Received 05.05.2025, Revised 22.07.2025, Accepted 28.08.2025

Development of a technical condition assessment algorithm for complex systems based on probabilistic failure estimation

Vladimir Vychuzhanin, Alexey Vychuzhanin

This study proposed an integrated algorithm for assessing the technical condition of ship power plants, combining case-based reasoning (CBR), Bayesian networks, Markov processes, and cognitive simulation modelling. The algorithm was designed to enhance the accuracy and adaptability of diagnostics under conditions of uncertainty, limited data, and dynamic operational environments. The diagnostic process followed a multi-stage architecture that included the retrieval of historical failure cases, probabilistic correction based on interdependencies among components, modelling of component degradation over time, and adaptive scenario analysis. Each component of the algorithm plays a distinct role: CBR provides analogies to previously observed failures; Bayesian networks quantify probabilistic links between interrelated faults; Markov chains model the temporal degradation of equipment and estimate transition probabilities between operational states; and cognitive modelling allows the generation and testing of rare or cascading failure scenarios under variable conditions. The integration of these elements ensures that the algorithm dynamically updates failure probabilities and adapts to changing operational data. Simulation results demonstrated several improvements: the average prediction error for remaining useful life of components was reduced from 9% to 5.7%; the accuracy in identifying rare and cascading failures increased by 18% due to the use of cognitive modelling; and Bayesian correction reduced false positive diagnoses by 7.2% compared to baseline CBR systems. Overall, the predicted failure probability for 25,000 hours of operation was reduced from 83% (Bayesian-only model) to 68% with full model integration. The practical significance of the proposed algorithm lies in its ability to improve predictive maintenance planning, reduce equipment downtime, and increase the operational reliability of complex marine engineering systems. The modular architecture also enables the adaptation of the algorithm to various types of industrial technical systems

predictive maintenance; probabilistic modelling; cognitive simulation; integration of diagnostic methods; adaptive technical solutions; expert systems; intelligent monitoring
9-19
Vychuzhanin, V., & Vychuzhanin, A. (2025). Development of a technical condition assessment algorithm for complex systems based on probabilistic failure estimation. Information Technologies and Computer Engineering, 22(2), 9-19. https://doi.org/10.31649/vitce/2.2025.09

References

[1] Abbas, A.N., Chasparis, G., & Kelleher, J.D. (2022). Interpretable hidden Markov model-based deep reinforcement learning hierarchical framework for predictive maintenance of turbofan engines. In R. Wrembel, J. Gamper, G. Kotsis, A.M. Tjoa & I. Khalil (Eds.), Big data analytics and knowledge discovery. DaWaK 2022. Lecture notes in computer science (Vol. 13428, pp. 133-148). Cham: Springer. doi: 10.1007/978-3-031-12670-3_12.

[2] Ademujimi, T., & Prabhu, V. (2021). Fusion-learning of Bayesian network models for fault diagnostics. Sensors, 21(21), article number 7633. doi: 10.3390/s21227633.

[3] Anantharaman, M., Khan, F., Garaniya, V., & Lewarn, B. (2014). A step-by-step approach for evaluating the reliability of the main engine lube oil system for a ship’s propulsion system. International Journalon Marine Navigationand Safety of Sea Transportation, 8(3), 367-371. doi: 10.12716/1001.08.03.06.

[4] Başhan, V., Yucesan, M., Gul, M., & Demirel, H. (2024). A fuzzy Bayesian network risk assessment model for analyzing the causes of slow-down processes in two-stroke ship main engines. Ships and Offshore Structures, 19(5), 670-686. doi: 10.1080/17445302.2024.2323889.

[5] Chen, M., Xia, J., Huang, R., & Fang, W. (2022). Case-based reasoning system for aeroengine fault diagnosis enhanced with attitudinal Choquet integral. Applied Sciences, 12(11), article number 5696. doi: 10.3390/app12115696.

[6] Corrales, M., Berti, S., Denel, B., Williamson, P., Aleardi, M., & Ravasi, M. (2025). Annealed Stein variational gradient descent for improved uncertainty estimation in full-waveform inversion. Geophysical Journal International, 241(2), 1088-1113. doi: 10.1093/gji/ggaf096.

