Tashkent State Technical University (Tashkent, Uzbekistan)
Zh. U. Sevinov, Head of the Department of Information Processing and Control Systems, Doctor of Technical Sciences, Professor, j.sevinov@tdtu.uz
Almalyk branch of NUST MISiS (Almalyk, Uzbekistan)
B. М. Тemerbekova, Head of the Department of Information Technologies and Automation of Technological Processes and Production, Doctor of Technical Sciences, Associate Professor, misis_temerbekova@mail.ru
U. B. Mamanazarov, Senior Lecturer of the Department of Information Technologies and Automation of Technological Processes and Production, Master of Technical Sciences, m67811@mail.ru
Tashkent State University of Economics (Tashkent, Uzbekistan)
G. М. Bekimbetova, Head of the Department of Economics and Management, Doctor of Economics, Associate Professor, gmkbbd@gmail.com
Almalyk State Technical Institute (Almalyk, Uzbekistan)
B. М. Bekimbetov, Senior Lecturer at the Department of Electrical Engineering, Power Engineering and Process Automation4, Master of Technical Sciences, bakhodir.bekimbetov@inbox.ru
A reproducible scheme for predictive control of a technological circuit at a copper-molybdenum processing plant is presented, combining cloud-based data processing and hybrid models. Telemetry and laboratory data streams (SCADA/MES, LIMS, ERP) are aggregated in a Data Lake (Parquet) and routed using Spark/Airflow to two classes of models: LSTM-DNN for timeseries forecasting and ensemble boosting regressors for static-dynamic relationships. The pipeline includes time alignment (1-minute interval), outlier filtering (|z| > 3), missing-value interpolation, separate min-max normalization for the Train/Test sets, and generation of domain-specific features (windows, utilization coefficients, ratios, and temporal gradients), followed by selection using Mutual Information and Shap. During a 12-month pilot deployment, the following results have been achieved: R2 ≈ 0.85 for p80 prediction, with an approximately 15% reduction in particle-size distribution variability; R2 ≈ 0.90 for Cu/Mo recovery prediction, with reagent consumption reduced by up to 7% and copper recovery increased by 2–3 percentage points; and R2 ≈ 0.88 for predicting the composition after smelting, with a 5–10% reduction in specific energy consumption. Stability has been confirmed using k-fold cross-validation (k = 5) and testing with ±10% noise, with a performance degradation of no more than 2.3%. Integration via a Rest-Api enables recommendations to be transmitted to the HMI/SCADA system (pH adjustment, dosage correction, operating-mode adjustment), providing proactive process control without physical equipment modernization. The contribution lies in the systematic cloud-centric integration of ML/AI into the control loop, with a demonstrable technological and economic effect.
1. Hochreiter S., Schmidhuber J. Long short-term memory. Neural Computation. 1997. Vol. 9, Iss. 8. pp. 1735–1780.
2. Zhang Y., Zhang S., Wang Q. LSTM-based soft sensor model for prediction of metallurgical process quality. Metals. 2020. Vol. 10, Iss. 6. pp. 821.
3. Qin S. J. Survey on data-driven industrial process monitoring and diagnosis. Annual Reviews in Control. 2012. Vol. 36, Iss. 2. pp. 220–234.
4. Zhou H. et al. Informer: Beyond efficient transformer for long sequence time-series forecasting. Proceedings of the AAAI Conference on Artificial Intelligence. 2021. Vol. 35. Iss. 12. pp. 11106–11115.
5. Wu H. et al. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. NeurIPS. 2021. Vol. 34. pp. 22419–22430.
6. Bi Z., Wang J., Zhang X. Real-time data reliability evaluation using deep neural networks in industrial control systems. Measurement. 2021. Vol. 182. 109664.
7. Sevinov J., Temerbekova B., Bekimbetova G., Mamanazarov U., Bekimbetov B. Hybrid LSTM-DNN Architecture with low-discrepancy hypercube sampling for adaptive forecasting and data reliability control in metallurgical information-control systems. Processes. 2026. Vol. 14. DOI: 10.3390/pr14010147
8. Alshathri S., Hemdan E. E.-D., El-Shafai W., Sayed A. Digital twin-based automated fault diagnosis in industrial IoT applications. Computers, Materials & Continua. 2023. Vol. 75, Iss. 1. pp. 183–196.
