0.54) recovery in the gravimetric concentrate, mass (0.80) and metallurgical (0.12) recovery in the flotation tailings, mass (0.77) and metallurgical (0.11) recovery in the leaching tailings, mass recovery (0.84) of gas sent to the sulphuric acid plant, and metallurgical recovery (0.65) in the leaching concentrate. The results obtained with neural networks were superior to the ones obtained when three alternative techniques were tested. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S2448-167X2020000400571 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S2448-167X2020000400571 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/0370-44672020730001 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Fundação Gorceix |
publisher.none.fl_str_mv |
Fundação Gorceix |
dc.source.none.fl_str_mv |
REM - International Engineering Journal v.73 n.4 2020 reponame:REM - International Engineering Journal instname:Fundação Gorceix (FG) instacron:FG |
instname_str |
Fundação Gorceix (FG) |
instacron_str |
FG |
institution |
FG |
reponame_str |
REM - International Engineering Journal |
collection |
REM - International Engineering Journal |
repository.name.fl_str_mv |
REM - International Engineering Journal - Fundação Gorceix (FG) |
repository.mail.fl_str_mv |
||editor@rem.com.br |
_version_ |
1754734691844358144 |