Search

Machine learning (ML) applications are increasing their footprint in underground mine planning, enabled by the gradual enrichment of research methods. Indeed, improvements in prediction results have been accelerated in areas such as mining dilution, stope stability, ore grade, and equipment availability, among others. In addition, the increasing deployment of equipment with digital technologies and rapid information retrieval sensor networks is resulting in the production of immense quantities of operational data. However, despite these favourable developments, optimisation studies on key input activities are still siloed, with minimal or no synergies towards the primary objective of optimising the production schedule. As such, the full potential of ML benefits is not realised. To explore the potential benefits, this study outlines primary input areas in production scheduling for reference and limits the scope to six key areas, covering dilution prediction, ore grade variability, geotechnical stability, ventilation, mineral commodity prices and data management. The study then delves into the literature of each before examining the limitations of existing common applications, including ML. Finally, conclusions with recommendations/solutions to enhance resilience, global optimality, and reliability of the production schedule through synergistic nexus with function-specific optimised input models are presented. [ABSTRACT FROM AUTHOR]

The short-term scheduling of activities in underground mines is an important step in mining operations. This procedure is a challenging optimization problem since it deals with many resources and activities conducted in a confined working space. Moreover, underground mining operations deal with multiple uncertainties such as the variation of activity durations. In this paper, a constraint programming (CP) model is proposed for short-term planning in underground mines. The developed model takes into account the technical requirements of underground operations to build realistic mine schedules. Furthermore, two different approaches are proposed based on the CP model for robust short-term underground mine scheduling. The first approach aims to create a robust schedule using multiple scenarios of the problem. This stochastic CP model enables to find a set of ordered robust sequences of activities performed by each available disjunctive resource over several scenarios. In the second approach, a confidence constraint is introduced in the CP model to specify the probability that the schedule generated would not underestimate the duration of activities. The model allows the mine planner to control the risk level with which an optimized solution should be produced such that it can be implemented given the actual activity durations. The presented approaches are tested on real data sets of an underground gold mine in Canada. An evaluation model is designed to evaluate the robust performance of the proposed models. The experiments demonstrate that both scenario-based and confidence-constraint approaches outperform the deterministic model by generating schedules that are more robust to uncertainties in underground operations. [ABSTRACT FROM AUTHOR]

This study examines how ESG risks and opportunities can be systematically identified, assessed, and incorporated into the early-stage design and planning of natural resources projects. The focus for this study will be on the mining activities required to source the resources for the global decarbonization effort. The need for a framework to incorporate ESG risks and opportunities into the strategic mine planning process was first identified in the de Beers Sustainability Valuation Approach. The Social Value Capital Decision Model advanced by BHP represents an advance on the de Beers model. This is the first example of a structured methodology for systematically considering stakeholder values and incorporating these into the capital decision framework. To test the applicability of a new approach to mine design by using Quality Function Deployment (QFD), a case study involving a copper mine located in South America was developed. This case study demonstrates how QFD can provide clear line-of-sight to connect design decisions with priority stakeholder concerns. The framework provides a communications tool for aligning the ESG design process across functional silos within complex organizations. The development of appropriate software tools could assist in managing the inherent complexity associated with integrating stakeholder value concerns into early stage design decisions.

Conventional underground long-term mine planning is based on a deterministic stepwise framework, which is unable to effectively manage the synergies between the mine planning components or to manage the orebody risk in production schedules and forecasts. The present study enhances prior integrated optimisation approaches to a variation of the sublevel longhole open stoping mining method using backfilling, through a new two-stage stochastic integer programming formulation. A comparison to a sequential stochastic approach shows different stope layouts and extraction sequences for a copper mine with secondary elements being gold and uranium. The integrated approach shows lower horizontal development costs and 6% higher net present value. [ABSTRACT FROM AUTHOR]

