Acoustic emission and machine learning for in situ monitoring of a gold–copper ore weakening by electric pulse

Abstract

The excessive energy consumption from the mining industry are currently receiving international attention. A promising method able to enhance significantly the comminution process efficiency worldwide is by using electric pulse fragmentation treatment. However, to insure a minimum energy consumption in real scale operation, an online process monitoring is of utmost importance. This work presents an in situ and real-time monitoring method by combining acoustic emission sensor and advanced machine learning algorithms. The proposed method was developed on a gold-copper ore in well-controlled single stone experiments and in semi-continuous process, reproducing a real industrial environment. In single stone experiment, the pulse energies was varied from 200 to 750 J leading to three weakening behaviours; no discharge, surface discharge and fragmentation. Acoustic signals for these categories have been decomposed with wavelet packets, and sub-band energies have been chosen as features. Then, only the most informative features were selected via standard linear principal component analysis. Finally, the classification was performed via a traditional support vector machine. In the semi-continuous experiments, an unsupervised learning method was used for classification task based on Laplacian support vector machine. Results for single stone tests showed accuracy above 90% for the three categories. For semi-continuous tests, we demonstrated that the unsupervised classification can be applied efficiently to estimate the amount of weakening of the passed through ore. We are very confident that the proposed method can be easily industrialised to monitor in situ and in real-time the electric discharge process within a comminution operation.