Pulp Chemistry Variables for Gaussian Process Prediction of Rougher Copper Recovery

Insight about the operation of froth flotation through modelling has been in existence since early 1930s. Irrespective numerous industrial models that have developed over years, metallurgical outputs often do not involve pulp chemistry variables. As such, this work investigated influence variables (pH, Eh, dissolved oxygen and temperature) on prediction performance rougher copper recovery using a Gaussian process regression algorithm. Model assessed with linear correlation coefficient (r), root mean square error (RMSE), absolute percentage (MAPE) scatter index (SI) indicated are essential predicting recovery, obtaining r values > 0.98, RMSE < 0.32, MAPE 0.20 SI 0.0034. RNCA feature weights reveal relevance order pH Eh temperature.