Optimisation of cylinder lubrication feed rates for slow-speed marine diesel engines based on image deep learning

• Autorzy: Zhao Enrui , Zhang Guichen , Han Bing , Li Qiuyu

Identyfikatory

DOI

10.2478/pomr-2025-0022

• Języki publikacji: EN

Abstrakty

EN

To solve the problems of low accuracy and the significant impact of human factors when manually adjusting the oil feed rate (FR) and base number (BN) of the cylinder oil in a marine slow-speed diesel engine, a new method for optimising cylinder lubrication adjustments based on image deep learning is proposed. This method involves inspecting the wear and carbon deposition on the inner surface of the cylinder liner and the piston ring surface through the scavenging port. Images captured during an inspection are normalised, clustered and segmented, and features are extracted to create a comprehensive cylinder lubrication image database. Then, based on the HU invariant moment and HSV colour space, the images are fused and similarity matched, and image search software is developed. This approach addresses the randomness and significant errors that are often associated with the manual adjustment of the cylinder oil FR. The software is implemented to manage the cylinder lubrication on a very large crude carrier. The results demonstrate that the proposed optimisation method can achieve optimal control targets: the residual oil iron content is found to be below 25 ppm, the residual oil BN is above 30 mg KOH/g, and the cylinder liner wear rate is below 0.1 mm/1,000 h, thereby reducing the risk of excessive wear on the cylinder liner.

Słowa kluczowe

EN

marine main engine; cylinder lubrication; feed rate; image deep learning

• Wydawca: Gdańsk University of Technology, Faculty of Ocean Engineering & Ship Technology
• Czasopismo: Polish Maritime Research
• Rocznik: 2025
• Tom: nr 2
• Strony: 74--83
• Opis fizyczny: Bibliogr. 21 poz., rys., tab.

Twórcy

autor

Zhao Enrui

• Merchant Marine College, Shanghai Maritime University, Shanghai, China
• School of Navigation and Shipping, Shandong Jiaotong University, Weihai, China

• https://orcid.org/0009-0005-8139-6098

autor

Zhang Guichen

• Merchant Marine College, Shanghai Maritime University, Shanghai, China

• https://orcid.org/0000-0001-8123-2775

autor

Han Bing

• National Engineering Research Center of Shipping Control System, Shanghai, China

