Journal: Volume 30, No. 3, 2025
Pages: 80 – 92
DOI: https://doi.org/10.62660/bcstu/3.2025.80
780 Views

Adaptive similarity assessment metric for intelligent failure diagnostics in ship power plants

Vladimir Vychuzhanin, Alexey Vychuzhanin
Received 18.04.2025
Revised 03.08.2025
Accepted 15.09.2025

Abstract

Prompt and accurate diagnosis of failures in ship power plants (SPPs) is essential for ensuring maritime safety, minimising operational risks, and optimising maintenance strategies. With increasing system complexity, heterogeneous data sources, and limited historical failure records, conventional diagnostic methods often prove insufficient, especially in scenarios involving rare or ambiguous faults. The purpose of this study was to develop an interpretable, adaptive, and probabilistically grounded methodology for assessing similarity between failure cases within SPPs for use in intelligent decision support systems. The proposed method integrates Euclidean, Jaccard, and logistic similarity metrics with Bayesian inference, temporal degradation modelling, frequency-based weight correction, and contextual smoothing of affected subsystems. The model employs L-BFGS-B optimisation to automatically adjust metric weights according to diagnostic relevance. Numerical experiments based on synthetic case data revealed high classification accuracy: 96% for failures related to cooling system overheating, 84% for bearing degradation cases, and 92% for fuel supply irregularities. Even with a 40% reduction in training data volume, the performance drop did not exceed 7%, indicating strong resilience to data sparsity. The visualisation of decision boundaries demonstrated the model’s ability to distinguish overlapping failure classes while preserving semantic interpretability. Weight optimisation results identified “failure type” as the dominant factor, while “risk category” and “affected subsystems” had negligible impact and were excluded. Bayesian aggregation further improved the credibility of diagnostic conclusions by combining local similarity with global statistical priors. The developed methodology can be effectively applied by marine engineers, ship operators, and developers of intelligent diagnostic platforms for fault detection, root cause analysis, and predictive maintenance under conditions of uncertainty and incomplete information. Its modular structure also allows extending it to other complex technical domains beyond SPPs

Keywords

decision support system; Bayesian aggregation; adaptive weight coefficients; case-based failure analysis; probabilistic metric; similarity of technical conditions