This study examines how ESG risks and opportunities can be systematically identified, assessed, and incorporated into the early-stage design and planning of natural resources projects. The focus for this study will be on the mining activities required to source the resources for the global decarbonization effort. The need for a framework to incorporate ESG risks and opportunities into the strategic mine planning process was first identified in the de Beers Sustainability Valuation Approach. The Social Value Capital Decision Model advanced by BHP represents an advance on the de Beers model. This is the first example of a structured methodology for systematically considering stakeholder values and incorporating these into the capital decision framework. To test the applicability of a new approach to mine design by using Quality Function Deployment (QFD), a case study involving a copper mine located in South America was developed. This case study demonstrates how QFD can provide clear line-of-sight to connect design decisions with priority stakeholder concerns. The framework provides a communications tool for aligning the ESG design process across functional silos within complex organizations. The development of appropriate software tools could assist in managing the inherent complexity associated with integrating stakeholder value concerns into early stage design decisions. [ABSTRACT FROM AUTHOR]

Copyright of Journal of King Abdulaziz University: Engineering Sciences is the property of King Abdulaziz University, Scientific Publishing Centre and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Since the open-pit precedence-constrained production scheduling problem is an NP-hard problem, solving it is always a challenging task, especially from a long-term perspective because a mineral deposit containing millions of blocks would require several million precedence arcs as constraints, making the solution time grow exponentially and making a direct approach unfeasible. Therefore, different strategies have been employed since the 1960s to reduce the size of this problem, such as determining the ultimate pit limit, subdividing it into phases, segmenting the production scheduling problem into long-, mid-, and short-term plans, as well as aggregating blocks into clusters, thus significantly reducing the number of precedence arcs. Different modeling and clustering strategies have already been employed in an attempt to reduce the size of the mine sequencing problem, such as layer modeling, re-blocking, bench-phase clustering, or polygon (mining cut) clustering based on a similarity function. The mining cut clustering problem has been solved lately by machine learning and heuristics techniques, and this approach can also introduce operational constraints to the mine sequencing problem, such as equipment size, minimum pit width, and preferential mining direction. In this study, we propose a mining cut clustering model based on Mixed Integer Linear Programming (MILP). Then we solve it by an exact approach and by Constraint Programming (CP), analyzing the strengths and weaknesses of the Constraint Optimization Problem (COP) and Constraint Satisfaction Problem (CSP) techniques. Numerical experiments were carried out on the Bench 15 of the Newman1 dataset, demonstrating the superiority of the COP approach. [ABSTRACT FROM AUTHOR]

Long-term production planning for open-pit mines is recognised as one of the vital decision-making issues in open-pit mining operations. In addition, the ore grade is one of the most significant sources of uncertainty in a mining operation, as it classified run-of-mine material into ore and waste. In the classical approach, the destination of mining blocks is determined by comparing the estimated grade with a pre-determined cut-off grade. However, the uncertainty of material grade dramatically affects production planning. In this paper, a novel model was developed based on the idea of simulating the grade to incorporate the risk of grade uncertainty. In the proposed model, the economic consequences of the assigned destination are calculated using the profit and loss functions and they are integrated with the production scheduling. The proposed production planning was implemented in an iron ore mine, and the results were discussed for classical, loss, and profit models. Results show that the net present value increases by 3.64% by implementing the profit function. In contrast, the loss function method reduces the net present value by 2.23% compared to the classic model. This happens because the amount of ore class is increased by 7.46% using the profit function method and decreased by 2.49% using the loss function method. Additionally, the coefficient of variation, as an index of uncertainty, was investigated. The results show that the loss function approach attempts to extract more reliable blocks in the early years and postpone the high-uncertain blocks to the later years of the production.

Long-term production planning for open-pit mines is recognised as one of the vital decision-making issues in open-pit mining operations. In addition, the ore grade is one of the most significant sources of uncertainty in a mining operation, as it classified run-of-mine material into ore and waste. In the classical approach, the destination of mining blocks is determined by comparing the estimated grade with a predetermined cut-off grade. However, the uncertainty of material grade dramatically affects production planning. In this paper, a novel model was developed based on the idea of simulating the grade to incorporate the risk of grade uncertainty. In the proposed model, the economic consequences of the assigned destination are calculated using the profit and loss functions and they are integrated with the production scheduling. The proposed production planning was implemented in an iron ore mine, and the results were discussed for classical, loss, and profit models. Results show that the net present value increases by 3.64% by implementing the profit function. In contrast, the loss function method reduces the net present value by 2.23% compared to the classic model. This happens because the amount of ore class is increased by 7.46% using the profit function method and decreased by 2.49% using the loss function method. Additionally, the coefficient of variation, as an index of uncertainty, was investigated. The results show that the loss function approach attempts to extract more reliable blocks in the early years and postpone the high-uncertain blocks to the later years of the production. [ABSTRACT FROM AUTHOR]

