G.V. Rybina¹, V.A. Tailakov², Ya.S. Napadailo³

¹⁻³National Research Nuclear University "MEPhI" (Moscow, Russia)

¹gvrybina@yandex.ru, ²vic7519@mail.ru, ³napadailo@skynapp.com

The paper presents a compositional hybrid fuzzy–neural cognitive model designed to support intelligent decision-making in two critical application domains: (i) fault diagnosis of wind turbine components and (ii) operational switching control in electrical substations. The proposed model integrates fuzzy cognitive maps with neural learning algorithms, thereby ensuring high interpretability, robustness to exogenous disturbances, and suitability for real-time deployment within a problem-oriented intelligent decision support system (IDSS).

The objective of the study is to evaluate the applicability and methodological advantages of the compositional model as a functional element of a real-time IDSS architecture for the diagnosis and control of complex technical systems (CTS) in the power industry. The considered CTS include wind turbine assemblies, where timely fault detection and location are required, as well as substation equipment, where operational switching must be executed under strict safety and reliability constraints.

The research outcomes comprise the development of a multilayer interpretable model based on fuzzy cognitive maps and augmented with adaptive linear and bilinear learning algorithms. The model enables continuous online adaptation, captures nonlinear dependencies among system variables, and explicitly incorporates external factors into the decision-making process. Experimental evaluation using real and synthetic datasets, including wind turbine condition-monitoring data and the IEEE 118-bus benchmark, demonstrates that the proposed model outperforms state-of-the-art approaches (LFCM, RNN, CNN) in diagnostic accuracy, decision latency, and computational efficiency.

The practical significance of the study lies in enhancing the reliability and operational resilience of IDSS for managing and diagnosing CTS under uncertainty. The model supports the ongoing digitalization of power-system operations and contributes to reducing failure risks and economic losses by enabling timely, context-aware decision support in real-time environments.

1. Rybina G.V. Intellektualnye sistemy: ot A do Ya. Seriya monografii v trekh knigakh. Kniga 2. Intellektualnye dialogovye sistemy. Dinamicheskie intellektualnye sistemy. M.: Nauchtekhlitizdat. 2015. 163 s. (in Russian)
2. Rybina G.V. Intellektualnye sistemy ot A do Ya. Seriya monografii v trekh knigakh. Kniga 1. Sistemy, osnovannye na znaniyakh. Integrirovannye ekspertnye sistemy. M.: Nauchtekhlitizdat. 2014. 224 s. (in Russian)
3. Bashlykov A.A., Eremeev A.P. Osnovy konstruirovaniya intellektualnykh sistem podderzhki prinyatiya reshenii v atomnoi energetike: Uchebnik. M.: INFRA-M. 2025. 351 s. (in Russian)
4. Lokhin V.M., Romanov M.P. Intellektualnye sistemy upravleniya – perspektivnaya platforma dlya sozdaniya tekhniki novogo pokoleniya. Vestnik MGTU MIREA. 2014. № 1(2). S. 1−24. (in Russian)
5. Osipov G.S. Metody iskusstvennogo intellekta. M.: FIZMATLIT. 2011. 296 s. (in Russian)
6. Rybina G.V. Osnovy postroeniya intellektualnykh sistem: uchebnoe posobie. M: Finansy i statistika; INFRA-M. 2010. 2014. 2021. 432 c. (in Russian)
7. Rybina G.V., Stepankov V.Yu., Grigorev A.A. Integratsiya modelei, metodov i programmnykh sredstv, sovmestno opredelyayushchikh logiku prinyatiya reshenii v dinamicheskikh intellektualnykh sistemakh. Neirokompyutery, razrabotka, primenenie. 2024. T. 26. № 5. S. 57−71. (in Russian)
8. Napadailo Ya.S., Tailakov V.A., Rybina G.V. Interpretiruemyi mnogosloinyi klassifikator na osnove nechetko-neirosetevoi kognitivnoi modeli v zadachakh tekhnicheskoi diagnostiki. Dvadtsat vtoraya Natsionalnaya konf. po iskusstvennomu intellektu s Mezhdunar. uchastiem KII-2025 (Sankt-Peterburg, 06-10.10.2025 g.). Trudy konf. V 3‑kh tomakh. T. 2. SPb: Izd-vo FITs RAN. 2925. S. 86−96. (in Russian)
9. Zakharova A.A., Podvesovskii A.G., Isaev R.A. Nechetkie kognitivnye modeli v upravlenii slabostrukturirovannymi sotsialno-ekonomicheskimi sistemami. Informatsionnye i matematicheskie tekhnologii v nauke i upravlenii. 2020. № 4 (20). S. 5−23. (in Russian)
10. Zagranovskaya A.V. Sistemnyi analiz na osnove nechetkikh kognitivnykh kart. Vestnik Rossiiskogo ekonomicheskogo universiteta imeni G.V. Plekhanova. 2018. № 4. S. 152−160. (in Russian)
11. Borisov V.V. Nechetkie kognitivnye modeli kak osnova dlya issledovaniya slozhnykh sistem i protsessov. Rechevye tekhnologii. 2020. № 1−2. S. 48−62. (in Russian)
12. Wang W., Wang Y., Han X. A dynamic failure mode and effect analysis for train systems failures risk assessment using FCM and prospect theory. Management System Engineering. 2022. V. 1. Article 8. doi: 10.1007/s44176-022-00008-x.
13. Karatzinis G.D., Apostolikas N.A., Boutalis Y.S., Papakostas G.A. Fuzzy Cognitive Networks in Diverse Applications Using Hybrid Representative Structures. International Journal of Fuzzy Systems. 2023. V. 25. P. 2534−2554. doi: 10.1007/s40815-023-01564-4.
14. Borisov V.V. Sistematizatsiya nechetkikh i gibridnykh nechetkikh modelei. Myagkie izmereniya i vychisleniya. 2020. T. 29. № 4. S. 98−120. (in Russian)
15. Kulinich A.A. Klassifikatsiya kognitivnykh kart i metody ikh analiza. Shestaya Mezhdunar. nauchno-tekhnich. konf. «Integrirovannye modeli i myagkie vychisleniya v iskusstvennom intellekte» (Kolomna, 2011 g.). Trudy konf. T. 1. M.: Fizmatlit. 2011. S. 124−135. (in Russian)
16. Boutalis Y., Theodoridis D., Kottas T., Christodoulou M.A. Theory and Applications of the Neurofuzzy and Fuzzy Cognitive Network Models. System Identification and Adaptive Control. Springer International Publishing. 2014. doi: 10.1007/978-3-319-06364-5.
17. Kosko B. Fuzzy Cognitive Maps. International Journal of Man-Machine Studies. 1986. V. 24 (1). P. 65−75. doi: 10.1016/S0020-7373(86)80040-2.
18. University of Washington. Power Systems Test Case Archive. [Online]. Available: https://labs.ece.uw.edu/pstca/.