Interdisciplinary barriers separating data scientists and geometallurgists have complicated systematic attempts to incorporate machine-learning into mine production management; however, experiences in excavating a vein-hosted gold deposit within the Alhué region of Chile have led to methodological advances, which is the subject of the current paper. These deposits are subject to several challenges, from increasing orebody complexity and decreasing gold grades to the significant geological uncertainty that is intrinsic to these systems. These challenges then translate to mineral processing, which is already dealing with increased environmental and technological constraints. Geological uncertainty causes stockout risks that can be mitigated by the approach that is developed within this paper, which features alternate operational modes and related control strategies. A digital twin framework based on discrete event simulation (DES) and a customized machine-learning (ML) model is proposed to incorporate geological variation into decision-making processes, including the setting of trigger point that induces mode changes. Sample calculations that were based on a simulated processing plant that was subject to mineralogical feed changes demonstrated that the framework is a valuable tool to evaluate and mitigate the potential risks to gold mineral processing performance.

The Alhué deposit (Melipilla, Chile) is an example of a hydrothermal Au-Ag-Zn(-Pb) vein system hosted within the volcanic rocks of the Las Chilcas Formation. The dominant ore minerals observed are free electrum and native gold associated with silver sulfosalts, and with magnetite and base metal sulphides, including pyrite +/− sphalerite-galena-chalcopyrite. The alteration assemblage in the veins mainly consists of quartz epidote-chlorite-actinolite with lesser smectite, amphibole, and calcite-kaolinite-garnet. Mineralized veins also contain variable amounts of base metals, some of which (e.g., copper and iron) are considered harmful to the extraction of precious metals. Iron and especially copper minerals are known cyanide consumers; ore type classification schemes that do not consider the detrimental effects of such mineralogy or process elements can ultimately result in metal losses from ore feed restrictions, as well as spikes in cyanide consumption and higher operating costs. Mineralogical and geological variation can nonetheless be managed by applying alternating modes of operation as demonstrated in this paper; the decision to switch between modes is governed by current and forecasted stockpile levels feeding into the process. Simulations based on experiences at the Alhué deposit are provided that demonstrate the importance of standardized operational modes and their potential impact on cyanide consumption control.

The control of chromite feeds is supported by alternating modes of operation that respond to imbalances in feed stockpiles. Conventional classifications of chromite relate to its end uses: metallurgical (with high Cr₂O₃ content and Cr:Fe ratio close to 3, to produce ferrochrome), chemical and refractory. However, natural chromite is represented broadly as (Fe,Mg)O⋅(Cr,Al,Fe)₂O₃ to illustrate the common replacement of Fe²⁺ by Mg²⁺, and Cr³⁺ by Al³⁺ and Fe³⁺. Indeed, the variation in chromite characteristics is problematic for integrated management, but can be handled through continuous improvement projects that apply process mineralogy and well-known quantitative methods. Sample calculations have been included within this paper to demonstrate the importance of standardised operational modes, and their potential impact on chromite processing.