A Comparative Study on Supervised Machine Learning Algorithms for Copper Recovery Quality Prediction in a Leaching Process

Abstract

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.

Random forest for generating recommendations for predicting copper recovery by flotation

“…La industria minera ha evolucionado hacia la I4.0, que incluye características como automatización completa, flexibilidad multidisciplinaria, escalabilidad, agilidad y resiliencia [4,5]. En este contexto, los sistemas de soporte a la decisión en la producción industrial de cobre están siendo integrados a herramientas computacionales que respaldan la toma de decisiones en diversas tareas [6,7].…”

“…El presente trabajo se centra en la generación de un modelo predictivo para la variable dependiente Y, que representa el diámetro de Sauter (D32), en el proceso de flotación. Este modelo se basa en una metodología que integra la preparación y comprensión de los datos, el entrenamiento con el algoritmo Random Forest (RF), la validación del modelo y la interpretación de resultados, así como la generación de recomendaciones dirigidas al operador de la máquina de flotación [4]. A través del análisis de datos, buscamos identificar patrones y anticipar las mejores condiciones de separación de minerales, lo que proporciona una base sólida para la toma de decisiones informada, contribuyendo así a mejorar la eficacia y reducir los costos operativos [5].…”

Smart Manufacturing in Mining. Adopting Machine Learning to Improve a Copper Milling Process

“…The article presents a number of predictive techniques and a methodology to cope with datasets from operations and a method to get optimum models. Flores and Leiva (2021) address the use of AI techniques in order to optimize the industrialization of copper. The article develops a case in a mining operation, where they compared different models for predicting the recovery of copper by leaching using four data sets from the process.…”

Using ontological representation in the copper leaching domain for operation mode plan recommendation

“…But with the use of techniques such as leaching, production margins can be improved; in fact, it is estimated that around 20% of the world's copper is currently produced using the leaching process [12]. In Chile, heap leaching is mainly used for low-medium grade material (0.3 -0.7%), to process oxides and currently also secondary sulfides [3,12,13].…”

“…are considered. that allow calculating optimal operation time and amount of copper to be recovered [12,13]. These analytical models are formalized in mathematical formulas that are already established in the industry [15].…”