Mining Institute KSC RAS (Apatity, Russia)
Nikitin R. M., Scientific Secretary, PhD in Engineering, r.nikitin@ksc.ru
Lukichev S. V., Director, Doctor of Engineering Sciences, Senior Researcher, s.lukichev@ksc.ru
Opalev A. S., Leading Researcher, PhD in Engineering, a.opalev@ksc.ru

Apatity Branch of Murmansk Arctic University (Apatity, Russia)
Biryukov V. V., Associate Professor, birukovval@rambler.ru

A software application has been developed to create adaptive models for mineral processing flow charts and processes, leveraging machine learning technology. The application enables generation of synaptic weights in a neural network that establish precise correlations between the input and output parameters of industrial processes, facilitating the creation of adaptive models. Its algorithm is based on the architecture of feedforward neural networks, incorporating bias neurons. This tool is designed for direct integration into automated process control systems, enabling real-time optimization of enrichment processes, identification of optimal input and output values, and accurate forecasting to support rapid and effective decision-making. The application was tested on data from the iron ore enrichment section of a crushing and beneficiation plant, which led to the development of a block-based adaptive model representing the qualitative and quantitative process flow charts of the section. The model comprises interconnected adaptive submodels for processes such as grinding, wet magnetic and magnetic-gravity separation, classification, and desliming. These submodels, represented by trained neural networks, are linked according to the operational flow chart, allowing comprehensive validation of the overall model and analysis of the impact of changes in any single process on the entire section. The ability to update training datasets ensures that the neural network adapts to operational changes in the beneficiation plant. These changes may include variations in initial ore batch composition, useful component content in the products, process performance, slurry solid content, water consumption, circulation load, and concentrate grade.

1. Khopunov E. A. Digitization of subsoil use technologies. Izvestiya Vysshikh Uchebnykh Zavedenii. Gornyi Zhurnal. 2021. No. 2. pp. 70–78.
2. Gritsayuk Ya. O., Osipova V. A. Digital transformation of beneficiation processes. KIP i Avtomatika: Obsluzhivanie i Remont. 2021. No. 1. pp. 29–31.
3. Rylnikova M. V., Strukov K. I., Radchenko D. N., Esina E. N. Digital transformation: A prerequisite and foundation for sustainable development of mining operations. Gornaya Promyshlennost. 2021. No. 3. pp. 74–78.
4. Nagovitsyn O. V. The development of MGIS in the modern realities of the Russian mining industry. Digital technologies in mining. Abstracts of the All-Russian scientific and technical conference. Apatity: KSC RAS, 2023. pp. 36–37.

5. Noome Z. M., Roux J. D., Padhi R. Optimal control of mineral processing plants using constrained model predictive static programming. Journal of Process Control. 2023. Vol. 129. DOI: 10.1016/j.jprocont.2023.103067
6. Aleksandrova T. N., Chanturia A. V. Ore preparation process selection for ferruginous quartzites based on simulation modeling. Obogashchenie Rud. 2023. No. 1. pp. 3–9.
7. Blyudenov A. P., Makushev S. Yu., Cherepanov D. V., Schneider D. A. Digitalization of a processing plant. Gornaya Promyshlennost. 2023. No. 3. pp. 15–18.
8. McCoy J. T., Auret L. Machine learning applications in minerals processing: A review. Minerals Engineering. 2019. Vol. 132. pp. 95–109.
9. Aldrich C. Deep learning in mining and mineral processing operations: A review. IFAC – Papers OnLine. 2020. Vol. 53, Iss. 2. pp. 11920–11925.
10. Ohenojaa M., Koistinen A., Hultgren M. et al. Continuous adaptation of a digital twin model for a pilot flotation plant. Minerals Engineering. 2023. Vol. 198. DOI: 10.1016/j.mineng.2023.108081
11. Zhang D., Gao X. A digital twin dosing system for iron reverse flotation. Journal of Manufacturing Systems. 2022. Vol. 63. pp. 238–249.
12. Koh E. J. Y., Amini E., Gaur S. et al. An automated machine learning (Auto ML) approach to regression models in minerals processing with case studies of developing industrial comminution and flotation models. Minerals Engineering. 2022. Vol. 189. DOI: 10.1016/j.mineng.2022.107886
13. Gomez-Flores A., Ilyas S., Heyes G. W., Kim H. A critical review of artificial intelligence in mineral concentration. Minerals Engineering. 2022. Vol. 189. DOI: 10.1016/j.mineng.2022.107884
14. Bakhmetova N. A., Tokarev S. V. Modeling of technological processes using neural networks. Sovremennye Naukoyemkie Tekhnologii. 2008. No. 2. pp. 139–140.
15. Antipin A. L., Zelenina L. I. Process modeling based on neural networks. Sovremennye Nauchnye Issledovaniya i Innovatsii. 2015. No. 7. URL: https://web.snauka.ru/issues/2015/07/55119 (accessed: 08.12.2024).
16. Jamróz D., Niedoba T., Pieta P., Surowiak A. The use of neural networks in combination with evolutionary algorithms to optimise the copper flotation Enrichment process. Applied Sciences. 2020. Vol. 10, Iss. 9. DOI: 10.3390/app10093119
17. Lu J., Li Ch., Ding J. Ensemble random weights neural network based online prediction model of the production rate for mineral beneficiation process. Proc. of the 5^th IFAC workshop on mining, mineral and metal processing. Shanghai, China. August 2018. DOI: 10.1016/j.ifacol.2018.09.383
18. Peng F., Nie Q. Research status and prospect of application of neural network in mineral processing prediction. Proc. of the 4^th International conference on cyber security intelligence and analytics. Cham: Springer, 2022. Vol. 2. pp. 615–621.