Mine planning and pit design involve making the best decisions and recognising good practices for the profitable exploitation of mineral resources. A pit design project begins with the delimitation of the ore body in the form of blocks, then going through pit optimisation, then pit design and sequencing and ends with the economic evaluation. Several techno-economic indicators are used in these stages and have a direct impact on mine planning. The research methodology proposes an in-depth study of the geotechnical parameters of the pit to be conducted in mine planning in a more reliable and assertive way, with the aid of 3D geotechnical modelling. From a geotechnical point of view, an initial validation of the methodology was performed in an example of application in an iron mine, where a change in the planned slope angles of a pit over a 5-year period was suggested. The suggested new pit guarantees safety factors that suit the minimum stability requirements and proposes a 1.49% higher ore availability and a 0.90% increase in the net present value. [ABSTRACT FROM AUTHOR]

Stope design is an important part of mine planning, and it aims to balance ore recovery, ore dilution, and production costs without compromising the safety aspects. This paper summarizes the main results from the research, which aims to introduce new techniques to describe the ore body and surrounding rock mass at the tunnel face prior to stope excavation. The research comprises a literature review and a survey among mining professionals to assess current stope design practices. The study identifies geotechnical data, software improvements, and integration of design into mine planning as the most critical areas for improvement. The empirical part of the study proposes new techniques for fast data acquisition. The laser-induced breakdown spectrometry (LIBS) technique is developed for measurements at the tunnel face and from core boxes to provide mineralogical and geometallurgical data. Ground-penetrating radar (GPR) studies are conducted to improve discontinuity characterization, and rapid photogrammetric methods are proposed for efficient tunnel geometry characterization. The techniques discussed in this paper already have many industrial applications. This study reveals their potential to be adopted and further developed to serve ore and rock mass characterization for stope design. [ABSTRACT FROM AUTHOR]

Productivity in open pit operations in the mining industry is conditioned by the manual assignment of trucks by the dispatcher, who does not have the ability to find the optimal policy by himself, having many variables that consider. To this end, an MIP optimization model is proposed that considers the scheduling of a discretized operating shift in smaller stages that consider positions and capacities of available trucks, and congestion based on a differential speed based on the number of trucks in different sections of the transport route. The model seeks to prioritize the transfer of material to crushers and meet material goals during the planning horizon. Preliminary results indicate that it is possible to reduce the violation of the production plan by destination by 12% and increase productivity by 46% with respect to the state of the art of similar solutions. [ABSTRACT FROM AUTHOR]

Abstract Since the open-pit precedence-constrained production scheduling problem is an NP-hard problem, solving it is always a challenging task, especially from a long-term perspective because a mineral deposit containing millions of blocks would require several million precedence arcs as constraints, making the solution time grow exponentially and making a direct approach unfeasible. Therefore, different strategies have been employed since the 1960s to reduce the size of this problem, such as determining the ultimate pit limit, subdividing it into phases, segmenting the production scheduling problem into long-, mid-, and short-term plans, as well as aggregating blocks into clusters, thus significantly reducing the number of precedence arcs. Different modeling and clustering strategies have already been employed in an attempt to reduce the size of the mine sequencing problem, such as layer modeling, re-blocking, bench-phase clustering, or polygon (mining cut) clustering based on a similarity function. The mining cut clustering problem has been solved lately by machine learning and heuristics techniques, and this approach can also introduce operational constraints to the mine sequencing problem, such as equipment size, minimum pit width, and preferential mining direction. In this study, we propose a mining cut clustering model based on Mixed Integer Linear Programming (MILP). Then we solve it by an exact approach and by Constraint Programming (CP), analyzing the strengths and weaknesses of the Constraint Optimization Problem (COP) and Constraint Satisfaction Problem (CSP) techniques. Numerical experiments were carried out on the Bench 15 of the Newmanl dataset, demonstrating the superiority of the COP approach.

