Applied Machine Learning for Geometallurgical Throughput Prediction—A Case Study Using Production Data at the Tropicana Gold Mining Complex

With the increased use of digital technologies in the mining industry, the amount of centrally stored production data is continuously growing. However, datasets in mines and processing plants are not fully utilized to build links between extracted materials and metallurgical plant performances. This...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Christian Both, Roussos Dimitrakopoulos
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	tactical geometallurgy data analytics in mining ball mill throughput measurement while drilling non-additivity Mineralogy QE351-399.2
Acceso en línea:	https://doaj.org/article/777f5b1e15fd4d99ad8e7fd94877fe3d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:777f5b1e15fd4d99ad8e7fd94877fe3d
record_format	dspace
spelling	oai:doaj.org-article:777f5b1e15fd4d99ad8e7fd94877fe3d2021-11-25T18:26:39ZApplied Machine Learning for Geometallurgical Throughput Prediction—A Case Study Using Production Data at the Tropicana Gold Mining Complex10.3390/min111112572075-163Xhttps://doaj.org/article/777f5b1e15fd4d99ad8e7fd94877fe3d2021-11-01T00:00:00Zhttps://www.mdpi.com/2075-163X/11/11/1257https://doaj.org/toc/2075-163XWith the increased use of digital technologies in the mining industry, the amount of centrally stored production data is continuously growing. However, datasets in mines and processing plants are not fully utilized to build links between extracted materials and metallurgical plant performances. This article shows a case study at the Tropicana Gold mining complex that utilizes penetration rates from blasthole drilling and measurements of the comminution circuit to construct a data-driven, geometallurgical throughput prediction model of the ball mill. Several improvements over a previous publication are shown. First, the recorded power draw, feed particle and product particle size are newly considered. Second, a machine learning model in the form of a neural network is used and compared to a linear model. The article also shows that hardness proportions perform 6.3% better than averages of penetration rates for throughput prediction, underlining the importance of compositional approaches for non-additive geometallurgical variables. When adding ball mill power and product particle size, the prediction error (RMSE) decreases by another 10.6%. This result can only be achieved with the neural network, whereas the linear regression shows improvements of 4.2%. Finally, it is discussed how the throughput prediction model can be integrated into production scheduling.Christian BothRoussos DimitrakopoulosMDPI AGarticletactical geometallurgydata analytics in miningball mill throughputmeasurement while drillingnon-additivityMineralogyQE351-399.2ENMinerals, Vol 11, Iss 1257, p 1257 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	tactical geometallurgy data analytics in mining ball mill throughput measurement while drilling non-additivity Mineralogy QE351-399.2
spellingShingle	tactical geometallurgy data analytics in mining ball mill throughput measurement while drilling non-additivity Mineralogy QE351-399.2 Christian Both Roussos Dimitrakopoulos Applied Machine Learning for Geometallurgical Throughput Prediction—A Case Study Using Production Data at the Tropicana Gold Mining Complex
description	With the increased use of digital technologies in the mining industry, the amount of centrally stored production data is continuously growing. However, datasets in mines and processing plants are not fully utilized to build links between extracted materials and metallurgical plant performances. This article shows a case study at the Tropicana Gold mining complex that utilizes penetration rates from blasthole drilling and measurements of the comminution circuit to construct a data-driven, geometallurgical throughput prediction model of the ball mill. Several improvements over a previous publication are shown. First, the recorded power draw, feed particle and product particle size are newly considered. Second, a machine learning model in the form of a neural network is used and compared to a linear model. The article also shows that hardness proportions perform 6.3% better than averages of penetration rates for throughput prediction, underlining the importance of compositional approaches for non-additive geometallurgical variables. When adding ball mill power and product particle size, the prediction error (RMSE) decreases by another 10.6%. This result can only be achieved with the neural network, whereas the linear regression shows improvements of 4.2%. Finally, it is discussed how the throughput prediction model can be integrated into production scheduling.
format	article
author	Christian Both Roussos Dimitrakopoulos
author_facet	Christian Both Roussos Dimitrakopoulos
author_sort	Christian Both
title	Applied Machine Learning for Geometallurgical Throughput Prediction—A Case Study Using Production Data at the Tropicana Gold Mining Complex
title_short	Applied Machine Learning for Geometallurgical Throughput Prediction—A Case Study Using Production Data at the Tropicana Gold Mining Complex
title_full	Applied Machine Learning for Geometallurgical Throughput Prediction—A Case Study Using Production Data at the Tropicana Gold Mining Complex
title_fullStr	Applied Machine Learning for Geometallurgical Throughput Prediction—A Case Study Using Production Data at the Tropicana Gold Mining Complex
title_full_unstemmed	Applied Machine Learning for Geometallurgical Throughput Prediction—A Case Study Using Production Data at the Tropicana Gold Mining Complex
title_sort	applied machine learning for geometallurgical throughput prediction—a case study using production data at the tropicana gold mining complex
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/777f5b1e15fd4d99ad8e7fd94877fe3d
work_keys_str_mv	AT christianboth appliedmachinelearningforgeometallurgicalthroughputpredictionacasestudyusingproductiondataatthetropicanagoldminingcomplex AT roussosdimitrakopoulos appliedmachinelearningforgeometallurgicalthroughputpredictionacasestudyusingproductiondataatthetropicanagoldminingcomplex
_version_	1718411139781492736

Applied Machine Learning for Geometallurgical Throughput Prediction—A Case Study Using Production Data at the Tropicana Gold Mining Complex

Ejemplares similares