Improvement of detection quality for parameters of flotation machines using neural network

The algorithms of solution of a problem connected with the control over flotation process using computer vision are reviewed. It is revealed that the algorithm of foam generator unit synchronization with flotation machine, with the measurement of an illuminance level, covers not all necessary runs. It is proposed to improve the existing algorithms by using neural network for the identification of blades of the foam generator unit. The check-up data on the efficiency and adequacy of the learned model of identifying blades of the foam generator unit are described. The developed algorithm using the neural network model is compared with the earlier proposed algorithm. It is concluded that the learned neural network model makes it possible to reduce the number of the missed runs as compared with the previous algorithm by 5.1%.

Zatonskiy A. V., Kuznetsov S. V., Salomatova K. A. Improvement of detection quality for parameters of flotation machines using neural network. MIAB. Mining Inf. Anal. Bull. 2025;(6):153-167. [In Russ]. DOI: 10.25018/0236_1493_2025_6_0_153.

A.V. Zatonsliy¹, Dr. Sci. (Eng.), Professor, Head of Chair, e-mail: zxenon@narod.ru,
K.A. Salomatova¹, Senior Lecturer, e-mail: kristya_0103@mail.ru,
S.V. Kuznetsov¹, Student, e-mail: kuznetsovstas04@yandex.ru,
¹ Perm National Research Polytechnic University, Berezniki Branch, Berezniki, Russia.

A.V. Zatonsliy, e-mail: zxenon@narod.ru.

1. Dioujeva N. V., Tinkova A. A. Global mineral fertilizer market analysis. Vestnik of Astrakhan State Technical University. Series: Economics. 2020, no. 1, pp. 91—100. [In Russ]. DOI: 10.24143/20735537-2020-1-91-100.

2. Wakeel A., Ishfaq M. Potash use and dynamics in agriculture. Springer, 2022, 144 p.

3. Belkin P. A., Kataev V. N. Regularities of the chemical composition of technogenic transformation which groundwater undergoes in the areas of the potash deposits development. News of the Ural State Mining University. 2018, no. 2 (50), pp. 55—64. [In Russ]. DOI: 10.21440/2307-2091-2018-2-55-64.

4. Zemskov A. N., Liskova M. Yu., Zaalishvili V. B., Shamrin M. Yu. Modern technological and technical solutions for mining operations potash mines. News of the Tula state university. Sciences of Earth. 2022, no. 2, pp. 284—296. [In Russ]. DOI: 10.46689/2218-5194-2022-2-1-284-296.

5. Yurkevich N. V., Grosheva T. V., Edelev A. V., Gureev V. N., Mazov N. A. Modern approaches to the enrichment of barite ores. Journal of Mining Institute. 2024, vol. 270, pp. 977—993. [In Russ].

6. Silakov A. V., Varlamova S. A., Kotkov P. V. Software recognition of image defects of regular textures in the textile industry. Proceedings of higher education institutions. Textile industry technology. 2022, no. 2 (398), pp. 266—272. [In Russ]. DOI: 10.47367/0021-3497_2022_2_266.

7. Zatonskiy A. 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. [In Russ]. DOI: 10.17580/or.2016.02.09.

8. Varlamova S. A., Zatonskiy A. V., Fedoseeva K. A. Illumination sensitivity analysis for the speck-based froth detection method using potash flotation machines. Obogashchenie Rud. 2021, no. 6, pp. 29—33. [In Russ]. DOI: 10.17580/or.2021.06.05.

9. Malysheva A. V. Modeli i algoritmy podderzhki prinyatiya resheniy pri upravlenii protsessom flotatsii kaliynoy rudy [Models and algorithms for decision support in managing the flotation process of potash ore], Candidate’s thesis, Perm, 2020, 19 p.

10. Fedoseeva K. A. Sovershenstvovanie metodov identifikatsii sostoyaniya pennogo sloya kaliynykh flotomashin [Improvement of methods for identifying the state of the foam layer in potash flotation machines], Candidate’s thesis, Perm, 2023, 19 p.

11. Chen L., Li S., Bai Q., Yang J., Jiang S., Miao Y. Review of image classification algorithms based on convolutional neural networks. Remote Sensing. 2021, vol. 13, no. 22, article 4712. DOI: 10.3390/rs13224712.

12. Zhao X., Wang L., Zhang Y., Han X., Deveci M., Parmar M. A review of convolutional neural networks in computer vision. Artificial Intelligence Review. 2024, vol. 57, article 99. DOI: 10.1007/ s10462-024-10721-6.

13. Liu L., Ouyang W., Wang X., Fieguth P., Chen J., Liu X., Pietikainen M. Deep learning for generic object detection: A survey. International Journal of Computer Vision. 2020, vol. 128, pp. 261—318. DOI: 10.1007/s11263-019-01247-4.

14. Kaur R., Singh S. A comprehensive review of object detection with deep learning. Digital Signal Processing. 2023, vol. 132, article 103812. DOI: 10.1016/j.dsp.2022.103812.

15. Andriyanov N. A., Dementiev V. E., Tashlinskii A. G. Detection of objects in the images from likelihood relationships towards scalable and efficient neural networks. Computer Optics. 2022, vol. 46, no. 1, pp. 139—159. [In Russ]. DOI: 10.18287/2412-6179-CO-922.

16. Ren J., Wang Y. Overview of object detection algorithms using convolutional neural networks. Journal of Computer and Communications. 2022, vol. 10, no. 1, pp. 115—132. DOI: 10.4236/jcc. 2022.101006.

17. Dvoynikova A. A., Kagirov I. A., Karpov A. A. Analytical review of methods for automatic detection of user engagement in virtual communication. Information and Control Systems. 2022, no. 5, pp. 12—22. [In Russ]. DOI: 10.31799/1684-8853-2022-5-12-22.

18. Diwan T., Anirudh G., Tembhurne J. V. Object detection using YOLO: challenges, architectural successors, datasets and application. Multimedia Tools and Applications. 2023, vol. 82, pp. 9243— 9275. DOI: 10.1007/s11042-022-13644-y.

19. Cong X., Li S., Chen F., Liu C., Meng Y. A review of YOLO object detection algorithms based on deep learning. Frontiers in Computing and Intelligent Systems. 2023, vol. 4, no. 2, pp. 17—20. DOI: 10.54097/fcis.v4i2.9730.

20. Timoshkin M. S., Mironov A. N., Leont'yev A. S. Comparison of YOLO v5 and Faster R-CNN for detecting people in the image in streaming mode. International Research Journal. 2022, no. 6 (120), pp. 137—146. [In Russ]. DOI: 10.23670/IRJ.2022.120.6.020.

21. Vaughan L. Python tools for scientists: An introduction to using Anaconda, JupyterLab, and Python’s scientific libraries. No Starch Press, 2023, 744 p.