Fault diagnosis based on improved information entropy and 1DCNN for marine turbocharger rotor with variable speed

• Autorzy: Hu Lei , Hu Haoran , Hu Nao , Liu Luyuan , Dong Fei , Yang Jianguo , Zhong Jiahong

Identyfikatory

DOI

10.2478/pomr-2025-0040

• Języki publikacji: EN

Abstrakty

EN

Due to the lack of a standardised method for determining representative locations for measuring points, it is difficult to select sensitive data on turbocharger rotor faults. In addition, the uncertainty in the feature parameters used for diagnosis under variable rotational speeds leads to low accuracy in fault identification. To address these issues, vibration signals from a turbocharger rotor under various conditions are obtained in this study via a fault simulation test, and a fault diagnosis method for rotor faults under variable speed conditions is proposed based on a sensitivity and multi-dimensional feature analysis of measurement points. The sensitivity of the improved and traditional information entropy is evaluated using a variance analysis across the measurement points, and the most effective vibration measurement points are selected based on the improved information entropy. The effective characteristic parameters of the vibration signals at multiple measurement points are analysed and extracted, and the numer of dimensions of the feature parameters is reduced using the t-distributed stochastic neighbour embedding (t-SNE) method. Faults in the turbocharger rotor at the different speeds are classified using a one-dimensional convolutional neural network (1DCNN), and the arithmetic ability of the diagnostic algorithm is evaluated. The results demonstrate that the proposed methods of selecting measurement points and fault diagnosis can effectively identify rotor faults at different degrees and various speeds: the accuracy of fault diagnosis is 99.85%, and the arithmetic ability is markedly enhanced compared with that of traditional methods.

Słowa kluczowe

EN

marine turbocharger; sensitivity analysis; variable speed; improved information entropy; feature fusion

• Wydawca: Gdańsk University of Technology, Faculty of Ocean Engineering & Ship Technology
• Czasopismo: Polish Maritime Research
• Rocznik: 2025
• Tom: nr 3
• Strony: 118--130
• Opis fizyczny: Bibliogr. 44 poz., rys., tab.

Twórcy

autor

Hu Lei

• Wuhan University of Technology, School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan, China

• https://orcid.org/0000-0003-3292-0090

autor

Hu Haoran

• Wuhan University of Technology, School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan, China

• https://orcid.org/0009-0008-5868-8377

autor

Hu Nao

• Wuhan University of Technology, School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan, China

• https://orcid.org/0000-0003-4094-3858

autor

Liu Luyuan

• Wuhan University of Technology, School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan, China

autor

Dong Fei

• Wuhan University of Technology, School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan, China

• https://orcid.org/0000-0001-6422-3199

autor

Yang Jianguo

• Wuhan University of Technology, School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan, China

