Marinésio Pinheiro de Lima
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Marinésio Pinheiro de Lima has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Hyongdoo Jang
Hanwha Mining Services Australia, Brisbane, QLD 4172, Australia
1 shared publication - Igor Fernandes Gomes
Universidade Federal de Pernambuco
1 shared publication - Jorge Luiz Valença Mariz
Mining Engineering Department, Universidade Federal de Pernambuco, Recife 50670-901, Brazil
1 shared publication - Leonardo José Do Nascimento Guimarães
Professor Dr Universidade Federal de Pernambuco (UFPE) Pernambuco Brazil
1 shared publication - Ricardo Martins de Abreu Silva
Federal University of Pernambuco
1 shared publication - Tertius S. G. Ferraz
Computer Center, Universidade Federal de Pernambuco, Recife CEP 50740-560, Brazil
1 shared publication
Latest Publications
- Open Access
- 26 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (11) , 5996
Predicting Dilution in Underground Mines with Stacking Artificial Intelligence Models and Genetic Algorithms
Dilution in underground mining refers to the unintended incorporation of waste material into the ore, reducing ore grade, revenue, and operational safety. Unplanned dilution, specifically, occurs due to overbreak caused by blasting inefficiencies or poor rock stability. To mitigate this issue, various factors related to rock quality, stope geometry, drilling, and blasting must be carefully considered. This study introduces a statistically rigorous methodology for the prediction of dilution in underground mining operations. The proposed framework incorporates a 10-fold cross-validation procedure with 30 repetitions, along with the application of nonparametric statistical tests. A total of eight supervised machine learning algorithms were investigated, with their hyperparameters systematically optimized using two distinct genetic algorithm (GA) strategies evaluated under varying population sizes. The models include support vector machines, neural networks, and tree-based approaches. Using a dataset of 120 samples, the results indicate that the GA-ANN model outperforms other approaches, achieving , , and values of 0.2986, 0.8457, and 0.3928 for the training dataset, and 0.1882, 0.9508, and 0.2283 for the testing dataset, respectively. Furthermore, four stacking models were constructed by aggregating the top-performing base learners, giving rise to ensemble metamodels applied, for the first time, to the task of dilution prediction in underground mining.- 26 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (11) , 5996
Open AccessPredicting Dilution in Underground Mines with Stacking Artificial Intelligence Models and Genetic Algorithms
Dilution in underground mining refers to the unintended incorporation of waste material into the ore, reducing ore grade, revenue, and operational safety. Unplanned dilution, specifically, occurs due to overbreak caused by blasting inefficiencies or poor rock stability. To mitigate this issue, various factors related to rock quality, stope geometry, drilling, and blasting must be carefully considered. This study introduces a statistically rigorous methodology for the prediction of dilution in underground mining operations. The proposed framework incorporates a 10-fold cross-validation procedure with 30 repetitions, along with the application of nonparametric statistical tests. A total of eight supervised machine learning algorithms were investigated, with their hyperparameters systematically optimized using two distinct genetic algorithm (GA) strategies evaluated under varying population sizes. The models include support vector machines, neural networks, and tree-based approaches. Using a dataset of 120 samples, the results indicate that the GA-ANN model outperforms other approaches, achieving , , and values of 0.2986, 0.8457, and 0.3928 for the training dataset, and 0.1882, 0.9508, and 0.2283 for the testing dataset, respectively. Furthermore, four stacking models were constructed by aggregating the top-performing base learners, giving rise to ensemble metamodels applied, for the first time, to the task of dilution prediction in underground mining. - Open Access
- 1 January 2024
- Published by FapUNIFESP (SciELO) in REM - International Engineering Journal
- Vol. 77 (3) , e230080
Numerical modeling of the underground mining stope stability considering time-dependent deformations via finite element method
The main objective of this study is to evaluate the hanging wall stability of the mining stopes resulting from the open stope underground mining method, taking into account the exposure time of the wall sans any support, through numerical simulation, using an elasto-viscoplastic model formulated for the finite element method. In order to carry out the simulation, a real application case was chosen: the extraction of a mining block from the underground zinc mine of Nexa Resources, in the municipality of Vazante-MG, which operates through the open stope mining method, where the values of unplanned dilution are known. The stability of the stope’s hanging wall was analyzed through two instability indicators, the horizontal displacements and the minor principal stress, simulated in a two-dimensional perpendicular section and in the center of the stope. The results obtained in the simulations were coherent with the real results that occurred in the stope, and with the rheological behavior of the rocks, since the unstable regions increase with the exposure time without any type of support used, which shows that the model used is a good alternative for prediction of the dilution and the evolution of instability areas of the stope wall according to its exposure time.
- 1 January 2024
- Published by FapUNIFESP (SciELO) in REM - International Engineering Journal
- Vol. 77 (3) , e230080
Open AccessNumerical modeling of the underground mining stope stability considering time-dependent deformations via finite element method
The main objective of this study is to evaluate the hanging wall stability of the mining stopes resulting from the open stope underground mining method, taking into account the exposure time of the wall sans any support, through numerical simulation, using an elasto-viscoplastic model formulated for the finite element method. In order to carry out the simulation, a real application case was chosen: the extraction of a mining block from the underground zinc mine of Nexa Resources, in the municipality of Vazante-MG, which operates through the open stope mining method, where the values of unplanned dilution are known. The stability of the stope’s hanging wall was analyzed through two instability indicators, the horizontal displacements and the minor principal stress, simulated in a two-dimensional perpendicular section and in the center of the stope. The results obtained in the simulations were coherent with the real results that occurred in the stope, and with the rheological behavior of the rocks, since the unstable regions increase with the exposure time without any type of support used, which shows that the model used is a good alternative for prediction of the dilution and the evolution of instability areas of the stope wall according to its exposure time.