This work tackles the open pit planning problem in an optimal control framework. We study the optimality conditions for the so-called continuous formulation using Pontryagin's Maximum Principle, and introduce a new, semi-continuous formulation that can handle the optimization of a two-dimensional mine profile. Numerical simulations are provided for several test cases, including global optimization for the one-dimensional final open pit, and first results for the two-dimensional sequential open pit. Theses indicate a good consistency between the different approaches, and with the theoretical optimality conditions. [ABSTRACT FROM AUTHOR]

This article seeks to represent the step by step to obtain the economic valuation and the scheduling of a mining project, based on a hypothetical polymetallic deposit of Cu and Au, by applying the concepts of equivalent law to express the presence of the different metals in terms of a single mineral, the critical and marginal cut-off grade to define the economically viable limits of mining and the implementation of the DESWIK software package. [ABSTRACT FROM AUTHOR]

In open pit mines, the long-term scheduling defines how the mine should be developed. Uncertainties in geological attributes makes the search for an optimal scheduling a challenging problem. In this work, we provide a framework to account for uncertainties in the spatial distribution of grades in long-term mine planning using deep Q-Learning. Mining, processing and metallurgical constraints are accounted as restrictions in the reinforcement learning environment. Such environment provides a flexible structure to incorporate geometallurgical properties in production scheduling, as part of the block model. Geometric constraints (block precedence) and operational restrictions have been included as part of the agent-environment interaction. The effectiveness of the method is demonstrated in a controlled study case using a real multivariate drill-hole dataset, maximizing the net-present value of the project. The present framework can be extended and improved, to meet the particular needs and requirements of mining operations. We discuss on the current limitations and potential for further research and applications. [ABSTRACT FROM AUTHOR]

Abstract Mining in Brazil is one of the pillars that support its GDP (gross domestic product). Its execution requires technique and expertise. In a mining venture, the value chain drives the business to achieve its goals. Mine planning has a great influence on its performance, as it is through it that the organization is based to offer its products to the market and, consequently, the low compliance with the established premises will bring undesirable inconveniences. Within the planning, the short term is dedicated to operationalize the plans made possible by the long and medium term teams, in addition to attending to market variations. The indicators that control this process are of great importance, as an incorrect identification inserted in the various criteria that compose it can guide managers towards inefficient decision making. The objective of this study was, through lean methodology, to identify the main performance indicators that impact on the non-exception of the mining plan measured by the adherence and compliance indicators. In this method, the main causes of non-adherence and compliance with the mining plan were identified, enabling short and medium-term actions that leveraged the indicators. This study leveraged the average adherence and compliance by 17% and 54.9%, respectively, exceeding the target set for 6.5% and 49.2% respectively.

A critical step in planning an open-pit operation corresponds to the design of ramps required to access the different sectors and levels. This design is very complicated because the ramps affect the excavation's shape, therefore, its economic value. Thus, planners generate contours to be used as reference for the design. These contours (or equivalently the volume they contain) are generated by mathematical models that aim to optimize the economic value that is contained in them. Then, through Computer-Aided Design software, planners manually draw the operational design that, hopefully, retrieves as much value as possible from the reference volumes and is operationally feasible. Unfortunately, this manual process does not ensure the quality of the design, leading to results that are not optimal and are highly dependent on the engineer's expertise. This article presents a methodology that starts from the same reference volume that the planner uses to generate a mine design automatically. It works in two steps. Firstly, it uses integer programming to generate a new discretized contour but containing enough space for ramps. Secondly, it utilizes a computer algorithm to transform the discretized profile into an operational pit design that complies with the mine design's geometrical constraints. To study the proposed methodology's applicability, we considered three cases with their corresponding reference pushbacks and used our approach to create 15 different operational designs (in total). In two of the three cases, the methodology generated profiles that were, at worst, within less than 2 % deviation in value and tonnage. In the third case, the loss in economic value was more than 11 % ; however, this performance was equivalent to a manual design produced by an engineer. [ABSTRACT FROM AUTHOR]

