Estimation of copper grade from the flotation froth using image analysis and machine vision

Document Type : Research Article


1 bResearch Department of Mining and hydrometallurgy, Mineral Processing Research Institute, Academic Center for Education, Culture & Research, Tarbiat Modares University, Tehran, Iran

2 Assistant Professor, Institute of Mineral Processing, ACECR at Tarbiat Modares


By observing froth surface, operators can usually determine the metallurgical parameters (grade and recovery) of the flotation process, but it is associated with many problems such as the inability to continuously monitor significant differences with operation results, and various observations by different persons. In this study, the physical and structural properties of flotation froth images have been investigated to determine the metallurgical parameters of copper oxide ore. Pre-processing and processing of images obtained from the flotation froth were studied using artificial neural networks in the MATLAB program. The estimated grade was compared with the actual grade to check the accuracy of the system. Studies show that when the three color characteristics (red, green, and blue colors) of images are used to determine the grade of froth, these three characteristics alone are not sufficient to estimate the grade, and the amount of error rate is 21.7%. When factors of the three color characteristics and their standard deviation were studied for estimating the grade, the error rate reached 8.7%. Finally, the simultaneous studies of 11 characteristics including color channels, their standard deviation and haralic characteristics (entropy, contrast, energy, correlation, and gradient-density) showed a very good similarity between the actual grade and their predicted grade. The calculated error rate was greatly reduced to 2.3%. The method of work was including of the picture taking of froth flotation, pre-processing and processing of images, characteristics extraction, system training, testing and validation, and finally, the results showed that the amount of froth grade in the online form.


Main Subjects

[1] B. Shean, J. Cilliers, A review of froth flotation control, International Journal of Mineral Processing, 100(3-4) (2011) 57-71.
[2] G. Bonifazi, S. Serranti, F. Volpe, R. Zuco, Characterisation of flotation froth colour and structure by machine vision, Computers & Geosciences, 27(9) (2001) 1111-1117.
[3] M. Massinaei, Estimation of metallurgical parameters of flotation process from froth visual features, International Journal of Mining and Geo-Engineering, 49(1) (2015) 75-81.
[4] D. Moolman, J. Eksteen, C. Aldrich, J. Van Deventer, The significance of flotation froth appearance for machine vision control, International Journal of Mineral Processing, 48(3-4) (1996) 135-158.
[5] X.-M. Mu, J.-P. Liu, W.-H. Gui, Z.-H. Tang, C.-H. Yang, J.-Q. Li, Machine vision based flotation froth mobility analysis, in:  Proceedings of the 29th Chinese Control Conference, IEEE, 2010, pp. 3012-3017.
[6] A. Mehrabi, N. Mehrshad, M. Massinaei, Machine vision based monitoring of an industrial flotation cell in an iron flotation plant, International Journal of Mineral Processing, 133 (2014) 60-66.
[7] K. Jani, H. Jari, L. Martti, H. Heikki, J. Miettunen, Image Analysis Based Control of Copper Flotation, IFAC Proceedings Volumes, 38(1) (2005) 229-234.
[8] J. Liu, W. Gui, Z. Tang, H. Hu, J. Zhu, Machine vision based production condition classification and recognition for mineral flotation process monitoring, International Journal of Computational Intelligence Systems, 6(5) (2013) 969-986.
[9] J. Kaartinen, J. Hätönen, H. Hyötyniemi, J. Miettunen, Machine-vision-based control of zinc flotation—a case study, Control Engineering Practice, 14(12) (2006) 1455-1466.
[10] L. Jinping, G. Weihua, T. Zhaohui, Flow velocity measurement and analysis based on froth image SIFT features and Kalman filter for froth flotation, Turkish Journal of Electrical Engineering and Computer Science, 21(Sup. 2) (2013) 2378-2396.
[11] Bai Y, J. Wang, and X. Hu, Froth Recognition Based on Machine Vision for Monitoring Coal Flotation Process, Journal of Residuals Science & Technology(2016).
[12] J. Kaartinen, H. Hyötyniemi, Determination of ore size distribution with image analysis, in:  IASTED International Conference on Intelligent Systems and Control, Salzburg, Austria, June 25-27, 2003, IASTED, ACTA Press, 2003, pp. 406-411.
[13] A. Jahedsaravani, M. Marhaban, M. Massinaei, Prediction of the metallurgical performances of a batch flotation system by image analysis and neural networks, Minerals Engineering, 69 (2014) 137-145.
[14] C. Marais, C. Aldrich, The estimation of platinum flotation grade from froth image features by using artificial neural networks, Journal of the Southern African Institute of Mining and Metallurgy, 111(2) (2011) 81-85.
[15] J. Kaartinen, A. Tolonen, Utilizing 3D height measurement in particle size analysis, IFAC Proceedings Volumes, 41(2) (2008) 3292-3297.
[16] Saeedzadeh Fatemeh, Mohammadnejad Niazi Saeed, Sahib Mahmoud Reza, Ebadi Hamid, Mokhtarzadeh Mehdi, Extracting, optimizing and investigating the effect of different image texture information on large-scale image classification, NATIONAL GEOMATICS CONFERENCE, Volume 22, (2015) (in Persian)
[17] C.-H. Yang, C.-H. Xu, X.-m. Mu, K.-J. Zhou, Bubble size estimation using interfacial morphological information for mineral flotation process monitoring, Transactions of Nonferrous Metals Society of China, 19(3) (2009) 694-699.
[18] P. Holtham, K. Nguyen, On-line analysis of froth surface in coal and mineral flotation using JKFrothCam, International Journal of Mineral Processing, 64(2-3) (2002) 163-180.
[19] Determination of mineral grade using MLP neural network and image processing technique, Iranian Journal of Mining Engineering(IRJME),3  (6) ( 2008) 67-73 (in Persian).