• https://orcid.org/0000-0002-3020-3015

autor

Li Qiuyu

• Merchant Marine College, Shanghai Maritime University, Shanghai, China

Bibliografia

• 1. Wei C, Chen X, Chen L, et al. Effects of pilot oil injection timing on combustion, covariance and knocking of a natural gas–diesel duel-fuel low-speed engine. Pol. Marit. Res. 2024, 31, 69-75. https://doi.org/ 10.2478/pomr-2024-0051.
• 2. Temizer İ. The combustion analysis and wear effect of biodiesel fuel used in a diesel engine. Fuel. 2020, 270, 117571. https://doi.org/10.1016/j.fuel.2020.117571.
• 3. Cihan O. Experimental and numerical investigation of the effect of fig seed oil methyl ester biodiesel blends on combustion characteristics and performance in a diesel engine. Energy Rep. 2021, 7, 5846-5856. https://doi.org/10.1016/j.egyr. 2021.08.180.
• 4. Włodzimierz K. Marine slow-speed engines’ cylinder oil lubrication feed rate optimization in real operational conditions. Energies, 2022, 15, 8378. https://doi.org/ 10.3390/en15228378.
• 5. Operation Data and Maintenance Instruction Manual, MC Series Engines Edition, 2014. Editor B&W Man. Retrieved from https://man-es.com/applications/projectguides/2stroke/content/printed/98-50mc.pdf.
• 6. Lejre K, Glarborg P, Christensen H, et al. Experimental investigation and mathematical modeling of the reaction between SO2(g) and CaCO3(s) containing micelles in lube oil for large two-stroke marine diesel engines. Chem. Eng. J. 2020, 388, 124188. https://doi.org/10.1016/j.cej. 2020.124188.
• 7. Prakash C. Modeling the root causes of engine friction loss: Transient elastohydrodynamics of a piston subsystem and cylinder liner lubricated contact. Appl. Math. Model. 2015, 39, 2234-2260. https://doi.org/10.1016/j.apm. 2014.10.011.
• 8. He Y, Zhou P, Xie L, et al. Design and experimental development of a new electronically controlled cylinder lubrication system for the large two-stroke crosshead diesel engines. Int. J. Engine Res. 2019, 20, 986-1000. https://doi. org/10.1177/ 1468087418824216.
• 9. Zhao B, Hu X, Li H, et al. A new approach for modeling and analysis of the lubricated piston skirt-cylinder system with multi-physics coupling. Tribol. Int. 2022, 167, 1-16. https://doi.org/ 10.1016/j.triboint.2021.107381.
• 10. Bernhaed F, Berhard S. Comprehensive multi-scale cylinder lubrication model for reciprocating piston compressors: From rigid-body dynamics to lubricant-flow simulation. Tribol. Int. 2023, 178, 1-13. https://doi.org/10.1016/j.triboint. 2022.108028.
• 11. Liu Y, Chan F, Wang D. Computer vision and deep learning: Using MATLAB and Python as tools. Beijing, BJ: Publishing House of Electronics Industry; 2019.
• 12. Yang A, Zhi J, Yang K, et al. Computer vision technology based on sensor data and hybrid deep learning for security detection of blast furnace bearing. IEEE Sensors J. 2021, 21, 24982-24992. https://doi.org/10.1109/JSEN.2021.3077468.
• 13. Sajid K, Lee D. An adaptive dynamically weighted median filter for impulse noise removal. Eurasip J. Adv. Signal Process. 2023, 29, 100880. https://doi.org/10.1186 /s13634-017-0502-z.
• 14. Li Y, Li Z, Zheng C, et al. Adaptive weighted guided image filtering for depth enhancement in shape-from-focus. Pattern Recogn. 2022, 131, 108900. https://doi.org/10.48550/arXiv. 2201.06823.
• 15. Zhang J, Fan S, Lu G, et al. Wall thinning quantification with a lift-off distance for ferromagnetic structures using pulsed ECT equipped with ICA-Gauss filter and Hough Transform. NDT & E Int. 2025, 149, 103272. https://doi.org/10.1016/j.ndteint. 2024.103272.
• 16. Suvanthini T, Arachchige S, Nisha S, et al. Proximally sensed RGB images and color indices for distinguishing rice blast and brown spot diseases by k-means clustering: Towards a mobile application solution. Smart Agric. Tech. 2024, 9, 100532. https://doi.org/10.1016/j.atech. 2024.100532.
• 17. Qi K, Zhang H, Zheng Y, et al. Stripe segmentation of oceanic internal waves in SAR images based on Gabor transform and K-means clustering. Oceanologia 2023, 65(4), 548-555. https://doi.org/10.1016/j.oceano.2023.06.006.
• 18. Bieniek A, Moga A. An efficient watershed algorithm based on connected components. Pattern Recognition 2000, 33(6), 907-916. https://doi.org/10.1016/ S0031-3203(99)0011754-5.
• 19. Amal H, Jaouad E, Mostafa J. Rotation scaling and translation invariants by a remediation of Hu’s invariant moments. Multimed. Tools Appl. 2020, 79, 14225–14263. https://doi.org/ 10.1007/s11042-020-08648-5.
• 20. Meng W, He Z, Zha L, et al. Image-free Hu invariant moment measurement by single-pixel detection. Optics & Laser Tech. 2025, 181, 111581. https://doi.org/10.1016/j.optlastec. 2024.111581.
• 21. MAN Energy Solutions Service Letter: SL2023-738/IKCA. Sampling of scavenge drain oil Adjust feed rate factor in service, and monitor piston ring and cylinder liner wear. June 2023.

Uwagi

1. W pdf błędny nr Orcid dla autora Li Qiuyu.

2. Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki i promocja sportu (2025).