Berezniki Branch of Perm National Research Polytechnic University (Berezniki, Russia):

Varlamova S. A., Associate Professor, Candidate of Engineering Sciences, varlamovasa@mail.ru
Zatonsky A. V., Professor, Doctor of Engineering Sciences, zxenon@narod.ru

Perm National Research Polytechnic University (Perm, Russia):
Fedoseeva K. A., Postraduate

Machine vision methods are widely used in the industry. The paper considers the possibilities of using the machine vision technology to monitor potash ore flotation processes. It provides an overview of ready-made solutions for bubble edge detection. The widely used methods, however, are not suitable for the detection of cleaner flotation froth due to the specifics of its froth bed coloring and structure. A bubble detection method is described that is based on the distance between the specks generated by a point light source. The common algorithm is as follows: image conversion to grayscale, binarization, post-processing, and bubble separation using the ABCalgorithm. Particular attention is paid to establishing the proper binarization threshold, as it affects the quality of the final image significantly. A certain binarization threshold selection method is substantiated. The purpose of this work was to establish the sensitivity of the speck-based method for detecting the froth bed parameters to the binarization threshold. The study considers 20 experimental image sets obtained using different flotation machines, both with and without an additional light source. Binarization threshold selection profiles were generated for each frame. The respective profile analysis allowed identifying the best binarization thresholds for various types of flotation machines. As a result, specific methods for removing frames with low illumination and algorithms for determining the threshold binarization values for different types of flotation machines are proposed.

1. Mohr J., Park J.-H., Obermayer K. A computer vision system for rapid search inspired by surface-based attention mechanisms from human perception. Neural Networks. 2014. Vol. 60. pp. 182–193.
2. Yan H., Zhu J., Wang F., He D., Wang Q. Bayesian network-based technical index estimation for industrial flotation process under incomplete data. Proc. of the 32^nd Chinese control and decision conference (CCDC 2020). pp. 3354–3359. DOI: 10.1109/CCDC49329.2020.9164089.
3. Wang W., Liu W., Lang F., Wang F., Liu S. Froth image acquisition and enhancement on optical correction and retinex compensation. Minerals. 2018. Vol. 8, Iss. 3. DOI: 10.3390/min8030103.
4. Fayed H., Ragab S. Numerical simulations of two-phase flow in a self-aerated flotation machine and kinetics modeling. Minerals. 2015. Vol. 5, Iss. 2. pp. 164–188.
5. Romanenko S. A., Olennikov A. S. FrothMaster video system introduction experience practice at the «Green Mountain–2» Plant. Obogashchenie Rud. 2014. No. 2. pp. 23–28.
6. Liu J., Tang Z., Zhang J., Xu P., Liu W. Visual perceptionbased statistical modeling of complex grain image for product quality monitoring and supervision on assembly production line. PLoS ONE. 2016. Vol. 11, Iss. 3. DOI: 10.1371/journal.pone.0146484.
7. Chernetskaya I. E., Trufanov M. I., Concha Orozco H. E. Computer vision system for grain composition analysis of iron ore pellet. Izvestiya Yugo-Zapadnogo Gosudarstvennogo Universiteta. 2011. No. 5–1. pp. 98–102.
8. Zatonskiy А. V., Varlamova S. A. Use of reflection flare spots for automatic recognition of froth parameters in potassium ores flotation. Obogashchenie Rud. 2016. No. 2. pp. 49–56. DOI: 10.17580/or.2016.02.09.
9. Logunova O. S., Lednov A. V., Shilov R. E., Muslimov M. B., Baybulatov F. R. Segmentation of the image of the foam product of flotation: substantiation for replacement of the bubble of their glares. Matematicheskoye i Programmnoye Obespechenie Sistem v Promyshlennoy i Sotsialnoy Sferakh. 2018. Vol. 6, No. 1. pp. 12–19.
10. Zatonskiy A. V., Malysheva A. V. Improving algorithms of video sequence data recognition for identification of transition processes in a floatation machine of potassium ore. Vestnik Astrakhanskogo Gosudarstvennogo Tekhnicheskogo Universiteta. Seriya: Upravlenie, Vychislitelnaya Tekhnika i Informatika. 2019. No. 1. pp. 26–39.
11. Hoshen J., Kopelman R. Percolation and cluster distribution. I. Cluster multiple labeling technique and critical concentration algorithm. Physical Review B. 1976. Vol. 14, Iss. 8. pp. 3438–3445.
12. Malysheva A. V., Zatonskiy A. V. Study of the prospects for the transition to automatic control of the potash ore flotation. Avtomatizatsiya. Sovremennye Tekhnologii. 2019. Vol. 73, No. 3. pp. 119–127.
13. Farrokhpay S. The significance of froth stability in mineral flotation — A review. Advances in Colloid and Interface Science. 2011. Vol. 166. pp. 1–7.
14. Petukhov V. N., Svechnikova N. Yu., Alekseev D. I., Kuklina O. V., Yudina S. V., Puzina A. S., Akhmetzyanov T. N., Gavryushina Ya. V. Investigation of the cumulative effect of parameters on coal flotation indicators using regression analysis. Aktualnye Problemy Gornogo Dela. 2019. No. 1. pp. 53–60.