Predictive forecasting methodology for monitoring the technical condition of artificial structures

This paper proposes a methodology for predictive forecasting of the technical condition of artificial structures based on the integration of automated monitoring data, a reference numerical model, and a library of defect scenarios. The purpose of the methodology is to improve the reliability of determining the actual technical condition of a structure and the accuracy of forecasting its future change and remaining useful life. The approach is based on representing the structural state as a multidimensional feature vector of the stress-strain state, followed by the application of taxonomic analysis methods to assess proximity to reference and defective conditions.

An integral indicator – the taxonomic condition index – is introduced to quantitatively evaluate the degree of structural degradation and to identify transition states at early stages of defect development. A classification algorithm is developed to identify the most probable dominant defect type (corrosion, fatigue crack, bearing malfunction), to provide scenario-based localization and to estimate its parameters.

A predictive framework based on time series analysis of diagnostic features is implemented, enabling forecasting of degradation processes and estimation of the remaining service life. It is shown that the proposed methodology provides a transition from threshold-based monitoring to multidimensional state assessment, improves the informativeness of monitoring data, and enhances decision-making in infrastructure risk management.

The practical significance of the study lies in the applicability of the proposed methodology for improving the reliability and safety of bridge structures through early defect detection and proactive maintenance planning.

1. Shestakova E. B. Digital Engineering. Fundamentals and practical examples: monograph. Moscow: IPR Media; 2024. 191 p. (In Russ.). 2. Efanov D. V. Functional testing and monitoring of railway automation and telemechanics devices: monograph. Emperor Alexander I St. Petersburg State Transport University. St. Petersburg; 2016. 171 p. (In Russ.).

2. Fedotov M. V. Predictive diagnostics of diesel locomotive equipment based on intelligent data analysis. Specialty 05.22.07 ‘Railway Rolling Stock, Train Traction, and Electrification’. Dissertation for the Degree of Candidate of Engineering. Emperor Alexander I St. Petersburg State Transport University. St. Petersburg; 2021. 205 p. (In Russ.).

3. Garanin M. A., Dmitriev V. V., Verstina Yu. D. Data-driven railway station management. Transport Business of Russia. 2025;(5):279–285. (In Russ.). EDN EYRAGY.

4. Kondrashova Yu. N., Tretyakov A. M., Shalimov A. V. Forecasting for overhead power transmission lines using predictive analytics. Bulletin of the North Caucasus Federal University. 2024;(100):20–30. (In Russ.). DOI 10.37493/2307-907X.2024.1.2.

5. Levin V. M., Boyarova D. A. Distributed system for predictive condition monitoring of electrical grid equipment based on Time-to-Failure. Proceedings of Higher Educational Institutions. Energy Sector Problems. 2025;27(3):123–134. (In Russ.). DOI 10.30724/1998-9903-2025-27-3-123-134.

6. Volkov I. A., Bobin K. N. Methodology for predictive forecasting of defects during aircraft technical operation. Science. Industry. Defense. Proceedings of the XXIV All-Russian Scientific and Technical Conference: in 4 volumes. Edited by A. V. Guskov A.V. Novosibirsk; 2023. P. 216–218. (In Russ.). EDN LJQXMK.

7. Schmidt A. A., Kosyrev A. V. Analysis of the scientific and methodological framework for diagnostics, control, monitoring, and forecasting the technical condition of military communication equipment. Communication Equipment Technology. 2023;(164):81–92. (In Russ.). DOI 10.24412/2782-2141-2023-4-81-92.

8. Zakharov O. V., Zakharov I. V., Bocharov N. V. Use of predictive analytics and machine learning to forecast accidents during oil and gas well construction. Modern Problems of Mechanical Engineering. Proceedings in 2 parts. Gomel; 2025. P. 163–167. (In Russ.). EDN LBFKAA.

9. Pomelov V. N., Andreev V. V. Development of a methodology for forecasting and verifying hydraulic resistance in channels of various geometries based on a predictive model. Nuclear Technologies: From Research to Implementation. Proceedings of the Scientific and Practical Conference. 2018. P. 42–43. (In Russ.). EDN VNRVST.

10. Aung Ch. M., Portnov E. M., Podoprigora V. D. Development of a methodology for predictive reliability analysis of electrical devices. Prospects of Science. 2025;(189):64–70. (In Russ.). EDN LTYZYY.

11. Popova E. S., Nefedov A. V. Integration of the step-by-step state forecasting methodology for complex technical objects into artificial intelligence systems. Artificial Intelligence. Theory and Practice. 2025;(12):87–89. (In Russ.). EDN WXRKPV.

12. Bushuev S. V., Uskova M. L., Popov A. N. Impact of technical diagnostics and monitoring systems on the reliability of railway automation and telemechanics devices during operation. Transport of the Urals. 2014;(42):68–72. (In Russ.). EDN SVNLDD.

13. Donets N. A., Afanasyev V. S. Assessment of the economic efficiency of monitoring the technical condition of bridge structures. Part 1. Transport Construction. 2016. No. 1. P. 15–17. (In Russ.). EDN VOOPVT.

14. Donets N. A., Afanasyev V. S. Economic efficiency of monitoring the technical condition of bridge structures. Part 2. Transport Construction. 2016;(2):2–4. (In Russ.). EDN VOOPYV.

15. Efanov D. V. Emergence and development prospects of functional control and monitoring systems for railway automation and telemechanics devices. Automation in Transport. 2016;2(1):124–148. (In Russ.). EDN VXJDHV.

16. Yashnov A. N. Methodology for end-to-end monitoring of the technical condition of bridge structures throughout their lifecycle. Specialty 2.1.8 ‘Design and construction of roads, subways, airfields, bridges, and transport tunnels’. Dissertation for the degree of Doctor of Engineering. Siberian Transport University. Novosibirsk; 2023. 376 p. (In Russ.).

17. Gusev G. N. Sensor degradation in an intelligent deformation monitoring system and a method for its diagnosis. Mechanics of Deformable Solids in Materials and Structures Design. Perm; 2024. P. 136–137. (In Russ.). EDN CLOJBF.

18. Makhonko A. A., Lazarev Yu. G., Antonyuk A. A. Technical aspects of accelerometer operation within the structural health monitoring system of the cable-stayed bridge over the Petrovsky Canal (part of the Western High-Speed Diameter Highway in St. Petersburg). Innovative Transport Systems and Technologies. 2024;10(3):401–418. (In Russ.). DOI 10.17816/transsyst630992.

19. Kochetkov A. V., Valiev Sh. N. Risk-based approach to bridge operation. Transport of the Russian Federation. 2024;(113):25–29. (In Russ.). EDN: JIQEXA.

20. Makhonko A. A., Lazarev Yu. G. Performance assessment of the structural health monitoring system for the cable-stayed bridge over the Petrovsky Canal (part of the Western High-Speed Diameter Highway in St. Petersburg). Putevoy Navigator. 2025;(88);28–34. (In Russ.). EDN ZQXSOZ.

21. Bely A. A., Pavlov E. I. Reliability of monitoring systems for transport and civil infrastructure facilities. Innovative Transport Systems and Technologies. 2026:12(1):76–95. (In Russ.). DOI 10.17816/transsyst701828. 23. Osetinsky O. V., Bely A. A., Antonyuk A. A., Osadchy G. V. Features and modern methods for monitoring the technical condition of artificial structures with railway truss spans. The Siberian Transport University Bulletin. 2024;(71):55–65. (In Russ.). DOI 10.52170/1815-9265_2024_71_55.