References

  1. Amin, K., Kapetanakis, S., Polatidis, N., Althoff, K.-D., & Dengel, A. (2020). DeepKAF: A heterogeneous CBR & deep learning approach for NLP prototyping. In 2020 International conference on innovations in intelligent systems and applications (INISTA) (pp. 1-7). Novi Sad. doi: 10.1109/INISTA49547.2020.9194679.
  2. Chen, M., Qu, R., & Fang, W. (2022). Case-based reasoning system for fault diagnosis of aero-engines. Expert Systems with Applications, 202, article number 117350. doi: 10.1016/j.eswa.2022.117350.
  3. Chen, Z., Xu, J., Alippi, C., Ding, S.X., Shardt, Y., Peng, T., & Yang, C. (2021). Graph neural network-based fault diagnosis: A review. ArXiv. doi: 10.48550/arXiv.2111.08185.
  4. Dubchak, L., Sachenko, A., Bodyanskiy, Y., Wolff, C., Vasylkiv, N., Brukhanskyi, R., & Kochan, V. (2024). Adaptive neuro-fuzzy system for detection of wind turbine blade defects. Energies, 17(24), article number 6456. doi: 10.3390/en17246456.
  5. Jimenez-Diaz, G., & Díaz-Agudo, B. (2024). Visualization of similarity models for CBR comprehension and maintenance. In Case-based reasoning research and development (ICCBR 2024) (pp. 67-80). Merida: Springer. doi: 10.1007/978-3-031-63646-2_5.
  6. Krüger, M. (2023). Comparative analysis of text-based CBR algorithms for cybercrime profiling investigations. In Lernen, wissen, daten, analysen (LWDA) 2023 (pp. 359-371). Marburg: CEUR Workshop Proceedings.
  7. Leake, D., Ye, X., & Crandall, D. (2021). Supporting case-based reasoning with neural networks: An illustration for case adaptation. In AAAI 2021 spring symposium on combining machine learning and knowledge engineering (AAAI-MAKE 2021). California: Palo Alto.
  8. Lin, N., Liu, H., Fang, J., Zhou, D., & Yang, A. (2023). An interpretability framework for similar case matching. ArXiv. doi: 10.48550/arXiv.2304.01622.
  9. Mathisen, B.M., Aamodt, A., Bach, K., & Langseth, H. (2020). Learning similarity measures from data. ArXiv. doi: 10.48550/arXiv.2001.05312.
  10. Mustyala, S., & Bisi, M. (2025). Ensembling harmony search algorithm with case-based reasoning for software development effort estimation. Cluster Computing, 28, article number 97. doi: 10.1007/s10586-024-04858-w.
  11. Neykov, N., & Stefanova, S. (2023). Using case-based reasoning in system diagnostics and maintenance. In Proceedings of seventh international congress on information and communication technology (pp. 345-359). Singapore: Springer. doi: 10.1007/978-981-19-2394-4_28.
  12. Ren, S., Gui, F., Zhao, Y., Zhan, M., & Wang, W. (2020). An effective similarity determination model for case-based reasoning in support of low-carbon product design. Advances in Mechanical Engineering, 12(10). doi: 10.1177/1687814020970313.
  13. Serrà, J., & Arcos, J.Ll. (2014). An empirical evaluation of similarity measures for time series classification. Knowledge-Based Systems, 67, 305-314. doi: 10.1016/j.knosys.2014.04.035.
  14. Valdez-Ávila, M.F., Bermejo-Sabbagh, C., Diaz-Agudo, B., Orozco-del-Castillo, M.G., & Recio-Garcia, J.A. (2023). CBR-fox: A case-based explanation method for time series forecasting models. In Case-based reasoning research and development. ICCBR 2023 (pp. 192-207). Cham: Springer. doi: 10.1007/978-3-031-40177-0_13.
  15. Virtanen, P., et al. (2020). SciPy 1.0: Fundamental algorithms for scientific computing in Python. Nature Methods, 17(3), 261-272. doi: 10.1038/s41592-019-0686-2.
  16. 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: 10.36059/978-966397-457-6.
  17. Xu, H., Wei, Y., Cai, Y., & Xing, B. (2023). Knowledge graph and CBR-based approach for automated analysis of bridge operational accidents: Case representation and retrieval. PLoS ONE, 18(11), article number e0294130. doi: 10.1371/journal.pone.0294130.
  18. Ye, J. (2017). Single-valued neutrosophic similarity measures based on cotangent function and their application in the fault diagnosis of steam turbine. Soft Computing, 21(3), 817-825. doi: 10.1007/s00500-015-1818-y.
  19. Ye, X., Leake, D., Wang, Y., Zhao, Z., & Crandall, D. (2024). Towards network implementation of CBR: Case study of a neural network K-NN algorithm. In Case-based reasoning research and development. ICCBR 2024. Lecture notes in computer science (pp. 354-370). Cham: Springer. doi: 10.1007/978-3-031-63646-2_23.
  20. Zeng, T., Bao, R., Qin, Y., Sun, X., Gao, Y., Cheng, L., Hou, P., Sang, H., Ma, L., & Zhou, X. (2025). MSFF-CBR: Case-based reasoning technology for adaptive multi-information fusion fault diagnosis. Measurement Science and Technology, 36(4), article number 045111. doi: 10.1088/1361-6501/adc474.
  21. Zuber, M., & Sirdey, R. (2021). Efficient homomorphic evaluation of k-NN classifiers. Proceedings on Privacy Enhancing Technologies 2021, 2, 111-129. doi: 10.2478/popets-2021-0020.

Suggested citation

Vychuzhanin, V., & Vychuzhanin, A. (2025). Adaptive similarity assessment metric for intelligent failure diagnostics in ship power plants. Bulletin of Cherkasy State Technological University, 30(3), 80-92. https://doi.org/10.62660/bcstu/3.2025.80