Irkutsk National Research Technical University, Irkutsk, Russia

Yu. V. Novikov, Senior Lecturer, Candidate of Engineering Sciences
N. D. Lukyanov, Candidate of Engineering Sciences, Associate Professor
A. E. Burdonov, Candidate of Engineering Sciences, Associate Professor, slimbul@inbox.ru

This paper investigates the dependence of the energy intensity of disintegration process in various rocks on various parameters, followed by the creation of a mathematical model. Five types of rocks were analyzed: apatite ore, porphyry, diabase, gabbro-diabase and carbonaceous phyllite schists. The data for the mathematical model were obtained through a series of laboratory experiments, such as determining moisture content and measuring destruction energy intensity at different temperatures. To analyze the influence of key factors: moisture content, rock volume, temperature and ore type, a mathematical model was developed based on the radial basis function (RBF) support vector method. The use of cross-validation and Shapley metrics improved the accuracy and adequacy of the model. The relevance of these studies lies in the fact that improving the efficiency of disintegration processes is important for reducing energy costs and increasing productivity in the mining industry. The results show that the type of ore and the temperature have the greatest impact on the destruction energy intensity. The model demonstrates high prediction accuracy with a coefficient of determination R2 = 0.73, which confirms its applicability for optimizing production processes. In addition, a search was conducted for the optimal temperature values at which energy intensity was minimized at fixed parameters of moisture content and rock volume, for which the L-BFGS-B method was applied. The proposed methodology can be integrated into automated control systems (ACS), which will allow real-time adjustment of the disintegration process parameters, reduce the energy consumption, and increase the efficiency of mineral extraction.
The study was supported by the Russian Science Foundation, Project No. 25-27-20120.

1. Burdonov A. E., Barakhtenko V. V., Prokhorov K. V., Gavrilenko A. A. Results of studies of disintegration working indices for alumina-containing wastes. Obogashchenie Rud. 2018. No. 4. pp. 11–16.
2. Fedotov K. V., Senchenko A. E., Kulikov Yu. V. Method of calculating autogenous / semiautogenous grinding energy based on combination of the Bond work indices. MIAB. 2014. No. 11. pp. 127–140.
3. Prokopenko A. V., Shishkin A. A., Savitskiy V. B., Amelin S. A. The study of safety of natural quality of diamonds under kimberlite regrinding in POLYCOM® 09/6-0—A high pressure roll press. Vestnik Irkutskogo gosudarstvennogo tekhnicheskogo universiteta. 2008. No. 3(35). pp. 200–202.
4. Khabarova I. A., Bunin I. Zh. Increasing of the efficiency of disintegration and flotation of low-grade copper–nickel sulfide ores. New Materials and Advanced Technologies : Sixth Interdisciplinary Scientific Forum with International Participation. Moscow : Tsentr nauchno-tekhnicheskikh resheniy, 2020. Vol. 2. pp. 465–470.
5. Qin H., Guo X., Tian Q., Yu D., Zhang L. Recovery of gold from sulfide refractory gold ore: Oxidation roasting pretreatment and gol d extraction. Minerals Engineering. 2021. Vol. 164. ID 106822.
6. Adewuyi S. O., Ahmed H. A. M., Ahmed H. M. A. Methods of ore pretreatment for comminution energy reduction. Minerals. 2020. Vol. 10, Iss. 5. ID 423.
7. Sultanalieva R. M., Konushbaeva A. T., Turdubaeva Ch. B. Energy intensity of rock disintegration under influence of time and temperature regime of microwave fields. Mezhdunarodnyi zhurnal prikladnykh i fundamentalnykh issledovaniy. 2019. No. 12-2. pp. 187–191.
8. Shibaeva D. N., Kompanchenko A. A., Tereschenko S. V. Analysis of the effect of dry magnetic separation on the process of ferruginous quartzites disintegration. Minerals. 2021. Vol. 11, Iss. 8. ID 797.
9. Homand-Etienne F., Houpert R. Thermally induced microcracking in granites: Characterization and analysis. International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts. 1989. Vol. 26, No. 2. pp. 125–134.
10. Srinivasan V., Tripathy A., Gupta T., Singh T. N. An investigation on the influence of thermal damage on the physical, mechanical and acoustic behavior of Indian Gondwana shale. Rock Mechanics and Rock Engineering. 2020. Vol. 53, Iss. 6. pp. 2865–2885.
11. Huang S., Liu Q., Cheng A., Liu Y. A statistical damage constitutive model under freezethaw and loading for rock and its engine ering application. Cold Regions Science and Technology. 2018. Vol. 145. pp. 142–150.
12. Guo Y., Huang L., Li X., Chen J., Sun J. Experimental investigation on the effects of thermal treatment on the physical and mechanical properties of shale. Journal of Natural Gas Science and Engineering. 2020. Vol. 82. ID 103496.
13. Cao K., Ma L., Wu Y., Spearing A. J. S., Khan N. M. et al. Statistical damage model for dry and saturated rock under uniaxial loading based on infrared radiation for possible stress prediction. Engineering Fracture Mechanics. 2022. Vol. 260. ID 108134.
14. Dobrov E. M. Engineering Geology : Textbook. 3rd revised and enlarged edition. Moscow : Akademiya, 2013. 224 p.
15. Cross-validation: Evaluating estimator performance. User Guide. Available at: https://scikit-learn.org/stable/modules/cross_validation.html (accessed: 12.11.2025).
16. Burdonov A. E., Novikov Yu. V., Lukyanov N. D. Application of regression analysis apparatus for processing the results obtained from ore processing by the centrifugal concentration method. Tsvetnye Metally. 2024. No. 5. pp. 15–22.
17. Smola A. J., Schölkopf B. A tutorial on support vector regression. Statistics and Computing. 2004. Vol. 14, Iss. 3. pp. 199–222.
18. Vapnik V., Izmailov R. V-matrix method of solving statistical inference problems. Journal of Machine Learning Research. 2015. Vol. 16. pp. 1683–1730.
19. Welcome to the SHAP documentation. 2018. Available at: https://shap.readthedocs.io/en/latest/ (accessed: 12.11.2025).
20. Demanet L., Jugnon V. Convex recovery from interferometric measurements. IEEE Transactions on Computational Imaging. 2017. Vol. 3, Iss. 2. pp. 282–295.