Wyniki wyszukiwania - BazTech

1

Predicting open-pit mine production using machine learning techniques

Kumah Faustin Nartey, Alex Kwasi Saim, Oppong Millicent Nkrumah, Arthur Clement Kweku

Journal of Sustainable Mining

|

2024

|

Vol. 23, iss. 2

118--131

EN

In mining, where production is affected by several factors, including equipment availability, it is necessary to develop reliable models to accurately predict mine production to improve operational efficiency. Hence, in this study, four (4) machine learning algorithms - namely: artificial neural network (ANN), random forest (RF), gradient boosting regression (GBR) and decision tree (DT)) - were implemented to predict mine production. Multiple Linear Regression (MLR) analysis was used as a baseline study for comparison purposes. In that regard, one hundred and twenty-six (126) datasets from an open-pit gold mine were used. The developed models were evaluated and compared using the correlation coefficient (R2), mean absolute percentage error (MAPE) and variance accounted for (VAF). It has been shown in this study that the ANN model can best estimate open-pit mine production by comparing its performance to that of the other machine learning models. The R2, MAPE, RMSE and VAF of the models were 0.8003, 0.7486, 0.7519, 0.6538, 0.6044, 4.23%, 5.07%, 5.44%, 6.31%, 6.15% and 79.66%, 74.69%, 74.10%, 65.16% and 60.11% for ANN, RF, GBR, DT and MLR, respectively. Overall, this study has shown that machine learning algorithms predict mine production with higher accuracy.

2

Uncertainty analysis of production in open pit mines – operational parameter regression analysis of mining machinery

Lanke A. A., Ghodarati B., Hoseinie S. H.

Mining Science

|

2016

|

Vol. 23

147--160

EN

In mining uncertainties related to equipment and operation are major reasons for loss of production. In order to address this issue, a wide literature review was done in this study. It showed that reliability of equipment, spare part availability, automation of equipment are researched areas focused. However, a methodology which relates operational issues directly to production levels has been not studied with detailed analysis. In order to overcome this issue and propose, a method to achieve production assurance is the objective of this study. A case study with 2.5 years of data from a large open pit mine is carried out. Following the statistical principles, multiple regressions modelling with details analysis, optimization of payload and interpretation of analysis are used. It showed that at system level availability, utilization and maximum capacities are important criteria for finding root cause in loss of production. Model for shovel fleet showed that availability is the most important characteristics hindering it to achieve a higher level of production. It was also seen that 3 to 4 number of shovels are optimal for achieving current level of production. For truck fleet model represented that capacities involved are less important factor as compared to the utilization of the fleet.

3

Modeling and simulation analysis of mine production in 3D environment

Chęciński S., Witt A.

Mining Science

|

2015

|

Vol. 22

183--191

EN

The article considers the problems posed by the application of 3D simulation analysis to the modeling of production processes in surface mining. The issues here focused on include the possibilities of creating the representations of mining exploitation elements in a three-dimensional environment as well as the description of the influence that spatial characteristics of surface mines has on simulation processes. The paper also discusses the sense for employing simulation techniques in the design of surface mining production processes and presents the results of analysis performed for a model production system. In conclusion the advantages and disadvantages of the described solutions are compared and the perspectives for their further development and popularization are described.

4

Symulacje funkcjonowania układu produkcyjnego kopalni odkrywkowej w środowisku 3D

Chęciński S., Witt A.

Górnictwo Odkrywkowe

|

2015

|

R. 56, nr 6

5--10

PL

W artykule przedstawiono problematykę wykorzystania analiz symulacyjnych 3D w modelowaniu procesów produkcyjnych górnictwa odkrywkowego. Przedstawiono możliwości tworzenia reprezentacji elementów eksploatacji górniczej w środowisku trójwymiarowym oraz omówiono wpływ charakterystyki przestrzennej kopalni odkrywkowych na przeprowadzanie procesów symulacji. Omówiono zasadność wykorzystania technik symulacyjnych w projektowaniu procesów produkcyjnych górnictwa odkrywkowego oraz zaprezentowano wyniki analiz zrealizowanych dla modelowego układu produkcyjnego. Podsumowaniem publikacji jest zestawienie zalet i wad opisywanych rozwiązań, wraz z konkluzjami dotyczącymi dalszego ich rozwoju i popularyzacji.

EN

Article discusses basic issues related to using 3D simulation analysis for mining production processes modeling. It presents the possibilities of making a three dimensional mine elements representation, and also contains discussion about the impact of mine spatial characteristics on making simulation analysis. The article shows correct techniques of using simulation processes during the planning of mining production and presents the results of analysis made for model production system. In the summary advantages and disadvantages of the presented solutions are listed, along with conclusions for its future development and popularization.

5

Optimization of mineral processing plant through ROM ore size

Pan X.

AGH Journal of Mining and Geoengineering

|

2012

|

Vol. 36, no. 4

123-132

EN

The ore beneficiation at a mine could be described as complex and expensive, involving many balancing processes where material flow rates, size, density and other factors must all be in balance, if any degree of plant optimization is to be achieved. To determine the optimum setup for maximizing throughput at the final step in the beneficiation process, such as the dense media separation units, a mine optimizer is developed using constraint-based global optimization. The Mine Optimizer uses plant unit availability, capacity in tons per hour (t/h), change in material size (between crushers) and other constraints. The result is that improving cheaper upstream processes, such as blasting, can significantly increase the throughput of expensive downstream processes, like crushing, through improved fragmentation of the ROM ore. For instance, if the ROM ore is not in the required range, the plant production is unbalanced and consequently the mine could loss production by 10-20%, even 50% in the worst case. On one hand, a finer ROM ore may result in lower utilisation of both crushing and coarse separation by 50%. Meanwhile other process units are running at 100% capacity, such as slimes and tailing dumping. In addition, a finer ROM ore may destroy the mineral value as well, such as in the cases of mining coal, iron ore, and diamond ore, where a higher price is for the products of larger size.

PL

Wzbogacanie rud w kopalni można określić jako złożone i drogie, uwzględniające wiele procesów bilansowych, dla których ilości materiału, ich rozmiar, gęstość i inne cechy muszą pozostawać w stanie określonej równowagi jeżeli optymalizacja jest celem, który chce się osiągnąć. Aby określić optymalne ustawienia dla procesu wzbogacania, tj. w przypadku jednostek wzbogacania w cieczach ciężkich skonstruowano optymalizator kopalniany uwzględniający ogólną optymalizację zakładu. Optymalizator Kopalni korzysta z dostępności danej jednostki, wydajności w tonach na godzinę (t/h), zmian w rozmiarach materiału (pomiędzy kruszeniami) i innych ograniczeń. Wynik pozwala zoptymalizować tańsze procesy, takie jest strzelanie co pozwala z kolei znacząco poprawić procesy droższe, tj. kruszenie, dzięki zoptymalizowanemu rozdrobnieniu rudy surowej. Dla przykładu, jeżeli uziarnienie rudy surowej nie jest wymaganego rozmiaru, produkcja zakładu nie jest zbilansowana i tym samym produkcja zakładu jest niższa o 10-20% lub nawet 50% w najgorszych przypadkach. Z drugiej strony, zbyt drobna ruda surowa może spowodować mniejszą stosowalność procesów kruszenia o nawet 50% a w tym samym czasie inne jednostki produkcyjne pracują na 100% swojej wydajności, tj. np. składowiska odpadów. Ponadto, drobniejsza ruda surowa może spowodować spadek wartości minerału, jak np. w przypadku węgla, rudy żelaza bądź diamentów, gdzie wyższa cena produktów zależy od większego ich rozmiaru.