[7] Garbatov, Y., & Georgiev, P. (2024). Markovian maintenance planning of ship propulsion system accounting for CII and system degradation. Energies, 17(16), article number 4123. doi: 10.3390/en17164123.

[8] Hostens, E., Eryilmaz, K., Vangilbergen, M., & Ooijevaa, T. (2024). Bayesian networks for remaining useful life prediction. Proceedings of the European Conference of the PHM Society, 8(1), 225-235. doi: 10.36001/phme.2024.v8i1.4019.

[9] ISO/IEC 31010:2019. (2019). Risk management – risk assessment techniques. ISO. Retrieved from https://cdn.standards. iteh.ai/samples/20731/fed109559624438c9350d9b18880016b/IEC-31010-2019.pdf.

[10] Krakhmalyov, O., Klitnoy, V., Zinchenko, O., Brusentsev, V., & Shelestova, A. (2024). Analysis and optimization of torsion shafts in the context of improving the strength and durability of a light armoured vehicle. Machinery & Energetics, 15(1), 65-75. doi: 10.31548/machinery/1.2024.65.

[11] Louvros, P., Stefanidis, F., Boulougouris, E., Komianos, A., & Vassalos, D. (2023). Machine learning and case-based reasoning for real-time onboard prediction of the survivability of ships. Journal of Marine Science and Engineering, 11(5), article number 890. doi: 0.3390/jmse11050890.

[12] Moon, H., Choi, J., & Cha, S. (2021). A multi-state Markov model to infer the latent deterioration process from the maintenance effect on reliability engineering of ships. ArXiv. doi: 10.48550/arXiv.2111.14368.

[13] Morato, P.G., Papakonstantinou, K.G., Andriotis, C.P., Nielsen, J.S., & Rigo, P. (2022). Optimal inspection and maintenance planning for deteriorating structural components through dynamic Bayesian networks and Markov decision processes. Structural Safety, 94, article number 102140. doi: 10.1016/j.strusafe.2021.102140.

[14] Nikpour, H., & Aamodt, A. (2021). Fault diagnosis under uncertain situations within a Bayesian knowledge-intensive CBR system. Progress in Artificial Intelligence, 10(3), 245-258. doi: 10.1007/s13748-020-00227-x.

[15] OREDA – offshore reliability data handbook (6th ed., Vol. 1). (2015). Trondheim: SINTEF.

[16] Park, Y., & Kim, H. (2024). Advanced design of naval ship propulsion systems utilizing battery-diesel-generator hybrid electric propulsion systems. Journal of Marine Science and Engineering, 12(11), article number 2034. doi: 10.3390/ jmse12112034.

[17] Poljak, I., Majnari , D., Mrzljak, V., & Lorencin, I. (2022). Condition-based maintenance of naval propulsion systems: A brief review. In International student scientific conference Ri-STEM-2022 (pp. 46-48). Rijeka: STEM.

[18] Vychuzhanin, V., & Vychuzhanin, A. (2025). Stochastic models and methods for diagnostics, assessment, and prediction of the technical condition of complex critical systems. Lviv-Torun: Liha-Pres. doi: 10.36059/978-966-397-457-6.

[19] Wang, J., Wang, Z., Stetsyuk, V., Ma, X., Gu, F., & Li, W. (2019). Exploiting Bayesian networks for fault isolation: A diagnostic case study of diesel fuel injection system. ISA Transactions, 86, 276-286. doi: 10.1016/j.isatra.2018.10.044.

[20] Wang, R., Chen, H., & Guan, C. (2021). A Bayesian inference-based approach for performance prognostics towards uncertainty quantification and its applications on the marine diesel engine. ISA Transactions, 112, 123-135. doi: 10.1016/j.isatra.2021.02.024.

[21] Zhang, Z., & Wu, L. (2024). Graph neural network-based bearing fault diagnosis using Granger causality test. Expert Systems with Applications, 242, article number 122827. doi: 10.1016/j.eswa.2023.122827.