Empress Catherine II Saint Petersburg Mining University, St. Petersburg, Russia

P. V. Ivanov, Associate Professor, Chair for Automation of Technological Processes and Production, Candidate of Technical Sciences, e-mail: Ivanov_PV@pers.spmi.ru
L. N. Nikitina, Associate Professor, Chair for Automation of Technological Processes and Production, Candidate of Technical Sciences, e-mail: nikitina_ln@spmi.ru
N. V. Vasilyeva, Associate Professor, Chair for Automation of Technological Processes and Production, Candidate of Technical Sciences, e-mail: vasileva_nv@pers.spmi.ru

Saint Petersburg State Institute of Technology (Technical University), St. Petersburg, Russia

L. A. Rusinov, Head of the Chair for Automation of Chemical Industry Processes, Doctor of Technical Sciences, Professor

The article considers an approach to analyzing a large array of operational control data for developing a control model using the example of the technological process of smelting copper-nickel sulfide raw materials in a melt layer. The approach includes data filtering, removing outliers and data gaps, “misses” and other defects that do not allow them to be used in constructing the model. Based on the data of operational control over the course of the technological process, two models for assessing the content of non-ferrous metals in smelting products were developed: a multiple regression predictive model (average modeling error is 6%), and a model based on the Random Forest algorithm (average modeling error is 1%). When choosing the best model, preference was given to the multiple regression model. Optimal process conditions were determined that can be recommended to the operator when controlling the process. The use of such methods of analyzing operational control data in the advisory mode will allow the process operator to stabilize the content of nonferrous metals in the matte, which will increase the technical and economic indicators of the smelting process of copper-nickel sulfide raw materials and improve the technological parameters of further pyrometallurgical processing. Due to the conduct of the technological process in a mode close to the optimal one, the consumption of resources will be reduced. It should be noted that the proposed method is universal, which allows to recommend it for other technological processes.

1. Aazam M., Zeadally S., Harras K. A. Deploying fog computing in industrial internet of things and Industry 4.0. IEEE Transactions on Industrial Informatics. 2018. Vol. 14, Iss. 10. pp. 4674–4682.
2. Gospodarikov A. P., Revin I. E., Morozov K. V. Composite model for seismic monitoring data analysis during mining operations using the example of the JSC Apatit`s Kukisvumchorrskoe deposit. Zapiski Gornogo instituta. 2023. Т. 262. pp. 571–580. DOI: 10.31897/PMI.2023.9.
3. Akberdina V. V. Transformation of the industrial complex of Russia in the context of digitalization of the economy. Izvestiya Uralskogo gosudarstvennogo ekonomicheskogo universiteta. 2018. Vol. 19, No. 3. pp. 82–99. DOI: 10.29141/2073-1019-2018-19-3-8
4. Litvinenko V. S., Tsvetkov P. S., Molodtsov K. V. The social and market mechanism of sustainable development of public companies in the mineral resource sector. Eurasian Mining. 2020. No. 1. pp. 36–41.
5. Bartel A., Ichniowski C., Shaw K. How does information technology affect productivity? Plant-level comparisons of product innovation, process improvement, and worker skills. The Quarterly Journal of Economics. 2007. Vol. 122, Iss. 4. pp. 1721–1758.
6. Weng Y., Sun Y., Jiang D., Tao B. et al. Enhancement of real-time grasp detection by cascaded deep convolutional neural networks. Concurrency and Computation: Practice and Experience. 2021. Vol. 33, Iss. 5. 5976. DOI: 10.1002/cpe.5976
7. Matrokhina K. V., Makhovikov A. B., Trofimets E. N. Ensuring information security in corporate communication systems. E3S Web of Conferences. 2021. Vol. 266. 09001. DOI: 10.1051/e3sconf/202126609001
8. Ardanza A., Moreno A., Segura A., de la Cruz M., Aguinaga D. Sustainable and flexible industrial human machine interfaces to support adaptable applications in the Industry 4.0 paradigm. International Journal of Production Research. 2019. Vol. 57, Iss. 12. pp. 4045–4059.
9. Ivanov D., Tang C. S., Dolgui A., Battini D., Das A. Researchers’ perspectives on Industry 4.0: multi-disciplinary analysis and opportunities for operations management. International Journal of Production Research. 2021. Vol. 59, Iss. 7. pp. 2055–2078.
10. Capo D., Levina A., Dubgorn A., Schroder K. Enterprise architecture concept for digital manufacturing. IOP Conference Series: Materials Science and Engineering. 2020. Vol. 1001. 012044. DOI: 10.1088/1757-899X/1001/1/012044
11. Shestakov A. K., Petrov P. A., Nikolaev M. Yu. Automatic system for detecting visible emissions in the electrolysis shop of an aluminum plant based on machine vision and a neural network. Metallurg. 2022. No. 10. pp. 105–112. DOI: 10.1007/s11015-023-01445-z
12. Castelo-Branco I., Cruz-Jesus F., Oliveira T. Assessing Industry 4.0 readiness in manufacturing: evidence for the European Union. Computers in Industry. 2019.Vol. 107. pp. 22–32.
13. Ghobakhloo M., Fathi M. Corporate survival in Industry 4.0 era: the enabling role of lean-digitized manufacturing. Journal of Manufacturing Technology Management. 2020. Vol. 31, Iss. 1. pp. 1–30.
14. Martynov S. A., Bazhin V. Yu., Petrov P. A. A digital control system designed for ore thermal furnaces producing metallurgical silicon. Tsvetnye Metally. 2021. No. 1. pp. 70–76.