Method for comprehensive assessment of the technical condition of marine diesel engines using multidimensional analysis

The research focuses on developing a comprehensive method for assessing the technical condition of marine diesel engines using multidimensional analysis. In the context of tightening environmental standards and increasing reliability requirements for diesel engines, the development of comprehensive approaches that provide an integral assessment of their technical condition during the transition to predictive maintenance systems is relevant. The main problem addressed in this work is the absence of a comprehensive approach that enables the integration of disparate data from heterogeneous diagnostic systems into a single objective assessment of the technical condition of marine diesel engines. The object of the research is the processes of diagnosing marine diesel engines, and the subject is the existing methods for comprehensive assessment of their technical condition. The aim of the study is to develop a method that ensures an integral assessment and operational visualization of the technical condition of a marine diesel engine, provides a quantitative evaluation of its degree of degradation, enables objective comparison of different marine diesel engines, and formalizes decisions regarding the need for repair. To achieve this aim, the task of coordinating heterogeneous diagnostic features (parametric, vibroacoustic, oil analysis data, etc.) characterized by different units of measurement and time scales is addressed. The proposed approach is based on multidimensional analysis. The assessment procedure includes classification of diagnostic parameters, their linear normalization to a unified dimensionless scale, and transformation of the multidimensional diagnostic space into a two-dimensional visual model — a radar chart. For quantitative evaluation, the area of the chart is calculated and modified by introducing weighting coefficients that reflect the significance of each parameter; additionally, coefficients characterizing wear asymmetry and uniformity of unit degradation are introduced. The integral coefficient of technical condition is defined as the ratio of the chart area of the engine under study to the area of a reference chart constructed using reference parameter values. The developed mathematical apparatus and applied method allow calculation of the integral indicator (for example, 39.47 %, corresponding to an unsatisfactory condition) and visual identification of the most degraded units based on geometric parameters of the chart. The proposed method enables the integration of heterogeneous diagnostic parameters into a single integral indicator and supports the transition from scheduled preventive maintenance to condition-based maintenance, thereby improving safety, reliability, and economic efficiency of marine power plants and other sources of mechanical energy.

1. Onischenko, I. S. “Review of the development of requirements to ensure the safe operation of inland waterway vessels.” Vestnik gosudarstvennogo universiteta morskogo i rechnogo flota imeni admirala S. O. Makarova 17.1 (2025): 75–85. DOI: 10.21821/2309-5180-2025-17-1-75-85.

2. Tian, X., H. Gan and Y. Liu. “Construction of Knowledge Graph for Marine Diesel Engine Faults Based on Deep Learning Methods.” Journal of Marine Science and Engineering 13.4 (2025). DOI: 10.3390/jmse13040693.

3. Medvedev, V. V., V. V. Gavrilov and S. N. Kiselev. “Review and analysis of the possibility of various methods of increasing the energy efficiency of vessels.” Marine Intelligent Technologies 2–1(40) (2018): 94–103.

4. Afanaseva, O., D. Pervukhin and A. Khatrusov. “Vibration- Based Condition Monitoring of Diesel Engines in Industrial Energy Applications: A Scoping Review.” Energies 18.21 (2025). DOI: 10.3390/en18215717.

5. Barkova, N. A. and D. V. Grischenko. “Osnovnye napravleniya razvitiya vibratsionnoy diagnostiki sudovykh mashin.” Aktual’nye problemy morskoy energetiki: materialy shestoy mezhdunarodnoy mezhotraslevoy nauchno- tekhnicheskoy konferentsii, 16–17 fevralya 2017 g. Sankt-Peterburg: SPbGMTU, 2017: 24–27.

6. Grischenko, D. V. “Avtomaticheskaya obrabotka uzkopolosnykh spektrov vibratsii sudovykh mashin v tselyakh vydeleniya diagnosticheski znachimykh komponent.” Marine Intelligent Technologies 4–2(34) (2016): 8–13.

7. Radi, J., M. Šarić and A. Rubić. “Spectral- Based Fault Detection Method in Marine Diesel Engine Operation.” Sensors 25.18 (2025). DOI: 10.3390/s25185669.

8. Mathew, S. K. and Y. Zhang. “Acoustic- Based Engine Fault Diagnosis Using WPT, PCA and Bayesian Optimization.” Applied Sciences 10.19 (2020). DOI: 10.3390/app10196890.

9. Tuzov, L. V., O. K. Bezyukov and O. V. Afanas’eva. Vibratsiya sudovykh dvigateley vnutrennego sgoraniya. Sankt-Peterburg: Federal’noe gosudarstvennoe avtonomnoe obrazovatel’noe uchrezhdenie vysshego obrazovaniya “Sankt-Peterburgskiy politekhnicheskiy universitet Petra Velikogo”, 2012: 348.

10. Yang, X., X. Bi et al. “A Multiple Attention Convolutional Neural Networks for Diesel Engine Fault Diagnosis.” Sensors 24.9 (2024). DOI: 10.3390/s24092708.

11. Erofeev, P. A., V. A. Zhukov and S. G. Chernyy. “Classification of modern methods for improving the working process of marine diesel engine.” Vestnik gosudarstvennogo universiteta morskogo i rechnogo flota imeni admirala S. O. Makarova 12.4 (2020): 765–774. DOI: 10.21821/2309-5180-2020-12-4-765-774.

12. Zhukov, V. A., A. A. Butsanets, V. V. Gavrilov and S. A. Scherban. “Monitoring systems and diagnostics of ship power plant components.” Marine Radioelectronics 1(75) (2021): 22–27.

13. Kochergin, V. I., S. P. Glushkov and E. S. Zinchenko. “Using the thermodynamic processes features to assess the diesel power plants technical condition.” Vestnik gosudarstvennogo universiteta morskogo i rechnogo flota imeni admirala S. O. Makarova 16.1 (2024): 141–153. DOI: 10.21821/2309-5180-2024-16-1-141-153.

14. Mazur, E. V., N. L. Velikanov and G. E. Anan’ev. “Development of the algorithm for a comprehensive methodology for assessing the technical condition of a marine propulsion system cylinder piston group based on the indicators of the oil system.” Vestnik of Astrakhan State Technical University. Series: Marine Engineering and Technologies 1 (2024): 72–83. DOI: 10.24143/2073-1574-2024-1-72-83.

15. Gerike, P. B. and A. G. Nikitin. “Vibration- based diagnostics of centrifugal pumps.” Bulletin of Research Center For Safety in Coal Industry (Industial Safety) 4 (2020): 83–89.

16. Ariefjew, I. B. “Graph-analytical method for assessing the state of the object being diagnosed.” Russian Journal of Logistics & Transport Management 5.1 (2020): 10–18.

17. Kulagin, A. V. “Diagnosing the state of marine diesel engines by probabilistic fault recognition method.” Russian Journal of Water Transport 69 (2021): 109–122. DOI: 10.37890/jwt.vi69.220.