M.N. Belozerov1, A.N. Smirnov2

1 National Research Technological University “MISIS” (Moscow, Russia)
2 Sberbank of Russia PJSC, Central Office (Moscow, Russia)
1 mnbelozyorov@gmail.com, 2 asmirnov889@yandex.ru

Problem statement. Currently, the task of product quality control at the operational stage is becoming urgent, while the transition to business processes based on AI and ML is associated with the risk of financial losses due to errors in the operation of models. These losses can be comparable to credit, market or operational risks, which makes model risk management relevant. The purpose of the study is to set the task of product quality control in the processes of model risk management and to describe a specialized information system that simulates production processes in digital form and represents a digital twin of technological processes that uses enterprise information for modeling and rapid response to changes. Results. It has been established that in order to increase the efficiency of production preparation, end-to-end management tools are needed that contain information about all stages of the production process, simulate decision-making processes and automatically recalculate decisions when external or internal factors change. Practical significance. The proposed approach has been tested in the processes of managing the Sber model risk, individual elements of this approach have been tested in companies of the food and metallurgical industries.

Belozerov M.N., Smirnov A.N. The task of product quality control in model risk management processes. Nonlinear World. 2025. V. 23. № 1. P. 72–78. DOI: https:// doi.org/10.18127/ j20700970-202501-08 (In Russian)

1. Belozerov M.N. Dialogovaya procedura rascheta potrebnosti v iskhodnyh materialah i upravlenie syr'evymi zapasami v usloviyah mnogovariantnosti tekhnologij ispol'zovaniya syr'ya (In Russian).
2. Sber zhdet okolo 450 mlrd rublej dohodov v 2024 godu ot vnedreniya II. Interfaks [Elektronnyj resurs]. URL https://www.interfax.ru/business/950133 (data obrashcheniya: 01.09.24) (In Russian).
3. Gref ocenil effekt ot iskusstvennogo intellekta v Sberbanke v 2021 godu v 80–85 mlrd rub.. TASS. URL https://tass.ru/ekonomika/10997599 (data obrashcheniya: 01.09.24) (In Russian)
4. Dohod Sbera ot vnedreniya iskusstvennogo intellekta v 2022 godu prevysit 200 mlrd rublej. TASS. URL https://tass.ru/ekonomika/16293069 (data obrashcheniya: 01.09.24) (In Russian).
5. Pudovkin A.P., Panasyuk Yu.N., Moskvitin S.P. Nepreryvnyj kontrol' kachestva mnogoslojnyh materialov. Radiotekhnika. 2013. № 9. S. 120–123 (In Russian).
6. Vlasov A.I. i dr. Primenenie nejronnyh setej v obnaruzhenii defektov pechatnyh plat. Nejrokomp'yutery: razrabotka, primenenie. 2022. T. 24. № 6. S. 5–19 (In Russian).
7. Mudar K. i dr. Analiz osnovnyh podhodov k modelirovaniyu avarijnyh situacij dlya upravleniya riskami v sociotekhnicheskih sistemah. Dinamika slozhnyh sistem – XXI vek. 2021. T. 15. № 1. S. 22–37 (In Russian).
8. Wang S. et al. A deep learning-enhanced Digital Twin framework for improving safety and reliability in human–robot collaborative manufacturing. Robotics and computer-integrated manufacturing. 2024. V. 85. P. 102608.
9. Qin B. et al. Machine and Deep Learning for Digital Twin Networks: A Survey. IEEE Internet of Things Journal. 2024.
10. Yuan G. et al. Multi-objective coupling optimization of electrical cable intelligent production line driven by digital twin. Robotics and Computer-Integrated Manufacturing. 2024. V. 86. P. 102682.
11. Wang T. et al. Pipeline condition monitoring towards digital twin system: A case study. Journal of Manufacturing Systems. 2024. V. 73. P. 256–274.
12. Zhang Z. et al. Enabling collaborative assembly between humans and robots using a digital twin system. Robotics and Computer-Integrated Manufacturing. 2024. V. 86. P. 102691.
13. Usiagu G.S. et al. Simulation techniques in industrial engineering: A USA and African perspective review. Magna Scientia Advanced Research and Reviews. 2024. V. 10. № 1. P. 265–272.
14. Ahmad S.A. et al. Mathematical modeling techniques to predict the compressive strength of pervious concrete modified with waste glass powders. Asian Journal of Civil Engineering. 2024. V. 25. № 1. P. 773–785.
15. Palakurti N.R., Kolasani S. AI-Driven Modeling: From Concept to Implementation. Practical Applications of Data Processing, Algorithms, and Modeling. IGI Global/ 2024. С. 57–70.
16. Malik A. et al. Industrial revolution and environmental sustainability: an analytical interpretation of research constituents in Industry 4.0. International Journal of Lean Six Sigma. 2024. V. 15. № 1. P. 22–49.
17. Soltaninejad M. et al. Using Machine Learning Techniques to Forecast Mehram Company's Sales: A Case Study. Journal of Business and Management Studies. 2024. V. 6. № 2. P. 42–53.
18. Arefin S. et al. Retail Industry Analytics: Unraveling Consumer Behavior through RFM Segmentation and Machine Learning. 2024 IEEE International Conference on Electro Information Technology (eIT). IEEE. 2024. P. 545–551.
19. Jauhar S.K. et al. A deep learning-based approach for performance assessment and prediction: A case study of pulp and paper industries. Annals of Operations Research. 2024. P. 1–27.
20. Torkul O., Selvi I. H., Şişci M. Smart seru production system for Industry 4.0: a conceptual model based on deep learning for real-time monitoring and controlling. International Journal of Computer Integrated Manufacturing. 2024. V. 37. № 4. P. 385–407.