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

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