autor

Zhong Jiahong

• Chongqing Jiangjin Shipbuilding Industry Co., Ltd, China

Bibliografia

• 1. Adamkiewicz A, Nikończuk P. An attempt at applying machine learning in diagnosing marine ship engine turbochargers. Eksploat. Niezawodn. 2022, vol. 24, no. 4, pp. 795–804. https://doi.org/10.17531/ein.2022.4.19
• 2. Nyongesa AJ, Park MH, Lee CM, et al. Experimental evaluation of the significance of scheduled turbocharger reconditioning on marine diesel engine efficiency and exhaust gas emissions. Ain. Shams. E. J. 2024, vol. 15, no. 8, p. 102845. https://doi.org/10.1016/j.asej.2024.102845
• 3. Liu M, Yao MF, Wang H. Optimized design and simulation of thermal efficiency of diesel engine based on combustion chamber and turbocharger matching. Internal Combustion Engineering 2021, vol. 42, no. 05, pp. 14–22. DOI: 10.13949/j.cnki.nrjgc.2021.05.003
• 4. Barelli L, Bidini G, Bonucci F. Diagnosis methodology for the turbocharger groups installed on a 1 MW internal combustion engine. Appl Energ 2009, vol. 86, no. 12, pp. 2721–2730. https://doi.org/10.1016/j.apenergy.2009.04.034
• 5. Aretakis N, Mathioudakis K, Kefalakis M, et al. Turbocharger unstable operation diagnosis using vibroacoustic measurements. J. Eng. Gas Turbines Power 2004, vol. 126, no. 4, pp. 840–847. https://doi.org/10.1115/1.1771686
• 6. Girtler J, Rudnicki J. Quantumness in diagnostics of marine internal combustion engines and other ship power plant machines. Pol Marit Res 2023 vol. 4, pp. 110–119. https://doi.org/10.2478/pomr-2023-0064
• 7. Puzdrowska P. Diagnostic information analysis of quickly changing temperature of exhaust gas from marine diesel engine. Part I: Single factor analysis. Pol Marit Res 2021, vol. 4, pp. 97–106. https://doi.org/10.2478/pomr-2021-0052
• 8. Varbanets R, Shumylo O, Marchenko A, et al. Concept of vibroacoustic diagnostics of the fuel injection and electronic cylinder lubrication systems of marine diesel engines. Pol Marit Res 2022, vol. 29, no. 4, pp. 88–96. https://doi.org/10.2478/pomr-2022-0046
• 9. Qian HY. Fault characteristic analysis and diagnosis study of turbocharger rotor-bearing system. Jiangsu University of Science and Technology, 2023. DOI: 10.27171/d.cnki.ghdcc.2022.000464
• 10. Chunyu Z, Xinyang Q, Haiyu Q, et al. Research on fault diagnosis method of turbocharger rotor based on Hu-SVM-RFE. J Mech 2023, vol. 39, pp. 344–351. https://doi.org/10.1093/jom/ufad028
• 11. Pan R, Lin X. The application of support vector machine on fault diagnosis of the diesel engine exhaust gas turbocharger. 2012 International Conference on Computer Distributed Control and Intelligent Environmental Monitoring. IEEE, 2012, pp. 701–704. https://doi.org/10.1109/CDCIEM.2012.171
• 12. Anwarsha A, Narendiranath Babu T. Intelligent fault detection of rotating machinery using long-short-term memory (LSTM) network. International Conference on Emerging Technologies and Intelligent Systems. Cham: Springer International Publishing, 2022, pp. 76–83. https://doi.org/10.1007/978-3-031-20429-6_8
• 13. Aljemely AH, Xuan J, Xu L, et al. Wise-local response convolutional neural network based on naive Bayes theorem for rotating machinery fault classification. Appl Intell 2021, vol 51, pp. 6932–6950. https://doi.org/10.1007/s10489-021-02252-2
• 14. Liu Y, Xu Y, Liu J, et al. A hydraulic turbine fault diagnosis method based on synchrosqueezed wavelet transform and SE-ResNet. Water 2025, vol. 17, no. 3, p. 447. https://doi.org/ 10.3390/w17030447
• 15. Liang P, Deng C, Wu J, et al. Intelligent fault diagnosis of rotating machinery via wavelet transform, generative adversarial nets and convolutional neural network. Measurement 2020, vol. 159, p. 107768. https://doi.org/10.1016/j.measurement.2020.107768.
• 16. Qiao NG. Fault diagnosis and health prediction of highspeed train transmission system based on multi-sensor fusion. Jilin University, 2019. https://doi.org/10.27162/d.cnki.gjlin.2019.000070
• 17. Xu WM, Zhang YC, Liu WG, et al. Fusion of vibration signals from multiple observation points of flood discharge sluice pier based on correlation function. Journal of Yangtze River Scientific Research Institute 2015, vol. 32, no. 11, pp. 110–114.
• 18. Varbanets R, Minchev D, Kucherenko Y, et al. Methods of real-time parametric diagnostics for marine diesel engines. Pol Marit Res 2024, vol. 31, no. 3, pp. 71–84. https://doi.org/10.2478/pomr-2024-0037
• 19. Canalle GK, Salgado AC, Loscio BF. A survey on data fusion: What for? In what form? What is next? J Intell Inf Syst 2021, vol. 57, no. 1, pp. 25–50. https://doi.org/10.1007/s10844-020-00627-4
• 20. Yin S, Wang G, Gao H. Data-driven process monitoring based on modified orthogonal projections to latent structures. Ieee T Contr Syst T 2015, vol. 24, no. 4, pp. 1480–1487. https://doi.org/10.1109/TCST.2015.2481318
• 21. Puzdrowska P. Diagnostic analysis of exhaust gas with a quick-changing temperature from a marine diesel engine Part II: Two factor analysis. Pol Marit Res 2023, vol. 3, no. 7, pp. 11–17. https://doi.org/10.2478/pomr-2023-0042