Stope design is an important part of mine planning, and it aims to balance ore recovery, ore dilution, and production costs without compromising the safety aspects. This paper summarizes the main results from the research, which aims to introduce new techniques to describe the ore body and surrounding rock mass at the tunnel face prior to stope excavation. The research comprises a literature review and a survey among mining professionals to assess current stope design practices. The study identifies geotechnical data, software improvements, and integration of design into mine planning as the most critical areas for improvement. The empirical part of the study proposes new techniques for fast data acquisition. The laser-induced breakdown spectrometry (LIBS) technique is developed for measurements at the tunnel face and from core boxes to provide mineralogical and geometallurgical data. Ground-penetrating radar (GPR) studies are conducted to improve discontinuity characterization, and rapid photogrammetric methods are proposed for efficient tunnel geometry characterization. The techniques discussed in this paper already have many industrial applications. This study reveals their potential to be adopted and further developed to serve ore and rock mass characterization for stope design.

This paper presents the machine learning (ML) method, a novel approach that could be a profitable idea to optimize fleet management and achieve a sufficient output to reduce operational costs, by diminishing trucks’ queuing time and excavators’ idle time, based on the best selection of the fleet. The performance of this method was studied at the Zenouz kaolin mine to optimize the type of loader and the number of trucks used to supply the processing plant’s ore demands. Accordingly, five years’ data, such as dates, weather conditions, number of trucks, routes, loader types, and daily hauled ore, were collected, adapted, and processed to train the following five practical algorithms: linear regression, decision tree, K-nearest neighbour, random forest, and gradient boosting algorithm. By comparing the results of the algorithms, the gradient boosting decision tree algorithm was determined to be the best fit and predicted test data values with 85% accuracy. Subsequently, 11,322 data were imported into the machine as various scenarios and daily hauled minerals as output results were predicted for each working zone individually. Finally, the data which had the minimum variation from the selected required scheduled value, and its related data concerning loader type and the number of demanded trucks, were indicated for each day of the working year.

Safety is a primary consideration in underground mining operations. Accidents could cause fatalities, injuries, and permanent disability of labourers, as well as irreparable financial and reputational losses. As an underground mine consists of many workspaces distributed in various zones, the selection of a junction location will be significant for timely evacuation of miners from different areas. This paper aims to determine the optimal location of the junction point for emergency evacuation in the underground network. The location problem is formulated as a MiniMax problem. Three methods are presented: Elzinga–Hearn algorithm, a three-dimensional extension of the Elzinga–Hearn algorithm, and the Welzl algorithm. The proposed methods are fully implemented in Python, and their functionality is demonstrated by conducting various case studies in 2D and 3D. The case studies showed that the proposed approaches could be used to determine junction point(s) in an underground network to serve as an evacuation location. [ABSTRACT FROM AUTHOR]

Open-pit mines are surface excavations created to extract valuable material which, in most cases, is located near the surface. Pushbacks are connected regions of a mine with enough working area to support the mining operation over a defined period. Pushbacks designed without taking into consideration haulage ramps are defined here as semi-practical pushbacks. We introduce a new optimisation model for semi-practical pushbacks that accounts for operational conditions: minimum operational width and connectivity within the blocks that compose the pushbacks. Additionally, we propose an algorithm that uses a Sliding Window Heuristic, variable bounding, and other preprocessing routines to obtain solutions with less than 10% optimality gap for mining instances ranging between 30,000 to 50,000 blocks. [ABSTRACT FROM AUTHOR]

Noise emissions are a significant environmental impact caused by the mining industry in all technological phases of surface mining, mineral processing, and waste disposal. This paper presents the role of noise impact assessment and control in large-scale surface mining operations. Mine planning develops the model of mining operations, ore excavation, and waste dumping scheduling and processing rates, including spatial distribution of mining activities. Such a level of mine planning requires an environmental impact assessment study. This can be achieved by applying noise impact assessment models. The described approach can be used to verify the effectiveness of the proposed protection measures to reduce or eliminate the identified negative impacts. This paper presents a case study of environmental noise impact assessment and control at the Serbia Zijin Copper DOO Bor mine, encompassing the analysis of the noise protection measures efficiency within the planning of large-scale mining operations at the open-pit mine Veliki Krivelj. [ABSTRACT FROM AUTHOR]

