Concentrate Grade Prediction in an Industrial Flotation Column Using Artificial Neural Network

Today, column flotation has become an acceptable means of froth flotation for a fairly broad range of applications, in particular the cleaning of sulfides. Even after having been used for several years in mineral processing plants, the full potential of the column flotation process is still not fully exploited. There is no prediction of process performance for the complete use of available control capabilities. The online estimation of grade usually requires a significant amount of work in maintenance and calibration of on-stream analyzers in order to maintain good accuracy and high availability. These difficulties and the high cost of investment and maintenance of these devices have encouraged the approach of prediction of metal grade. Therefore, advanced new methods such as Artificial Neural Network (ANN) must be employed. In this paper, a new approach has been proposed for metallurgical performance prediction in flotation columns using ANN. Furthermore, a case study is carried out in an industrial Metso Minerals CISA flotation column (4 m in diameter and 12 m in height) at the Sarcheshmeh Copper Concentrator Plant. The values of Cu and Mo grades in the flotation feed and final concentrate, froth height, wash water, and the air and non-floated fraction flow rates were used for the simulation by ANN. Feed-forward ANNs with 3-13-6-1 and 4-4-8-1 arrangements were used to estimating Cu and Mo grades, respectively. The correlation coefficient values for the training and testing sets for Cu and Mo grades were 0.94 and 0.93 and 0.98 and 0.97, respectively. The results discussed in this paper indicate that the proposed model can be used to predict the Cu and Mo grades with a reasonable error. Also, analysis demonstrates that prediction of grade for optimizing and controlling column flotation for a wide range of operating conditions is highly effective.