• 22. Varbanets R, Fomin O, Pištěk V, et al. Acoustic method for estimation of marine low-speed engine turbocharger parameters. J Mar Sci Eng 2021, vol. 9, no. 3, p. 321. https://doi.org/10.3390/jmse9030321
• 23. Dong F, Yang J, Cai Y, et al. Transfer learning-based fault diagnosis method for marine turbochargers. Actuators 2023, vol. 12, no. 4, p. 146. https://doi.org/10.3390/act12040146
• 24. Dong F, Yang J, Hu L, et al. Multi-objective matched synchrosqueezing chirplet transform for fault feature extraction from marine turbochargers. IEEE Access 2023, vol. 11, pp. 80702–80715. https://doi.org/10.1109/ACCESS.2023.3296689
• 25. Qiao Q, Wang HJ, Ma K, et al. Gas turbine rotor fault diagnosis based on improved DenseNet-ViT joint network and transfer learning. Journal of Electronic Measurement and Instrumentation 2024, vol 38, no. 11, pp. 40-47. https://doi.org/10.13382/j.jemi.B2407526
• 26. Zorich VA. Entropy in thermodynamics and in information theory. Probl Inform Transm 2022, vol. 58, no. 2, pp. 103–110. https://doi.org/10.1134/S0032946022020016
• 27. Gour G, Tomamichel M. Entropy and relative entropy from information-theoretic principles. Ieee T Inform Theory 2021, vol. 67, no. 10, pp. 6313–6327. https://doi.org/10.1109/TIT.2021.3078337
• 28. Nascimento WS, Maniero AM, Prudente FV, et al. Electron confinement study in a double quantum dot by means of Shannon entropy information. Physica B 2024, vol. 677, p. 415692. https://doi.org/10.1016/j.physb.2024.415692
• 29. Lin J, Chen Q. Application of the EEMD method to multiple faults diagnosis of gearbox. 2010 2nd International Conference on Advanced Computer Control. IEEE, 2010, vol. 2, pp. 395–399. https://doi.org/10.1109/ICACC.2010.5486649
• 30. Dibaj A, Ettefagh MM, Hassannejad R, et al. A hybrid finetuned VMD and CNN scheme for untrained compound fault diagnosis of rotating machinery with unequal-severity faults. Expert Syst Appl 2021, vol. 167, p. 114094. https://doi.org/10.1016/j.eswa.2020.114094
• 31. Ni Q, Ji JC, Feng K, et al. A fault information-guided variational mode decomposition (FIVMD) method for rolling element bearings diagnosis. Mech Syst Signal Pr 2022, vol. 164, p. 108216. https://doi.org/10.1016/j.ymssp.2021.108216
• 32. Wang H, Zhang C, Zhao P, Yan M, Jin, Y. Gas turbine shock measurement point optimization based on shock response analysis. Journal of Vibration and Shock 2025, vol. 44, no. 4, pp. 244–252. https://doi.org/10.13465/j.cnki.jvs.2025.04.026
• 33. Zhang Z, Wang Z, Yu F. Optimization of vibration sensor placement for ship aft using local linear embedding. Noise and Vibration Control 2025, vol. 45, no. 1, p. 294. https://doi.org/10.3969/j.issn.1006-1355.2025.01.046
• 34. Kammer DC. Sensor placement for on-orbit modal identification and correlation of large space structures. J Guid Control Dynam 1991, vol. 14, no. 2, pp. 251–259. https://doi.org/10.23919/ACC.1990.4791265
• 35. Greenacre M, Groenen PJF, Hastie T, et al. Principal component analysis. Nat Rev Method Prime 2022, vol. 2, no. 1, p. 100. https://doi.org/10.1038/s43586-022-00184-w
• 36. Gewers FL, Ferreira GR, Arruda HFD, et al. Principal component analysis: A natural approach to data exploration. Acm Comput Surv (CSUR) 2021, vol. 54, no. 4, pp. 1–34. https://doi.org/10.1145/3447755
• 37. Tomeo I, Markopoulos PP, Savakis A. Quantum annealing for robust principal component analysis. arXiv: 2501.10431, 2025. https://doi.org/10.48550/arXiv.2501.10431
• 38. Lahdhiri H, Taouali O. Reduced rank KPCA based on GLRT chart for sensor fault detection in nonlinear chemical process. Measurement 2021, vol. 169, pp. 108342. https://doi.org/10.1016/j.measurement.2020.108342
• 39. Zhong JH, Huang C, Zhong SC, et al. Remaining useful life of rolling bearing based on t-SNE. Journal of Mechanical Strength 2024, vol. 46, no. 04, pp. 969–976. https://doi.org/10.16579/j.issn.1001.9669.2024.04.028
• 40. Van der Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res 2008, vol. 9, no. 11, pp. 2579–2605.
• 41. Liang Z, Zhang L, Wang X. A novel intelligent method for fault diagnosis of steam turbines based on T-SNE and XGBoost. Algorithms 2023, vol. 16, no. 2, p. 98. https://doi.org/ 10.3390/a16020098
• 42. Liang K, Zhao HJ, Song WZ. Research on evaluation of internal combustion engine sound quality based on convolutional neural network. Chinese Internal Combustion Engine Engineering 2019, vol. 40, no. 02, pp. 67–75. https://doi.org/10.13949/j.cnki.nrjgc.2019.02.010
• 43. Zhang BW, Pang XY, Cheng BA, et al. Fault diagnosis method for aeroengine bearing based on PIRD-CNN. Journal of Vibration and Shock 2024, vol. 43, no. 18, pp. 201– 207+231. https://doi.org/10.13465/j.cnki.jvs.2024.18.022
• 44. China Machinery Industry Federation. Intelligent Services Predictive Maintenance Algorithm Measurement Method: GB/T43555-2023. Beijing: China Standard Press, 2023.