Unplanned dilution and ore loss prediction in longhole stoping mines via multiple regression and artificial neural network analyses

Прогнозирование неплановой разубоженности и потерь руды на рудниках с длинноскважинной системой разработки методом множественной регрессии и с использованием искусственных нейронных сетей
Youhei Kawamura, Hyongdoo Jang, Erkan Topal, Yoshihito Kawamura
2015-01-01

artificial neural networklonghole stopingmultiple regression analysisore loss predictionunplanned dilution
Unplanned dilution and ore loss directly influence not only the productivity of underground stopes, but also the profitability of the entire mining process. Stope dilution is a result of complex interactions between a number of factors, and cannot be predicted prior to mining. In this study, unplanned dilution and ore loss prediction models were established using multiple linear and nonlinear regression analysis (MLRA and MNRA), as well as an artificial neural network (ANN) method based on 1067 datasets with ten causative factors from three underground longhole stoping mines in Western Australia. Models were established for individual mines, as well as a general model that includes all of the mine data-sets. The correlation coefficient (R) was used to evaluate the methods, and the values for MLRA, MNRA, and ANN compared with the general model were 0.419, 0.438, and 0.719, respectively. Considering that the current unplanned dilution and ore loss prediction for the mines investigated yielded an R of 0.088, the ANN model results are noteworthy. The proposed ANN model can be used directly as a practical tool to predict unplanned dilution and ore loss in mines, which will not only enhance productivity, but will also be beneficial for stope planning and design.
1
Models were built separately for individual mines and collectively as a general model incorporating data from all three mines.
2
The ANN model substantially exceeded the mines’ existing prediction performance, which had a correlation coefficient of only 0.088.
3
The general artificial neural network model achieved a correlation coefficient of 0.719, outperforming multiple linear regression (0.419) and multiple nonlinear regression (0.438).
4
The proposed ANN model is presented as a practical tool for supporting stope planning, design, and productivity improvement.
5
The study developed unplanned dilution and ore loss prediction models using 1,067 datasets and ten causative factors from three Western Australian longhole stoping mines.

Unplanned dilution and ore loss in underground longhole stoping mines

Prediction of unplanned dilution and ore loss based on their causative factors and comparison of multiple regression and artificial neural network models

Publication Details
Publication Date
2015-01-01
Journal
Publisher
ISSN
Cited by
34
Access Type
Author Information
Authors
Youhei Kawamura
Hyongdoo Jang
Erkan Topal
Yoshihito Kawamura
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%