Enhancing production process efficiency through neural network‑based optimization of technological routes

This paper proposes an integrated approach that includes: the use of graph theory for building a model of technological routes; the use of artificial intelligence methods for optimizing the constructed graph models, including algorithms for finding the shortest path taking into account changing constraints and heuristic optimization strategies; the development of a special LSTM-type recurrent neural network architecture to solve the problem posed in the study, adapted to work with sequences of route data; the implementation of a risk assessment system based on neural network analysis, which can be integrated into the overall architecture of technological route optimization, with the key task of identifying potential problems and developing preventive measures; the use of mathematical modeling to formalize the optimization process as a minimization problem under specified constraints. As a result of the study, an adaptive model for optimizing technological routes was developed, a specialized program was created to assess scientific and technical risks when introducing new or improved technologies at an enterprise, the architecture of the LSTM neural network was built taking into account the specifics of the industry-specific production processes under study, and the model was validated on real production data. The study has shown that the application of the developed approach makes it possible to significantly reduce the time required for making design decisions, optimize technological routes according to multiple necessary criteria while considering their importance for a particular optimization option, increase the accuracy of forecasting when implementing the results in production, and adapt technological processes to changing production conditions. Furthermore, the possibility of integrating the presented solution into existing CAM and MES systems has been demonstrated.

1. Shaykhulova A.F., Gavrilova O.A. System-technical bases of intellectualization methods for innovative production preparation in machine building. Avtomatizatsiya. Sovremennye tekhnologii. 2022;76(1):30–34. (In Russ.). https://doi.org/10.36652/0869-4931-2022-76-1-30-34

2. Puchkov A.Yu., Dli M.I., Lobaneva E.I. Application of deep neural networks in models of complex technological objects. Bulletin of SPbSIT(TU). 2020;(52):104–110. (In Russ.). https://doi.org/10.36807/1998-9849-2020-52-78-104-110

3. Shaykhulova A.F., Selivanov S.G. Digital transformation strategy development for industry 4.0. XXI Century: Resumes of the Past and Challenges of the Present Plus. 2021;10(2):92–95. (In Russ.).

4. Gorodnova N.V. Application of artificial intelligence in the business sphere: current state and prospects. Russian Journal of Innovation Economics. 2021;11(4):1473–1492. (In Russ.). https://doi.org/10.18334/vinec.11.4.112249

5. Makhalina O.M., Makhalin V.N. Artificial intelligence: a driver of economic development or a generator of problems and threats? BENEFICIUM. 2024;(1):14–21. (In Russ.). https://doi.org/10.34680/BENEFICIUM.2024.1(50).14-21

6. Tyryshkin S.Yu. Neural network optimization in automated control systems for complex technological processes and production. Proceedings of the TUSUR University. 2025;28(2):153–159. (In Russ.).

7. Soloviev D., Bondarenko I. Parametrical optimization of difficult technological processes of optical manufacture with technologies of artificial neural networks. Nauchno‑tekhnicheskii vestnik Sankt‑Peterburgskogo gosudarstvennogo universiteta informatsionnykh tekhnologii, mekhaniki i optiki. 2010;(6):121. (In Russ.).

8. Klimova T.Y., Khaimovich I.N., Tarasov V.A., Kurakov S.V. Preventing equipment failures in digital factory 4.0 using a neural network model. News of the Tula State University. Technical Sciences. 2025;(5):140–149. (In Russ.).

9. Anisimov A.A., Sorokovnin M.E., Tararykin S.V. Neural Network Identification and Tuning of Mechatronic Systems with State Controllers. Mekhatronika, Avtomatizatsiya, Upravlenie. 2025;26(2):65–76. (In Russ.). https://doi.org/10.17587/mau.26.65-76

10. Honin K.A., Ermolaev R.A. Technological process improvement in automated production. Young Scientist. 2018;(25):151–155. (In Russ.).