Copper mining activity is going through big changes due to increasing technological development in the area and the influence of industry 4.0. These changes, produced by technological context and more controls (e.g., environmental controls), are also becoming visible in Chilean mining. New regulations from the Chilean government and changes in the copper mining industry (such as a trend to underground mining) are fostering the search for better results in typical processes such as leaching. This paper describes an experience using artificial intelligence techniques, particularly random forest, to develop predictive models for copper recovery by leaching, using data from an enterprise present in northern Chile for more than 20 years. Two models, one of them with actual operational data and another one with data generated in a controlled environment (piling) are presented. Well-classified values of 98.90% for operational data and 98.72% for pile/piling data were obtained. The methodology devised for the study can be transferred to piling columns or piles with other characteristics, though the operation must focus on copper leaching. It can even be transferred to other leaching processes using another type of mineral, with proper adjustments.

The copper mining industry is increasingly using artificial intelligence methods to improve copper production processes. Recent studies reveal the use of algorithms, such as Artificial Neural Network, Support Vector Machine, and Random Forest, among others, to develop models for predicting product quality. Other studies compare the predictive models developed with these machine learning algorithms in the mining industry as a whole. However, not many copper mining studies published compare the results of machine learning techniques for copper recovery prediction. This study makes a detailed comparison between three models for predicting copper recovery by leaching, using four datasets resulting from mining operations in Northern Chile. The algorithms used for developing the models were Random Forest, Support Vector Machine, and Artificial Neural Network. To validate these models, four indicators or values of merit were used: accuracy (acc), precision (p), recall (r), and Matthew’s correlation coefficient (mcc). This paper describes the dataset preparation and the refinement of the threshold values used for the predictive variable most influential on the class (the copper recovery). Results show both a precision over 98.50% and also the model with the best behavior between the predicted and the real values. Finally, the obtained models have the following mean values: acc = 0.943, p = 88.47, r = 0.995, and mcc = 0.232. These values are highly competitive when compared with those obtained in similar studies using other approaches in the context.

The mining industry of the last few decades recognizes that it is more profitable to simulate model using historical data and available mining process knowledge rather than draw conclusions regarding future mine exploitation based on certain conditions. The variability of the composition of copper leach piles makes it unlikely to obtain high precision simulations using traditional statistical methods; however the same data collection favors the use of softcomputing techniques to enhance the accuracy of copper recovery via leaching by way of prediction models. In this paper, a predictive modeling contrasting is made; a linear model, a quadratic model, a cubic model, and a model based on the use of an artificial neural network (ANN) are presented. The model entries were obtained from operation data and data of piloting in columns. The ANN was constructed with 9 input variables, 6 hidden layers, and a neuron in the output layer corresponding to copper leaching prediction. The validation of the models was performed with real information and these results were used by a mining company in northern Chile to improve copper mining processes.

In wastewater treatment plants, the degradation of complex substances that contaminate water is carried out by microorganisms, which are fixed by a network formed by filamentous bacteria, creating large flocs that settle easily. However, the excessive growth of said bacteria causes a series of drawbacks such as the reduction of settling velocity, leakage of activated sludge with the effluent, and formation of supernatant, a phenomenon known as bulking. This research work seeks to develop and evaluate a procedure for the physical characterization of the flocs to determine the parameters that affect the settling velocity and thereby detect and control bulking. For this purpose, sedimentation and image analysis tests were carried out from wastewater from the Aguas Antofagasta treatment plant (Chile). The image analysis was performed with images captured from an optical microscope in two magnifications (100x and 50x), which were analyzed by marking each floc individually and characterized by an image processing software. Additionally, sedimentation tests were performed on columns (area of 74 (cm²) and height of 70 (cm)). As a result, an inversely proportional dependence was found on the settling velocity evaluated by the Vesilind equation in the zone of constant fall velocity with respect to the number of flocs connected per cluster, giving an estimate of the settling velocity depending on the number of flocs connected. This would allow predicting settling velocity with image analysis, taking into account that the problem of bulking is determined by the type of filamentous bacteria that causes it and the sedimentation process is affected in large part by local factors. It can be concluded through this study that as the number of flocs connected per cluster increases, the settling velocity decreases. This study provides wastewater treatment plants with a practical tool to determine sedimentation times and thus improve the quality of the treated water, avoiding problems of flocs leaking with the effluent. In addition, the image analysis itself allows rapid detection of the phenomenon of bulking and its severity.

This document presents a proposal for designing an expert system in the Gabriela Mistral Division’s crushing plant belonging to Codelco (Chile) with the objective of maximizing stacked tonnage, allowing the improvement of operational variables that directly interact with the crushing process. In addition, this study considers the impact that occurs in both the process and operational continuity regarding the standardization of the system. In the first stage, a survey and analysis of historic operation data was carried out, which allowed the definition of benchmarking indicators. Subsequently, both modalities of operation were compared, monitoring processed tonnage and detentions related to operational failures. As a result, significant differences were observed in the performance of the critical line operating with expert control, with a 55% reduction in the detentions referred to operational failures. Added to this is the benefit of low cost and improved quality as the control provides an analysis of the variables in reduced time intervals, which is superior to human control.

Autoclave leaching of zinc concentrate (Sphalerite) is an environmentally friendly process compared to roasting, which discharges pollutants into the atmosphere. Due to the amount of iron in the final product, a study is proposed to evaluate different reagents for eliminating iron from the autoclave outcome, minimizing Zn losses. The colloid formation, zinc losses, iron removal, phase separation stage characteristics (sedimentation and filtering), and reagent costs were used to evaluate six-iron precipitating reagents: CaO, Na₂CO₃, CaCO₃, NaOH, MgO, and Ca(OH)₂. CaO shows 99.5% iron removal and 87% zinc recovery. Although CaO was one of the reagents with significant zinc recovery, it presented operational difficulties in the filtration stage due to the high viscosity of the mixtures. Finally, Ca(OH)₂ is the reagent recommended due to its ease of use, zinc yield recovery, electrowinning efficiency, and iron precipitate filtration rate. Zinc recovery was above 80%, while the iron concentration in the solution was below 50 ppm.