Energy consumption represents a significant operating expense in the mining and minerals industry. Grinding accounts for more than half of the mining sector’s total energy usage, where the semi-autogenous grinding (SAG) circuits are one of the main components. The implementation of control and automation strategies that can achieve production objectives along with energy efficiency is a common goal in concentrator plants. However, designing such controls requires a proper understanding of process dynamics, which are highly complex, coupled, and have non-deterministic components. This complex and non-deterministic nature makes it difficult maintain a set-point for control purposes, and hence operations focus on an optimal control region, which is defined in terms of desirable behavior. This paper investigates the feasibility of employing machine learning models to delineate distinct operational regions within in an SAG mill that can be used in advanced process control implementations to enhance productivity or energy efficiency. For this purpose, two approaches, namely k-means and self-organizing maps, were evaluated. Our results show that it is possible to identify operational regions delimited as clusters with consistent results.

Energy consumption represents a high operational cost in mining operations. Ore size reduction stage is the main consumer in that process, where the Semiautogenous Mill (SAG) is one of the main components. The implementation of control and automation strategies that can achieve production goals along with energy efficiency are a common goal in concentrator plants; however, designing such controls requires a proper understanding of process dynamics which are highly complex. This work studies machine learning and deep learning strategies that can be used to generate models for predicting energy consumption, using key process variables. In particular, the application of K-Nearest Neighbors Regressor (KNN-reg), Polynomial Regression (PR), Support Vector Regression (SVR) and Long-Short Term Memory (LSTM) strategies for energy prediction over SAG mill process data is developed in order to identify configurations suitable to be implemented for real-time prediction integrated over industrial data infrastructures. All techniques are compared in terms of Root Mean Square Error (RMSE) where, although all the models achieved acceptable performance, best results were obtained by a LSTM implementation which yielded an error of less than 4% associated to energy prediction.

Mining is a critical industry that provides essential minerals and resources for modern society. Despite its benefits, the industry is also recognized as one of the most dangerous occupations, with geotechnical hazards being a primary concern. This study introduces the hazard recognition in underground mines application (HUMApp), a mobile application developed to enhance safety within underground mines by efficiently identifying geotechnical hazards, specifically focusing on roof falls. Employing a convolutional neural network (CNN), HUMApp achieved an accuracy of 90%, with recall and F1-score also reaching 90%, reflecting its high reliability in hazard detection. The application’s effectiveness was validated against expert assessments, showing significant agreement in identifying critical hazards. This validation highlights HUMApp’s potential to enhance proactive risk management in underground mining. This paper details each step of HUMApp’s development, from dataset preparation and model training to performance evaluation and application design, showcasing a scalable solution adaptable to various mining environments.