Three-scenario analysis of fault diagnosis accuracy in complex technical systems
Vladimir Vychuzhanin, Alexey VychuzhaninThe purpose of this study was to perform a three-scenario comparative analysis of the accuracy of intelligent fault diagnosis in complex technical systems using ship power plants (SPPs) as a representative case. The research sought to determine which diagnostic configuration ensures the highest accuracy and robustness under varying operational conditions. Three methodological configurations were analysed: a baseline model based on Case-Based Reasoning (CBR); CBR enhanced with probabilistic analysis using Bayesian networks and Markov chains; and a comprehensive integration of CBR with probabilistic models and simulation modelling of cascading failures. Experiments were conducted under three typical operational scenarios – nominal mode, high-load mode, and limited diagnostic data – reflecting real maritime conditions. Standard classification accuracy metrics were employed, including Accuracy, Recall, and F1-score. The results showed that the basic CBR configuration achieves an average accuracy of 82-85% under nominal conditions but significantly loses efficiency when data are incomplete. Integration with probabilistic models improves metric stability, increasing accuracy to 88-90%. At the optimal configuration of method weights (CBR – αd = 0.6, probabilistic models – βd = 0.2, simulation modelling – γd = 0.2), the minimum diagnostic error of 6% was achieved, and diagnostic accuracy exceeded 93% even under noisy or incomplete data. Analysis of confusion matrices and error visualisations revealed that integrated configurations reduce the number of type II errors by approximately 35% compared to isolated approaches. Three-dimensional plots of accuracy dependence on component weights confirmed a stable maximum in the balanced-parameter zone and highlighted the significance of the simulation component under complex operational conditions. The obtained results allowed formulating practical recommendations for selecting diagnostic configurations: CBR + Bayesian Networks for stable modes and full integration for overload or data-limited scenarios. The proposed methodology is adaptable to other intelligent diagnostic systems operating under uncertainty, variable load, and incomplete information, including cyber-physical and industrial systems. It represents a universal and scalable framework for applied diagnostics requiring high accuracy, adaptability, and robustness
References
[1] Aburakhia, S., Myers, R., & Shami, A. (2022). A hybrid method for condition monitoring and fault diagnosis of rolling bearings with low system delay. IEEE Transactions on Instrumentation and Measurement, 71, article number 3519913. doi: 10.1109/TIM.2022.3198477.
[2] Brito, L.C., Susto, G.A., Brito, J.N., & Duarte, M.A.V. (2021). An explainable artificial intelligence approach for unsupervised fault detection and diagnosis in rotating machinery. ArXiv. doi: 10.48550/arXiv.2102.11848.
[3] Cui, Y., Sun, Y., Cui, J., Zhao, F., & Yuan, M. (2025). Digital twin for marine diesel engine: Enhancing predictive maintenance and operational efficiency. In CSAA/IET international conference on aircraft utility systems (AUS 2024). Xi’an: CSAA/IET.
[4] Daya, A.A., & Lazakis, I. (2023). Component criticality analysis for improved ship machinery reliability. Machines, 11, article number 737. doi: 10.3390/machines11070737.
[5] Fera, F., & Spandonidis, C. (2024). A fault diagnosis approach utilizing artificial intelligence for maritime power systems within an integrated digital twin framework. Applied Sciences, 14, article number 8107. doi: 10.3390/ app14188107.
[6] Hasan, A., Asfihani, T., Osen, O., & Bye, R.T. (2024). Leveraging digital twins for fault diagnosis in autonomous ships. Ocean Engineering, 292, article number 116546. doi: 10.1016/j.oceaneng.2023.116546.
[7] Li, Y., Chen, Y., Hu, Z., & Zhang, H. (2023). Remaining useful life prediction of aero-engine enabled by fusing knowledge and deep learning models. Reliability Engineering & System Safety, 229, article number 108869. doi: 10.1016/j. ress.2022.108869.
[8] Lu, C., Tao, L., Ma, J., Cheng, Y., & Ding, Y. (2024). Fault diagnosis and prognostics based on cognitive computing and geometric space transformation. New York: Springer. doi: 10.1007/978-981-99-8917-1.
[9] 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.
[10] Morato, P.G., Papakonstantinou, K.G., Andriotis, C.P., Nielsen, J.S., & Rigo, P. (2020). 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.
[11] Nguyen, B.L.H., Vu, T.V., Nguyen, T.-T., Panwar, M., & Hovsapian, R. (2023). Spatial-temporal recurrent graph neural networks for fault diagnostics in power distribution systems. IEEE Access, 11, 46039-46050. doi: 10.1109/ ACCESS.2023.3273292.
[12] Orhan, M., & Celik, M. (2024). A literature review and future research agenda on fault detection and diagnosis studies in marine machinery systems. Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 238(1), 3-21. doi: 10.1177/14750902221149291.
[13] Quality-One International. (n.d.). Fault Tree Analysis (FTA). Retrieved from https://quality-one.com/fta.
[14] Panagiotopoulou, V., Petriconi, E., Giglio, M., & Sbarufatti, C. (2025). Deep learning-based identification of shaft imbalance faults in rotating machinery using the NARX model. Journal of Vibration Engineering & Technologies, 13, article number 261. doi: 10.1007/s42417-025-01823-8.
[15] Rigas, S., Tzouveli, P., & Kollias, S. (2024). An end-to-end deep learning framework for fault detection in marine machinery. Sensors, 24(16), article number 5310. doi: 10.3390/s24165310.
[16] Tang, W., Roman, D., Dickie, R., Robu, V., & Flynn, D. (2020). Prognostics and health management for the optimization of marine hybrid energy systems. Energies, 13(18), article number 4676. doi: 10.3390/en13184676.
[17] Ture, B.A., Akbulut, A.H., Zaim, A.H., & Çatal, C. (2023). Stacking-based ensemble learning for remaining useful life estimation. Soft Computing, 28, 1337-1349. doi: 10.1007/s00500-023-08322-6.
[18] Vychuzhanin, V., & Vychuzhanin, A. (2025). Intelligent diagnostics of ship power plants: Integration of case-based reasoning, probabilistic models, and ChatGPT. A universal approach to fault diagnosis and prognostics in complex technical systems. Lviv-Torun: Liha-Pres. doi: 10.36059/978-966-397-516-0.
[19] Vychuzhanin, V., Rudnichenko, N., Boyko, V., Shibaeva, N., & Konovalov, S. (2016). Devising a method for the estimation and prediction of technical condition of ship complex systems. Eastern-European Journal of Enterprise Technologies, 84(6/9), 4-11. doi: 10.15587/1729-4061.2016.85605.
[20] Xia, T., Han, D., Jiang, Y., Shao, Y., Wang, D., Pan, E., & Xi, L. (2024). Remaining useful life estimation based on selective ensemble of deep neural networks with diversity. Advanced Engineering Informatics, 62, article number 102608. doi: 10.1016/j.aei.2024.102608.
[21] Zhang, Y., Zhu, W., Jin, C., & Liang, Z. (2022). Hybrid modeling and simulation for shipboard power system considering high-power pulse loads integration. Journal of Marine Science and Engineering, 10, article number 1507. doi: 10.3390/ jmse10101507.