Application of machine vision to analyze grinding media kinematics in grinding chambers of vibratory mills

DOI: https://doi.org/10.30686/1609-9192-2026-5-229-234

Читать на русском языке Yury V. Dmitrak, Alexey A. Kravtsov
Institute of Comprehensive Exploitation of Mineral Resources of Russian Academy of Sciences, Moscow, Russian Federation
Mining Industry Journal (Gornaya Promyshlennost) №5/ 2026 p. 229-234

Summary: A fundamentally novel approach to determining the kinematic parameters of individual grinding bodies in the grinding chamber of a vibratory mill is presented based on application of machine vision algorithms. The YOLO model, version 23, was trained to determine the kinematic parameters of the balls in the vibratory mill grinding chamber. The model is able to track objects within a video stream, facilitating both object identification in a single frame and determination of the inter-frame displacements. A convolutional neural network, configured for object detection, was developed to identify objects within the frame. Balls were employed as the target objects (grinding bodies). Training was conducted on a manually annotated dataset comprising video frames captured during the operation of a vibratory mill loaded with four marker balls. A total of 108 frames were annotated, of which 90 constituted the training set and 18 served as the validation set. Annotation was performed using the Label Studio software. Automatic data acquisition on the ball paths was performed using the trained model, and visualization of the trajectories was provided. A dependencies of the average kinetic energy of the balls on the fill factor of the vibratory mill grinding chamber were obtained. It was established that the optimal fill factor is not dependent of the presence of the core and lies within the range of 0.8–0.9. The results of the conducted experiments provide a basis for determining future research directions aimed at investigating the energy intensity of the grinding process.

Keywords: machine vision, control scheme, kinematic parameters, artificial intelligence, convolutional neural network, object trajectory visualization, kinetic energy, collision intensity

Acknowledgements: The study was financially supported by Grant No. 25-67-00009 of the Russian Science Foundation, https://rscf.ru/project/25-67-00009/

For citation: Dmitrak Yury V., Kravtsov Alexey A. Application of machine vision to analyze grinding media kinematics in grinding chambers of vibratory mills. Mining Industry Journal (Gornaya Promyshlennost). 2026;(5):229–234. https://doi.org/10.30686/1609-9192-2026-5-229-234

Article info

Received: 30.05.2026

Revised: 06.07.2026

Accepted: 09.07.2026

Authors info

Dmitrak Yury V. – Dr. Sci. (Eng.), Professor, Chief Research As- sociate, Head of Department of Modelling and Management of Mining Systems, Institute of Comprehensive Exploitation of Mineral Resources of Russian Academy of Sciences, Moscow, Rus- sian Federation; https://orcid.org/0000-0003-1278-4845; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Kravtsov Alexey A. – Junior Researcher, Department of Model- ling and Management of Mining Systems, Institute of Comprehensive Exploitation of Mineral Resources of Russian Academy of Sciences, Moscow, Russian Federation; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

References

1. Tomach P. The influence of the grinding media diameter on grinding efficiency in a vibratory ball mill. Materials . 2024;17(12):2924. https://doi.org/10.3390/ma17122924

2. Sidor J. A mechanical layered model of a vibratory mill. Mechanics and Control . 2010;29(3):138–148. Available at: https://journals.bg.agh.edu.pl/MECHANICS-CTRL/2010-03/mech07.pdf (accessed: 03.04.2026).

3. Sergeev V.V., Muzaev I.D., Dmitrak Ju.V., Gerasimenko T.E. Mathematical modeling of oscillations in novel-type vibration mills. Mining Informational and Analytical Bulletin. 2021;(8):114–128. (In Russ.) https://doi.org/10.25018/0236_1493_2021_8_0_114

4. Matmurodov F., Rasulov N., Nematova N. Dynamic simulation of the operation of four support vibrators mills. Universum: Technical Sciences. 2025;(1-2):47–51. (In Russ.) https://doi.org/10.32743/UniTech.2025.130.1.19212

5. Пыкавая О.А., Боровский Д.Н. Влияние мелющей загрузки на эффективность помола в вибрационной мельнице. В кн.: Нефтегазохимия – 2024: материалы 7-го Междуна. науч.-техн. форума по химическим технологиям и нефтегазопереработке, г. Минск, 13–15 ноября 2024 г. Минск: БГТУ; 2024. С. 229–233. Режим доступа: https://elib.belstu.by/handle/123456789/68326 (дата обращения: 29.03.2026).

6. Пыкавая О.А., Боровский Д.Н. Взаимосвязь технологических параметров вибрационной мельницы с геометрическими и механическими характеристиками загрузки помольной камеры. В кн.: Нефтегазохимия – 2023: материалы 6-го Междунар. науч.-техн. форума по химическим технологиям и нефтегазопереработке, г. Минск, 1–3 ноября 2023 г. Минск: БГТУ; 2023. С. 203–207. Режим доступа: https://elib.belstu.by/handle/123456789/60584 (дата обращения: 29.03.2026).

7. Dmitrak Iu.V.,Kravtsov A.A., Adamova L.S., Kutuev R.R., Tsiganov A.E. Scientific analysis of mathematical models of charge motion in grinding chambers of varioustype mills. Mini . (In Russ.) Available at: https://giab-online.ru/files/Data/2025/9-1/9-1_2025_55-74.pdf (accessed: 29.03.2026).

8. Рысиков М.С., Богданов Н.Э. Исследование характера движения вибрационной мельницы в системе EDEM при помощи метода дискретного элемента. В кн.: Молодежь и научно-технический прогресс: сб. докл. 12-й междунар. науч.-практ. конф. студентов, аспирантов и молодых ученых, г. Губкин, 18 апреля 2019 г. Губкин; Старый Оскол: ООО «Ассистент плюс»; 2019. Т. 1. С. 115––119.

9. Калуцкий Д.О. Анализ конструкции вибрационных мельниц тонкого помола. В кн.: Образование. Наука. Производство: материалы 10-й Междунар. молодежного форума с междунар. участием, г. Белгород, 1–15 октября 2018 г . Белгород: БГТУ им. В.Г. Шухова; 2018. С. 1227–1232.

10. Redmon J., Divvala S., Girshick R., Farhadi A. You only look once: Unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, June 27–30, 2016. IEEE; 2016, pp. 779–788. https://doi.org/10.1109/CVPR.2016.91

11. Lin X., Peng J., Gan Z., Zhu J., Liu J. YOLO-master: MOE-accelerated with specialized transformers for enhanced real-time detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026, Colorado, June 3–7, 2026, pp. 18440–18449. Available at: https://arxiv.org/html/2512.23273 (accessed: 29.03.2026).

12. Jiang P., Ergu D., Liu F., Cai Y., Ma B. A review of yolo algorithm developments. Procedia Computer Science. 2022;199:1066– 1073. https://doi.org/10.1016/j.procs.2022.01.135

13. Terven J., Córdova-Esparza D.-M., Romero-González J.-A. A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction . 2023;5(4):1680-1716. https://doi.org/10.3390/make5040083

14. Gracheva N.Yu. Development of the laboratory stand on the basis of vibratory mill for the experimental determination of its operating parameters. Mining Informational and Analytical Bulletin. 2015;(5):202–207. (In Russ.)