Irkutsk National Research Technical University (Irkutsk, Russia)

Shtyrkin F. A., Programmer, shtyrkinfa@ex.istu.edu
Novikov Yu. V., Postgraduate Student, 89500505553r@gmail.com
Lukyanov N. D., Associate Professor, Candidate of Engineering Sciences, lukyanovnd@ex.istu.edu
Burdonov A. E., Associate Professor, Candidate of Engineering Sciences, Associate Professor, burdonovae@ex.istu.edu

Machine learning techniques in experimental data processing enable the identification of hidden patterns through the use of nonlinear relationships, providing opportunities for economic gains. This paper presents the results of a study on the application of machine vision methods for automating the analysis of video materials recorded during fracturing of mineral raw materials. In the face of increasing competition in the mining industry, there is a growing need for efficient, high-precision tools. The tool developed for this study is designed to detect defects occurring during the fracturing process and generate regression equations that characterize these defects. A thorough review of existing software libraries for automatic detection of fault contours, as well as their merging and approximation, was conducted. These methods can significantly reduce analysis time and enhance the accuracy of mineral fracture assessments. Special attention is given to the image processing algorithms used, which allow for the effective handling of data captured by video cameras. The paper also presents a block diagram of the tool, outlining its functionality and data processing flow at each stage. The tool was tested on real-world data, demonstrating that the use of machine vision and regression analysis algorithms can reduce costs and improve the overall efficiency of mining operations. It optimizes the rock crushing process by enabling precise equipment adjustments. This tool holds potential value for both academic researchers and professionals in the mining and machine learning fields.

1. Kalenov O. E. Digitalization in the mining industry. Vestnik Rossiyskogo Ekonomicheskogo Universiteta imeni G. V. Plekhanova. 2021. Vol. 18, No. 5. pp. 184–192.
2. Hurelchuluun I., Morozov V. V., Nikolaeva T. S., Kruglov V. N. Use of visiometric analysis of granulometric ore composition for automated crushing control. Rudy i Metally. 2019. No. 1. pp. 67–73.
3. Skvortsov D. E., Shadrin D. G., Burdonov A. E., Shonkhodoyev Z. Ch. Automated information system for conducting laboratory research of the sedimentation process. XXI Vek: Itogi Proshlogo i Problemy Nastoyashchego Plyus. 2024. Vol. 13, No. 3. pp. 43–50.
4. Novikov Yu. V., Vlasova V. V., Burdonov A. E. The influence of temperature on physical, mechanical, and grain size distribution characteristics of crushed ore. Obogashchenie Rud. 2024. No. 5. pp. 3–8.
5. Chanturia V. A., Dmitrak Yu. V., Atrushkevich V. A., Adamova L. S. Peculiarities of crack growth process under highfrequency action of grinding bodies on rocks. Marksheyderiya i Nedropolzovanie. 2022. No. 4. pp. 4–9.
6. Klyuev R. V., Gavrina O. A., Mikhalchenko S. N. Analysis of specific electrical energy consumption of the processing factory. Izvestiya Tulskogo Gosudarstvennogo Universiteta. Nauki o Zemle. 2020. No. 1. pp. 433–447.
7. Aleksandrova T. N., Orlova A. V., Taranov V. A. Current status in the copper ore processing (review). Izvestiya Vysshikh Uchebnykh Zavedeniy. Tsvetnaya Metallurgiya. 2021. Vol. 27, No. 3. pp. 4–14.
8. Fedotov P. K. Comparison of ore disintegration efficiency in the layer of particles, using the traditional apparatuses. Tsvetnye Metally. 2013. No. 5. pp. 19–23.
9. Dmitriev S. V., Tikhonov O. N. On the relationship of the energy crushing laws of Kika–Kirpichev and Rittinger with the Bond work index. Obogashchenie Rud. 2004. No. 2. pp. 9–10.

10. Nematollahi E., Zare S., Maleki-Moghaddam M., Ghasemi A., Ghorbani F., Banisi S. DEM-based design of feed chute to improve performance of cone crushers. Minerals Engineering. 2021. Vol. 168. DOI: 10.1016/j.mineng.2021.106927
11. Alizadeh M., Asachi M., Ghadiri M., Bayly A., Hassanpour A. A methodology for calibration of DEM input parameters in simulation of segregation of powder mixtures, a special focus on adhesion. Powder Technology. 2018. Vol. 339. pp. 789–800.
12. Burmistrov A. V., Il′ichev V. Yu. Object recognition in images using basic Python language tools and OPENCV library. Nauchnoye Obozrenie. Tekhnicheskie Nauki. 2021. No. 5. pp. 15–19.
13. Tsukanova N. I. Application of neural networks to solving practical problems of image processing and structured data. Moscow: KURS Publishing House, 2022. 256 p.
14. Harris C. R., Millman K. J., van der Walt S. J., et al. Array programming with NumPy. Nature. 2020. Vol. 585. pp. 357–362.
15. Scikit-learn: machine learning in Python. URL: https://scikit-learn.org/stable/index.html (accessed: 12.12.2024).
16. Arthur D., Vassilvitskii S. How slow is the k-means method? Proc. of the 22 annual symposium on computational geometry – SCG′06. June 5–7, 2006, Sedona, Arizona, USA. pp. 144–153.
17. Babichev S., Lytvynenko V., Osypenko V. Implementation of the objective clustering inductive technology based on DBSCAN clustering algorithm. Proc. of the 12th International scientific and technical conference on computer sciences and information technologies CSIT. September 05–08, 2017, Lviv. Vol. 1. pp. 479–484.
18. Ester M., Kriegel H.-P., Sander J., Xu X. A densitybased algorithm for discovering clusters in large spatial databases with noise. Proc. of 2nd International conference on knowledge discovery and data mining (KDD-96). August 2–4, 1996, Portland, Oregon, USA. pp. 226–231.
19. Linear models. URL: https://scikit-learn.org/stable/modules/linear_model.html (accessed: 12.12.2024).
20. Bakhtin I. V. A linear regression model using the Scikit-Learn library. Innovatsii. Nauka. Obrazovanie. 2021. No. 27. pp. 939–951.
21. Kobzar′ A. I. Applied mathematical statistics. Moscow: Fizmatlit, 2006. 816 p.
22. Magnus Ya. R., Katyshev P. K., Peresetsky A. A. Econometrics. The initial course. Moscow: Delo, 2004. 576 p.
23. Li Ch., Zhou J., Dias D. Utilizing semantic-level computer vision for fracture trace characterization of hard rock pillars in underground space. Geoscience Frontiers. 2024. Vol. 15, Iss. 2. DOI: 10.1016/j.gsf.2023.101769
24. Witsil A. J. C., Johnson J. B. Volcano video data characterized and classified using computer vision and machine learning algorithms. Geoscience Frontiers. 2020. Vol. 11, Iss. 5. pp. 1789–1803.