Predicting tanker main engine power using regression analysis and artificial neural networks

Abstract

The purpose-oriented design and planning of ships is maintained throughout production. Outer form of ship equipment starts with the steel construction process. The outer body production process moves ahead with painting, quality control tests, and bureaucratic procedures. In accordance with all these form and block operations, choosing a main engine suitable for all other technical parameters is vital, especially regarding ship speed and the amount of cargo it will carry. As a result, estimating main engine power is attempted with the help of artificial neural network (ANN) and regression analyses by considering a ship’s technical parameters (e.g., draught, depth, deadweight tonnage [DWT], gross tonnage [GT], and engine power). This study conducts regression and ANN analyses over 836 tanker ships from the Marine Traffic database to predict main engine power using input parameters (deadweight (DWT), Length (L), Breadth (B), and gross ton (GT) values). The regression analyses show Model 7 to perform the best approximation with a determination value = 0.827 usable for estimating main engine power. After all the examinations, a very accomplished result of 0.98047 was additionally obtained from the ANN analysis. The study makes beneficial and innovative contributions to predicting tankers’ required main engine power.

Keywords

• Artificial Neural Network
• ANN
• Ship
• Main Engine
• Power
• Regression Analysis

References

1. [1] Marine Propulsion Engine Market - Growth, Trends, Covid-19 Impact, and Forecasts (2021 -2026). Mordor Intelligence; 2020.
2. [2] