DEVELOPMENT OF AN INTELLIGENT SYSTEM FOR ENHANCING MARINE ENGINEER READINESS FOR THE OPERATION AND REPAIR OF INJECTORS WITH VISUALIZATION OF THEIR 3D MODELS
https://doi.org/10.33815/2313-4763.2024.1.28.134-151
Abstract
The problem of enhancing the readiness of marine engineers for the operation and repair of ship technical systems is relevant due to the difficulty of detecting faults and the need for timely diagnostics. The aim of this research is to develop and implement an intelligent system that improves marine engineer readiness by visualizing 3D models of injectors and using fuzzy diagnostic methods. The research includes the formation of a conceptual system description, the creation of a formal-logical structure of injector diagnostic rules based on symptoms, the development of 3D injector models, and decision-support software.
The research employed methods of machine learning, automation, and fuzzy logic to improve diagnostic accuracy. The main functional elements of the system include: data input, where symptoms of injector faults are entered as a set of parameters; rule evaluation, which assesses the input data based on threshold values to determine the severity levels of symptoms; recommendation generation, where the system automatically generates recommendations based on rule evaluation; visualization of membership functions through the construction of graphs for each diagnostic rule; and 3D modeling, which involves creating 3D models of injectors for visualizing damaged components and facilitating the diagnostic process.
Experiments have shown that the developed system reduces the risk of errors and increases the efficiency of injector repairs. Testing demonstrated that the speed of operations in injector repairs increased by 22.5%. The system automatically evaluates symptoms and generates recommendations for the marine engineer, ensuring timely fault detection.
The practical significance of the system lies in its ability to reduce the impact of human factors on the operation of ship technical systems, enhancing overall reliability and safety. The system ensures operational flexibility, allowing the marine engineer to visually identify damaged injector components. The implementation of the intelligent system contributes to reducing the risk of emergency situations and optimizing the repair process.
The theoretical significance lies in the introduction of new approaches to injector diagnostics using machine learning, automation, and 3D visualization. The use of fuzzy logic for symptom evaluation and recommendation generation ensures more accurate and reliable fault detection. The proposed methods can be adapted for diagnosing other components of ship technical systems, opening new prospects for further research.
Bibliography: 33 sources, 5 figures.
References
2. Nosov, P. S. (2023). Systemic approaches to rational management of func-tional marine technical systems and complexes // Журналу "Водний транспорт. Збірник наукових праць Державного університету інфраструктури та технологій". No 2(38). С. 80–95. doi.org/10.33298/2226-8553.2023.2.38.09.
3. Nosov, P., Koretsky, O., Zinchenko, S., Prokopchuk, Y., Gritsuk, I., Sokol, I., Kyrychenko, K. (2023). Devising an approach to safety management of vessel control through the identification of navigator’s state. Eastern-European Journal 1of Enterprise Technologies, 4 (3 (124)), 19–32. doi: https://doi.org/10.15587/1729-4061.2023.286156.
4. Nosov, P., Zinchenko, S., Plokhikh, V., Popovych, I., Prokopchuk, Y., Makarchuk, D., Mamenko, P., Moiseienko, V., & Ben, A. (2021). Development and experimental study of analyzer to enhance maritime safety. Eastern-European Journal of Enterprise Technologies, 4/3(112), 27–35. https://doi.org/10.15587/1729-4061.2021.239093.
5. Weng, Jinxian & Yang, Dong & Chai, Tian & Fu, Shanshan. (2019). Investigation of occurrence likelihood of human errors in shipping operations. Ocean Engineering. 182. 28–37. 10.1016/j.oceaneng.2019.04.083.
6. Yang, Xinduoji & Liu, Minghui & Wang, Xinxin & Hu, Bingyu & Liu, Meng & Wang, Xiaomin. (2024). Ship Network Traffic Engineering Based on Reinforcement Learning. Electronics. 13. 1710. 10.3390/electronics13091710.
7. Yang, Taiwei & Zhu, Hanhua & Fan, Shidong & Wu, Jie & Yuan, Junlang & Zheng, Liangyan. (2023). Research on Lubrication Characteristics of Ship Stern Bearings Considering Bearing Installation Errors. Lubricants. 11. 478. 10.3390/lubricants11110478.
8. Saragih, Jasman & Hasibuan, Arnawan & Engineering, Electrical & , Suwarno. (2020). Analysis of Damage to Ship MT. Delta Victory due to Human Error and Electricity with the Shel Method. 10.1109/ELTICOM50775.2020.9230475.
9. Yu, Cairui. (2023). Exploring the Current Status and Development of Condition Monitoring and Fault Diagnosis for Power Machinery of Engineering Ships. Applied Science and Innovative Research. 7. p62. 10.22158/asir.v7n3p62.
10. Sharko, Oleksandr & Yanenko, Artem. (2023). MODELING OF INTELIGENT SOFTWARE FOR THE DIAGNOSIS AND MONITORING OF SHIP POWER PLANT COMPONENTS USING MARKOV CHAINS. Science-based technologies. 59. 251–261. 10.18372/2310-5461.59.17946.
11. Wang, Ning & Hou, Xiaojun & Ma, Jikun & Yuan, Bingbing & Xin, Fuyan. (2024). Research on Big Data Intelligent System for Fault Diagnosis of Computer Aided Ship Power System. Frontiers in Computing and Intelligent Systems. 8. 65–69. 10.54097/11sgn708.
12. Wei, Zhiguo & Wu, Jun & Li, Zhe & Cheng, Shangfang & Yan, Xiaojiang & Wang, Shunsen. (2024). The Intelligent Layout of the Ship Piping System Based on the Optimization Algorithm. Applied Sciences. 14. 2694. 10.3390/app14072694.
13. Lan, Dan & Xu, Peilong & Nong, Jia & Song, Junkang & Zhao, Jie. (2024). Application of Artificial Intelligence Technology in Vulnerability Analysis of Intelligent Ship Network. International Journal of Computational Intelligence Systems. 17. 10.1007/s44196-024-00539-z.
14. Hao, Guozhu & Xiao, Wenhui & Huang, Liwen & Chen, Jiahao & Zhang, Ke & Chen, Yaojie. (2024). The Analysis of Intelligent Functions Required for Inland Ships. Journal of Marine Science and Engineering. 12. 836. 10.3390/jmse12050836.
15. Zhang, Jiale & Jiang, Jiawei & Zhang, Sijie & Zhang, Peng & Dong, Junwei & Sun, Ze. (2023). A Review of Research on Intelligent Engine Room Systems. Advances in Machinery, Materials Science and Engineering Application IX. 10.3233/ATDE230571.
16. li, Guiqin & Li, Yang & Lan, Jian & Zhu, Qiuyu & Lu, Hao & Mitrouchev, Peter. (2020). Development of the database for intelligent ship management system. IOP Conference Series: Materials Science and Engineering. 768. 042055. 10.1088/1757-899X/768/4/042055.
17. Orifice Plate Flow Measurement Principle and Formula URL: (https://engineerscommunity.com/t/orifice-plate-flow-measurement-principle-and-formula/6165).
18. Varbanets, Roman & Minchev, Dmytro & Savelieva, I. & Rodionov, A. & Mazur, T. & Psariuk, S. & Bondarenko, V. (2023). Enhanced diagnostic techniques for marine diesel engines: achieving imo decarbonization compliance. Internal Combustion Engines. 26–36. 10.20998/0419-8719.2023.2.04.
19. Zacharewicz, Marcin & Kniaziewicz, Tomasz. (2017). Mathematical modelling malfunctions of marine diesel engine. MATEC Web of Conferences. 118. 00001. 10.1051/matecconf/201711800001.
20. Minchev, Dmytro & Varbanets, Roman & Shumylo, Oleksandr & Zalozh, Vitalii & Aleksandrovska, Nadiia & Bratchenko, Pavlo & Thanh Hai, Truong. (2023). Digital Twin Test-Bench Performance for Marine Diesel Engine Applications. Polish Maritime Research. 30. 81–91. 10.2478/pomr-2023-0061.
21. Pekař, Miloslav. (2024). The Behaviour of Gases. 10.1007/978-3-031-60321-1_4.
22. Fu, Chao & Liang, Xiaoxia & Li, Qian & Lu, Kuan & Gu, Fengshou & Ball, Andrew & Zheng, Zhaoli. (2023). Comparative Study on Health Monitoring of a Marine Engine Using Multivariate Physics-Based Models and Unsupervised Data-Driven Models. Machines. 49. 557. 10.3390/machines11050557.
23. Zacharewicz, Marcin & Kniaziewicz, Tomasz. (2017). Mathematical modelling malfunctions of marine diesel engine. MATEC Web of Conferences. 118. 00001. 10.1051/matecconf/201711800001.
24. Monieta, Jan. (2023). Diagnosing Cracks in the Injector Nozzles of Marine Internal Combustion Engines during Operation Using Vibration Symptoms. Applied Sciences. 13. 9599. 10.3390/app13179599.
25. Wu, Qinran & Liang, Xingyu & Zhu, Zhijie & Cui, Lei & Liu, Teng. (2024). Numerical Simulation Research on Combustion and Emission Characteristics of Diesel/Ammonia Dual-Fuel Low-Speed Marine Engine. Energies. 17. 2960. 10.3390/en17122960.
26. Gharib, Hla & Kovács, György. (2024). Implementation and Possibilities of Fuzzy Logic for Optimal Operation and Maintenance of Marine Diesel Engines. Machines. 12. 425. 10.3390/machines120604.
27. Varbanets, Roman & Shumylo, Oleksandr & Marchenko, Andrii & Minchev, Dmytro & Kyrnats, Vladyslav & Zalozh, Vitalii & Aleksandrovska, Nadiia & Brusnyk, Roman & Volovyk, Kateryna. (2022). Concept of Vibroacoustic Diagnostics of the Fuel Injection and Electronic Cylinder Lubrication Systems of Marine Diesel Engines. Polish Maritime Research. 29. 88-96. 10.2478/pomr-2022-0046.
28. Zakaria, Zunita & Hassan, Latiffah & Sharif, Zawiyah & Ahmad, Norazah & Ali, Rohaya & Husin, Suraya & Abd Hazis, Nor & Mohamed Sohaimi, Norfitriah & Bakar, Shafini & Garba, Bashiru (2020). Analysis of Salmonella enterica Enteritidis isolates from chicken and chicken meat products using PFGE, and MLST. 10.21203/rs.3.rs-23038/v1.
29. Heywood J. B., “Internal Combustion Engine Fundamentals,” McGraw Hill, New York, 1988.
30. Hiroyasu, H., Kadota, T., & Arai, M. (1983). Development and Use of a Spray Combustion Modeling to Predict Diesel Engine Efficiency and Pollutant Emissions : Part 1 Combustion Modeling. Jsme International Journal Series B-fluids and Thermal Engineering, 26, 569–575.
31. Lino, P., Maione, B., & Rizzo, A. (2007). Nonlinear modelling and control of a common rail injection system for diesel engines. Applied Mathematical Modelling, 31(9), 1770–1784.
32. Lakshminarayanan, P. A., Nayak, N., Dingare, S. V., and Dani, A. D. (June 19, 2002). "Predicting Hydrocarbon Emissions From Direct Injection Diesel Engines ." ASME. J. Eng. Gas Turbines Power. July 2002; 124(3): 708–716. https://doi.org/10.1115/1.1456091.
33. Omran, R., Younes, R., & Champoussin, J. C. (2008). Neural networks for real-time nonlinear control of a variable geometry turbocharged diesel engine. International Journal of Robust Nonlinear Control, 18(2), 1209–1229.