9. Anthi E., Williams L., Rhode M., Burnap P., Wedgbury A. Adversarial attacks on machine learning cybersecurity defences in Industrial Control Systems. Journal of Information Security and Applications. 2021. Vol. 58. DOI: 10.1016/j.jisa.2020.102717
10. Abdurakhmanova Y. M., Sevinov J. U. Algorithms to synthesis for adaptive sub-optimal control of dynamic objects based on regular methods. 2021 International Conference on Information Science and Communications Technologies (ICISCT). 1–3. 2021. DOI: 10.1109/ICISCT52966.2021.9670234
11. Temerbekova B. M. Application of systematic error detection method to integral parameter measurements in sophisticated production processes and operations. Tsvetnye Metally. 2022. No. 5. pp. 79–86.
12. Cantarelli C. C., Flyvbjerg B., Molin E. J. E., van Wee B. Cost overruns in large-scale transportation infrastructure projects: explanations and their theoretical embeddedness. European Journal of Transport and Infrastructure Research. 2010. Vol. 10, Iss. 1. pp. 5–18.
13. Choi S.-W., Lee E.-B., Kim J. -H. The engineering machine-learning automation platform (EMAP): a big-data-driven ai tool for contractors’ sustainable management solutions for plant projects. Sustainability. 2021. Vol. 13, Iss. 18. DOI: 10.3390/su131810384
14. Elahi M., Afolaranmi S. O., Martinez Lastra J. L., Perez Garcia J. A. A comprehensive literature review of the applications of AI techniques through the lifecycle of industrial equipment. Discover Artificial Intelligence. 2023. Vol. 3, Iss. 43. DOI: 10.1007/s44163-023-00089-x
15. Gawde S., Patil S., Kumar S., Kamat P., Kotecha K., Alfarhood S. Explainable predictive maintenance of rotating machines using LIME, SHAP, PDP, ICE. IEEE Access. 2024. Vol. 12. DOI: 10.1109/ACCESS.2024.3367110
16. Giriraj M., Muthu S. A cloud computing methodology for industrial automation and manufacturing execution system. Journal of Theoretical and Applied Information Technology. 2013. Vol. 52, Iss. 3. pp. 301–307.
17. Givehchi O., Trsek H., Jasperneite J. Cloud computing for industrial automation systems – a comprehensive overview. IEEE 18 th Conference on Emerging Technologies & Factory Automation (ETFA). 2013. Vol. 1–4. DOI: 10.1109/ETFA.2013.6648080
18. Gonzalez-Herbon R., Gonzalez-Mateos G., Rodriguez-Ossorio J. R., Dominguez M. et al. An Approach to Develop Digital Twins in Industry. Sensors. 2024. Vol. 24, Iss. 3. DOI: 10.3390/s24030998
19. Gulyamov S. M., Temerbekova B. M., Mamanazarov U. B. Noise immunity criterion for the development of a complex automated technological process. E3S Web of Conferences. 2023. Vol. 452. DOI: 10.1051/e3sconf/202345203014
20. Jamwal A., Agrawal R., Sharma M. Deep learning for manufacturing sustainability: Models, applications in Industry 4.0 and implications. International Journal of Information Management Data Insights. 2022. Vol. 2, Iss. 2. DOI: 10.1016/j.jjimei.2022.100107
21. Koay A. M. Y., Ko R. K. L., Hettema H., Radke K. Machine learning in industrial control system (ICS) security: Current landscape, opportunities and challenges. Journal of Intelligent Information Systems. 2023. Vol. 60. DOI: 10.1007/s10844-022-00753-1
22. Mattera G., Caggiano A., Nele L. Optimal data-driven control of manufacturing processes using reinforcement learning: An application to wire arc additive manufacturing. Journal of Intelligent Manufacturing. 2025. Vol. 36. DOI: 10.1007/s10845-023-02307-w
23. Mentsiev A. U., Kulpeiis Y. A., Smagulova K. K. Cloud computing in industrial automation systems. IOP Conference Series: Materials Science and Engineering. 2021. Vol. 1155, Iss. 1. DOI: 10.1088/1757-899X/1155/1/012063
24. Mokhtari S., Abbaspour A., Yen K. K., Sargolzaei A. A machine learning approach for anomaly detection in industrial control systems based on measurement data. Electronics. 2021. Vol. 10, Iss. 4. DOI: 10.3390/electronics10040407
25. Ng K. K. H., Chen C.-H., Lee C. K. M., Jiao J. (Roger), Yang Z.-X. A systematic literature review on intelligent automation: Aligning concepts from theory, practice, and future perspectives. Advanced Engineering Informatics. 2021. Vol. 47. DOI: 10.1016/j.aei.2021.101246
26. Pei-Breivold H. Towards factories of the future: Migration of industrial legacy automation systems in the cloud computing and Internet-of-things context. Enterprise Information Systems. 2020. Vol. 14, Iss. 4. pp. 542–562.
