Exploring Deep Learning for Dig-Limit Optimization in Open-Pit Mines

Williams, Jacob; Singh, Jagjit; Kumral, Mustafa; Ruiseco, Julian Ramirez

doi:10.1007/s11053-021-09864-y

Cited by 19 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of GA in various scientific fields remains very common. It's similar in mining, where GA is most commonly used for production and equipment scheduling optimisation [51][52][53], cut-off optimisation [54,55], and grade and quality control [56,57].…”

Section: Genetic Algorithmmentioning

confidence: 99%

Hybrid Model for Optimisation of Waste Dump Design and Site Selection in Open Pit Mining

Doderovic,

Stepanovic

et al. 2023

Minerals

View full text Add to dashboard Cite

Waste management is an unavoidable technological operation in the process of raw material extraction. The main characteristic of this technological operation is the handling of large quantities of waste material, which can amount to several hundred million cubic metres. At the same time, this operation must comply with all administrative and environmental standards. Therefore, optimising waste rock management (particularly haulage and dumping) has the potential to significantly improve the overall value of the project. This paper presents a hybrid model for the optimisation of waste dump design and site selection. The model is based on different mathematical methods (Monte Carlo simulation, genetic algorithm, analytic hierarchy process and heuristic methods) adapted to different aspects of the problem. The main objective of the model is to provide a solution (in analytical and graphical form) for the draft waste dump design, on the basis of which the final waste dump design can be defined. The functioning of the model is verified using an example of an existing open pit. In the case study, 2250 members of the initial population (different waste dump variants) were generated, and a total of 110 optimised solutions were obtained using 15 optimisations. The solution with the best value of the objective function is adopted, and the final waste dump design is created.

show abstract

Section: Genetic Algorithmmentioning

confidence: 99%

Hybrid Model for Optimisation of Waste Dump Design and Site Selection in Open Pit Mining

Doderovic,

Stepanovic

et al. 2023

Minerals

View full text Add to dashboard Cite

show abstract

“…This tool was later used to evaluate the relationship between selectivity, equipment size and dig-limits definitions [Ruiseco and Kumral, 2017]. Williams et al [2021] propose a neural network to evaluate the dig-limits definition made by the genetic algorithm in order to improve the efficency of this approach. Vasylchuk and Deutsch [2019] tackle this problem with an iterative heuristic based on an initial classification using a fixed grid to maximize the expected profit, and additional steps to solve problematic locations related to operational restrictions.…”

Section: Literature Reviewmentioning

confidence: 99%

Column Generation for Mining Cut Definition with Geometallurgical Interactions

2021

View full text Add to dashboard Cite

In this work we propose a novel approach to solve the mining cut definition problem in open pit mines with geometallurgical interactions. Mining cut definition deals with the aggregation of blocks into clusters which are extracted and processed as a single unit. The aggregation must fulfill operational considerations given by the loading equipment selectivity and should maximize the objectives given by the mine operation.The proposed approach utilizes mixed integer programming and a model inspired by column generation that, contrarily to previous works, has its decision variables defined directly on the set of all feasible cuts. The advantage of this is that the model does not require linear approximations of the geometallurgical behavior of the cuts based on the blocks it contains, and therefore, can utilize any non-linear function.We apply our methodology to a real-size case study to show that the model can be solved in reasonable time, but also that non-linear recovery functions influence the destination policy and expected profit, i.e., that following the traditional free selection policy (based on cut-off grade) is not the best strategy when realistic geometallurgical interactions are considered.

show abstract

“…Recently various researchers have developed algorithms to automate and optimize the dig limit delineation process, which rely on heuristics and metaheuristic algorithms. The techniques used include greedy algorithm-based methods (Richmond and Beasley, 2004;Vasylchuk and Deutsch, 2019), mixed integer programming (MIP) (Hmoud and Kumral, 2022;Nelis and Morales, 2021;Nelis, and Meunier, 2022;Sari and Kumral, 2017;Tabesh and Askari-Nasab, 2011), genetic algorithms (Ruiseco, 2016;Ruiseco, Williams, and Kumral, 2016;Ruiseco and Kumral, 2017;Williams et al, 2021), simulated annealing (Deutsch, 2017;Hanemaaijer, 2018;Isaaks, Treloar, and Elenbaas 2014;Kumral, 2013;Neufeld, Norrena, and Deutsch, 2003;Norrena and Deutsch, 2001), block aggregation by clustering (Salman et al, 2021) and convolutional neural networks (Williams et al, 2021), or a combination of techniques. With these algorithms, the definition of 'mineability' or 'digability' varied greatly between different investigators.…”

Section: Introductionmentioning

confidence: 99%

“…Finally, their model adapted problematic locations by reconsidering the neighbouring blocks and their destinations and performed a hill climbing step to improve the solution iteratively. Williams et al (2021) recently explored GA solutions using a CNN to assess the dig limit cluster quality. The algorithm was very fast but could not well distinguish different clustering penalties (position-and-orientation-related).…”

Section: Introductionmentioning

confidence: 99%

Stochastic analysis of dig limit optimization using simulated annealing

Duijvenbode

Shishvan

2023

J. S. Afr. Inst. Min. Metall.

View full text Add to dashboard Cite

The results of dig limit delineation in open pit mining are never truly optimized due to gaps in the underlying data, such as insufficient sampling. Aside from the data uncertainty, there is also an influence on the final dig limit by either humans or by the heuristic character of an optimization method like simulated annealing. Several dig limit optimizers have been published, which can replace the manual dig-limits designing process. However, these dig limit designs are generally not adapted to account for this heuristic character. In this paper we present a stochastic analysis tool that can be used with the results of heuristic dig-limit optimization to increase confidence in the obtained results. First, an enhanced simulated annealing algorithm for dig limit optimization is presented. Then, this algorithm is tested on ten different blasts at the Marigold mine, Nevada, USA, as a case study. Finally, the results are analysed with a destination-based ensemble probability map and an analysis conducted of the final solution data distribution. The generated dig-limit designs of the algorithm include high revenue areas that are excluded in comparable manual designs and show improved objective and revenue values. The analysis tool provides block destination probabilities and box plots with the distribution of opportunity value for the dig limit. Furthermore, with the analysis tool, it is possible to make well-informed design decisions in areas of uncertainty.

show abstract

Exploring Deep Learning for Dig-Limit Optimization in Open-Pit Mines

Cited by 19 publications

References 26 publications

Hybrid Model for Optimisation of Waste Dump Design and Site Selection in Open Pit Mining

Hybrid Model for Optimisation of Waste Dump Design and Site Selection in Open Pit Mining

Column Generation for Mining Cut Definition with Geometallurgical Interactions

Stochastic analysis of dig limit optimization using simulated annealing

Contact Info

Product

Resources

About