Estimation of froth flotation recovery and collision probability based on operational parameters using an artificial neural network

Abstract

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 (R ²) 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.

Keywords

flotation / recovery / collision / probability / neural networks

References

[1] Derjaguin B.V., Dukhin S.S. Theory of flotation of small and medium-size particles. Trans. Inst. Min. Metall., 1961, 70, 221.

[2] H.J. Schulze, Physico-chemical Elementary Processes in Flotation: An Analysis from the Point of View of Colloid Science Including Process Engineering Considerations, Elsevier, 1984, p.28.

[3] Ralston J., Fornasiero D., Hayes R. Bubble-particle attachment and detachment in flotation. Int. J. Miner. Process., 1999, 56(1–4): 133.

[4] Schubert H. On the turbulence-controlled microprocesses in flotation machines. Int. J. Miner. Process., 1999, 56(1–4): 257.

[5] B.V. Derjaguin and S.S. Dukhin, Kinetic theory of the flotation of fine particles, [in] Proceedings of the 13th International Mineral Processing Congress, Warsaw, 1979, p.21.

[6] Hu Y., Qiu G., Wang D. The studies of carrier flotation of ultrafine wolframite. Trans. Nonferrous Met. Soc. China, 1994, 2, 44.

[7] Lafuma F., Wong K., Cabane B. Bridging of colloidal particles through adsorbed polymers. J. Colloid Interface Sci., 1991, 143(1): 9.

[8] Valioulis I.A., List E.J. Collision efficiencies of diffusing spherical particles: hydrodynamic, van der Waals and electrostatic forces. Adv. Colloid Interface Sci., 1984, 20, 1.

[9] L.J. Warren, Ultrafine particles in flotation, [in] Principles of Mineral Flotation, Victoria, 1984, p.185.

[10] Crawford R., Ralston J. The influence of particle size and contact angle in mineral flotation. Int. J. Miner. Process., 1988, 23, 1.

[11] Wasserman P.D. Neural Computing: Theory and Practice, 1989 New York, Van Nostrant Reinhold

[12] Beale R.T., Adam H. Neural Computing: An Introduction, 1990 Bristol, Van Nostrant Reinhold

[13] Acharya C., Mohanty S., Sukla L.B., Misra V.N. Prediction of sulphur removal with Acidithiobacillus sp. using artificial neural networks. Ecol. Modell., 2006, 190, 223.

[14] Jorjani E., Chehreh Chelgani S., Mesroghli Sh. Prediction of microbial desulfurization of coal using artificial neural networks. Miner. Eng., 2007, 20, 1285.

[15] Jorjani E., Chehreh Chelgani S., Mesroghli Sh. Application of artificial neural networks to predict chemical desulfurization of Tabas coal. Fuel, 2008, 87, 2727.

[16] Chelgani S. C., Jorjani E. Artificial neural network prediction of Al₂O₃ leaching recovery in the Bayer process at the Jajarm alumina plant (Iran). Hydrometallurgy, 2009, 97, 105.

[17] Venkoba Raoa B., Gopalakrishna S.J. Hardgrove grindability index prediction using support vector regression. Int. J. Miner. Process., 2009, 91(1–2): 55.

[18] Chehreh Chelgani S., Hower J.C., Jorjani E., et al. Prediction of coal grindability based on petrography, proximate and ultimate analysis using multiple regression and artificial neural network models. Fuel Process. Technol., 2008, 89, 13.

[19] Cilek E.C. Application of neural networks to predict locked cycle flotation test results. Miner. Eng., 2002, 15, 1095.

[20] Labidi J., Pèlach M.A., Turon X., Mutjé P. Predicting flotation efficiency using neural networks. Chem. Eng. Process., 2007, 46, 314.

[21] Clifford P., Lloyd M., Zhang P. Technology research improves phosphate economics. Miner. Eng., 1998, 98, 46.

[22] Rodrigues W.J., Filho L.S.L., Masini E.A. Hydrodynamic dimensionless parameters and their Influence on flotation performance of coarse particles. Miner. Eng., 2001, 14, 1047.

[23] Roscoe R. The viscosity of suspensions of rigid spheres. Br. J. Appl. Phys., 1952, 3, 267.

[24] Girgin E.H., Do S., Gomez C.O., Finch J.A. Bubble size as a function of impeller speed in a self-aeration laboratory flotation cell. Miner. Eng., 2006, 19, 201.

[25] Rodrigues R.T., Rubio J. New basis for measuring the size distribution of bubbles. Miner. Eng., 2003, 16, 757.

[26] Yoon R.H. The role of hydrodynamic and surface forces in bubble-particle interaction. Int. J. Miner. Process., 2000, 58(1–4): 129.

[27] Hakeem M.A., Kamil M., Arman I. Prediction of temperature profiles using artificial neural networks in a vertical thermosiphon reboiler. Appl. Therm. Eng., 2008, 28, 1572.

[28] Afkhami A., Abbasi-Tarighat M., Bahramb M. Artificial neural networks for determination of enantiomeric composition of α-phenylglycine using UV spectra of cyclodextrin host-guest complexes. Comparison of feed-forward and radial basis function networks. Talanta, 2008, 75, 91.

[29] Farshad F.F., Garber J.D., Lorde J.N. Predicting temperature profiles in producing oil wells using artificial neural networks. Eng. Comput., 2000, 17, 735.

[30] Razmi-Rad E., Ghanbarzadeh B., Mousavi S.M., et al. Prediction of rheological properties of Iranian bread dough from chemical composition of wheat flour by using artificial neural networks. J. Food Eng., 2007, 81, 728.

[31] Alonso-Rodriguez A. Forecasting economic magnitudes with neural network models. Int. Adv. Econ. Res., 1999, 5(4): 496.

[32] Landau S., Brian S.E. A Handbook of Statistical Analyses Using SPSS, 2004 New York, Chapman Hall/Crc, 113.

[33] Smith K. Neural Networks in Business: Techniques and Applications, 2002 Hershey, Idea Group Publishing

[34] Demuth H., Beale M. Neural Network Toolbox for Use with MATLAB, 2002 Natick, The Mathworks Inc., 154.

[35] Aldrich C. Exploratory Analysis of Metallurgical Process Data with Neural Networks and Related Methods, 2002 Amsterdam, Elsevier, 5.