Mining in Brazil is one of the pillars that support its GDP (gross domestic product). Its execution requires technique and expertise. In a mining venture, the value chain drives the business to achieve its goals. Mine planning has a great influence on its performance, as it is through it that the organization is based to offer its products to the market and, consequently, the low compliance with the established premises will bring undesirable inconveniences. Within the planning, the short term is dedicated to operationalize the plans made possible by the long and medium term teams, in addition to attending to market variations. The indicators that control this process are of great importance, as an incorrect identification inserted in the various criteria that compose it can guide managers towards inefficient decision making. The objective of this study was, through lean methodology, to identify the main performance indicators that impact on the non-exception of the mining plan measured by the adherence and compliance indicators. In this method, the main causes of non-adherence and compliance with the mining plan were identified, enabling short and medium-term actions that leveraged the indicators. This study leveraged the average adherence and compliance by 17% and 54.9%, respectively, exceeding the target set for 6.5% and 49.2% respectively. [ABSTRACT FROM AUTHOR]

Successful mine planning is necessary for the sustainability of mining activities. Since this process depends on many criteria, it can be considered a multi-criteria decision making (MCDM) problem. In this study, an integrated MCDM method based on the combination of the analytic hierarchy process (AHP) and the technique for order of preference by similarity to the ideal solution (TOPSIS) is proposed to select the optimum mine planning in open-pit mines. To prove the applicability of the proposed method, a case study was carried out. Firstly, a decision-making group was created, which consists of mining, geology, planning engineers, investors, and operators. As a result of studies performed by this group, four main criteria, thirteen sub-criteria, and nine mine planning alternatives were determined. Then, AHP was applied to determine the relative weights of evaluation criteria, and TOPSIS was performed to rank the mine planning alternatives. Among the alternatives evaluated, the alternative with the highest net present value was selected as the optimum mine planning alternative. It has been determined that the proposed integrated AHP-TOPSIS method can significantly assist decision-makers in the process of deciding which of the few mine planning alternatives should be implemented in open-pit mines. [ABSTRACT FROM AUTHOR]

Environmental issues and sustainability are currently being discussed and studied in several areas of mining technology; combining these issues with improved mining operation and management is part of strategic mine planning. Waste management plays an important role in this process, as an alternative way of minimising environmental impacts and achieving more attractive economic scenarios, such as backfilling the pit. This study aimed to evaluate the application of the multi-stage dumping sequence (MSDS) in conjunction with in-pit deposition strategy for a phosphate mine providing general orientations and limits of applicability of the method. The MSDS makes use of temporary waste dumps which gives operational flexibility regarding waste management while reducing the Net Present Cost (NPC) (up to 8% in this study) compared with the traditional and sometimes untouchable rule of no re-handling approach during waste disposal. [ABSTRACT FROM AUTHOR]

This paper presents the machine learning (ML) method, a novel approach that could be a profitable idea to optimize fleet management and achieve a sufficient output to reduce operational costs, by diminishing trucks' queuing time and excavators' idle time, based on the best selection of the fleet. The performance of this method was studied at the Zenouz kaolin mine to optimize the type of loader and the number of trucks used to supply the processing plant's ore demands. Accordingly, five years' data, such as dates, weather conditions, number of trucks, routes, loader types, and daily hauled ore, were collected, adapted, and processed to train the following five practical algorithms: linear regression, decision tree, K-nearest neighbour, random forest, and gradient boosting algorithm. By comparing the results of the algorithms, the gradient boosting decision tree algorithm was determined to be the best fit and predicted test data values with 85% accuracy. Subsequently, 11,322 data were imported into the machine as various scenarios and daily hauled minerals as output results were predicted for each working zone individually. Finally, the data which had the minimum variation from the selected required scheduled value, and its related data concerning loader type and the number of demanded trucks, were indicated for each day of the working year. [ABSTRACT FROM AUTHOR]