TECHICAL NOTE

Neural networks to estimate bubble diameter and bubble size distribution of flotation froth surfaces

R.H. Estrada-Ruiz; R. Pérez-Garibay

Cinvestav-IPN (Unidad Saltillo), Ramos Arizpe, Coahuila, México

SYNOPSIS

This work analyses a new approach to estimates bubble size distribution of froth surfaces using artificial neural networks (ANN). Also, the robustness of ANN to interpret images with illumination perturbations, produced by light problems or dirt attached to the window of the video camera is evaluated. The experimental work was carried out in a laboratory flotation column, instrumented with an image acquisition system. The images were processed making use of a perceptron model with a hidden layer, sigmoidal transfer function and unitary bias, and the ANN trained with a back propagation algorithm. The results of validation show that ANN are reliable for learning and producing generalized predictions of the froth mean bubble diameter and bubble size distribution, when the model is trained using a database that contains information on the illumination intensity.

Keywords: image analysis, neural networks, bubble diameter, bubble size distribution

“Full text available only in PDF format”

References

1. SYMONDS, P.J. and DE JAGER, G. A technique for automatically segmenting images of the surface froth structures that are prevalent in flotation cells. Proc. of the 1992 South African Symposium on Communications and Signal Processing, University of Cape Town, Rondebosch, South Africa, 1992. pp. 111-115.         [ Links ]

2. WOODBURN, E.T., AUSTIN, L.G., and STOCKTON, J.B. A froth based flotation kinetic model, Trans. I ChemE, 1994. 72A, pp. 211-56.         [ Links ]

3. MOOLMAN, D.W., EKSTEEN, J.J., ALDRICH, C., and VAN DEVENTER, J.S.J. The significance of flotation froth appearance for machine vision control. Int. J. Mineral Processing, vol. 48, 1996. pp. 135-158.         [ Links ]

4. HARGRAVE, J.M. AND HALL, S.T. Diagnosis of concentrate grade and mass flow rate in tin flotation from color and surface texture analysis. Minerals Eng., vol. 10, no. 6, 1997. pp. 613-621.         [ Links ]

5. HOLTHAM, P.N. and NGUYEN, K.K. On-line analysis of froth surface in coal and mineral flotation using JKFrothCam. Int. J. Mineral Processing, vol. 64, 2002. pp. 163-180.         [ Links ]

6. THOMSON, S., FUETEN, F., and BOCKUS D. Mineral identification using artificial neural networks and the rotating polarizer stage, Computers & Geosciences, vol. 27, 2001. pp. 1081-1089.         [ Links ]

7. GUPTA, S., LIU P-H., SVORONOS, S.A., SHARMA, R., ABDEL-KHALEK, N.A., CHENG, Y., and EL-SHALL, H. Hybrid first-principles/neural networks model for column flotation. AIChe Journal. AIChe Journal, vol. 45, no. 3, 1999. pp.557-566.         [ Links ]

8. SHUMSHER-RUGHOOPUTH, H.C. and DAHARAM-VIR, S.D. Neural network process vision systems for flotation process. Neural network process vision systems, vol. 31, no. 3/4, 2002. pp. 529-535.         [ Links ]

9. GRAU, R.A. and HEISKANEN, K. Visual techniquefor measuring bubble size in flotation machines. Minerals Engineering, 2002. pp. 507-513.         [ Links ]

10. HERNÁNDEZ-AGUILAR, J.R., COLEMAN, R.G., GOMEZ, C.O., and FINCH, J.A.A. comparation between capilarity and imaging techniques for sizing bubbles in flotation systems. Mineral Engineering, vol. 17, 2004. pp. 53-61.         [ Links ]