Acoustic Sensing and Supervised Machine Learning for In Situ Classification of Semi-Autogenous (SAG) Mill Feed Size Fractions Using Different Feature Extraction Techniques

The harsh and hostile internal environment of semi-autogenous (SAG) mills renders real-time monitoring some critical variables practically unmeasured. Typically, feed size fractions are known to cause mill fluctuations impede the consistent processing behaviour ores. There is, therefore, need for continuous parameters optimal operation. In this paper, an acoustic-based sensing method is employed estimate, in real time, a snapshot different presented laboratory-scale SAG mill. Employing MATLAB 2020b programme, acoustic signal processed using various transform techniques such as power spectral density estimate (PSDE) by Welch’s method, discrete wavelet (DWT), packet (WPT), empirical mode decomposition (EMD), variational (VMD). Different fractional bandpowers obtained from PSDE spectrum, while statistical root mean square values further extracted DWT, WPT, EMD, VMD feature vectors. features used input machine-learning classification algorithms predictions. fraction predictions evaluated performance indicators confusion matrix accuracy, precision, sensitivity F1 score. study showed that extraction conjunction with Support Vector Machine (SVM), linear discriminant analysis (LDA), ensemble subclass machine learning demonstrated improved predicting variations.