Saeed Chehreh Chelgani, Behzad Shahbazi, and Bahram Rezai, Estimation of froth flotation recovery and collision probability based on operational parameters using an artificial neural network, Int. J. Miner. Metall. Mater., 17(2010), No. 5, pp. 526-534. https://doi.org/10.1007/s12613-010-0353-1
Cite this article as:
Saeed Chehreh Chelgani, Behzad Shahbazi, and Bahram Rezai, Estimation of froth flotation recovery and collision probability based on operational parameters using an artificial neural network, Int. J. Miner. Metall. Mater., 17(2010), No. 5, pp. 526-534. https://doi.org/10.1007/s12613-010-0353-1
Saeed Chehreh Chelgani, Behzad Shahbazi, and Bahram Rezai, Estimation of froth flotation recovery and collision probability based on operational parameters using an artificial neural network, Int. J. Miner. Metall. Mater., 17(2010), No. 5, pp. 526-534. https://doi.org/10.1007/s12613-010-0353-1
Citation:
Saeed Chehreh Chelgani, Behzad Shahbazi, and Bahram Rezai, Estimation of froth flotation recovery and collision probability based on operational parameters using an artificial neural network, Int. J. Miner. Metall. Mater., 17(2010), No. 5, pp. 526-534. https://doi.org/10.1007/s12613-010-0353-1
An artificial neural network and regression procedures were used to predict the recovery and collision probability of quartz flotation concentrate in different operational conditions. Flotation parameters, such as dimensionless numbers (Froude, Reynolds, and Weber), particle size, air flow rate, bubble diameter, and bubble rise velocity, were used as inputs to both methods. The linear regression method shows that the relationships between flotation parameters and the recovery and collision probability of flotation can achieve correlation coefficients (R2) of 0.54 and 0.87, respectively. A feed-forward artificial neural network with 3-3-3-2 arrangement is able to simultaneously estimate the recovery and collision probability as the outputs. In testing stages, the quite satisfactory correlation coefficient of 0.98 was achieved for both outputs. It shows that the proposed neural network models can be used to determine the most advantageous operational conditions for the expected recovery and collision probability in the froth flotation process.