Machine Learning Algorithms for Semi-Autogenous Grinding Mill Operational Regions’ Identification

Abstract

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.

Prediction of energy consumption in grinding using artificial neural networks to improve the distribution of fragmentation size [Predicción del consumo de energía en la molienda utilizando redes neuronales artificiales para mejorar la distribución del tamaño de la fragmentación]

“…et al, (2021). Furthermore, these networks can identify patterns and non-linear relationships between input variables and energy consumption, which can help discover new control and optimization strategies (López et al, 2023). Otsuki and Jang (2022) in their research use predictive neural networks to predict particle size distributions (PSD) in size reduction operations.…”

Maximum Likelihood Estimation for an SAG Mill Model Utilizing Physical Available Measurements

“…This study, described in [41], focuses on the estimation of SAG mill states using a simplified model, emphasizing the use of commonly available measurements not typically utilized. For SAG mills, recent works have concentrated on the application of neural networks and machine learning techniques to estimate mill throughput or identify operational regions within the SAG mill, primarily for control purposes (see [13], [26] and the references therein). The comparative study presented in [13] focuses on state estimation techniques for control, particularly modern predictive control.…”