27. Rousopoulou V., Vafeiadis T., Nizamis A., Iakovidis I. et al. Cognitive analytics platform with AI solutions for anomaly detection. Computers in Industry. 2022. Vol. 134. DOI: 10.1016/j.compind.2021.103555
28. San-Payo G., Ferreira J. C., Santos P., Martins A. L. Machine learning for quality control system. Journal of Ambient Intelligence and Humanized Computing. 2020. Vol. 11, Iss. 11. pp. 4491–4500.
29. Selvarajan S., Srivastava G., Khadidos Alaa O. et al. An artificial intelligence lightweight blockchain security model for security and privacy in IIoT systems. Journal of Cloud Computing. 2023. Vol. 12, Iss. 38. DOI: 10.1186/s13677-023-00412-y
30. Sevinov J. U., Boborayimov O. Kh., Bobomurodov N. H. Algorithms for synthesis of adaptive neural network control systems based on the velocity gradient
method. Ed. R. A. Aliev, J. Kacprzyk, W. Pedrycz, M. Jamshidi, M. Babanli, F. M. Sadikoglu. 16th International Conference on Applications of Fuzzy Systems, Soft Computing and Artificial Intelligence Tools – ICAFS-2023. Lecture Notes in Networks and Systems. 2024. DOI: 10.1007/978-3-031-76283-3_34
31. Shah V., Putnik G. D. Machine learning based manufacturing control system for intelligent Cyber-Physical Systems. FME Transactions. 2019. Vol. 47, Iss. 4. pp. 802–809.
32. Shilpashree S., Patil R. R., Parvathi C. Cloud computing an overview. International Journal of Engineering and Technology. 2018. Vol. 7, Iss. 4. pp. 2743–2746.
33. Su W., Xu G., He Z., Machica I. K. et al. Cloud-edge computing-based ICICOS framework for industrial automation and artificial intelligence: a survey. Journal of Circuits, Systems and Computers. 2023. Vol. 32, Iss. 10. DOI: 10.1142/S0218126623501682
34. Temerbekova B. M., Mamanazarov U. B., Bekimbetov B. M., Ibragimov Zh. M. Development of integrated digital twins of control systems for ensuring the reliability of information and measurement signals based on cloud technologies and artificial intelligence. Chernye Metally. 2023. No. 4. pp. 39–46.
35. Avazov K., Sevinov J., Temerbekova B., Bekimbetova G. et al. Hybrid cloud-based information and control system using LSTM-DNN neural networks for optimization of metallurgical production. Processes. 2025. Vol. 13, Iss. 7. DOI: 10.3390/pr13072237
36. Turgunbaev A., Temerbekova B. M., Usmanova Kh. A., Mamanazarov U. B. Application of the microwave method for measuring the moisture content of bulk materials in complex metallurgical processes. Chernye Metally. 2023. No. 4. pp. 23–28.
37. Yusupbekov A. N., Sevinov J. U., Mamirov U. F., Botirov T. V. Synthesis algorithms for neural network regulator of dynamic system control. Eds. R. A. Aliev, J. Kacprzyk, W. Pedrycz, M. Jamshidi, M. Babanli, F. M. Sadikoglu. 14th International Conference on Theory and Application of Fuzzy Systems and Soft Computing – ICAFS-2020. Advances in Intelligent Systems and Computing. 2021. pp. 723–730.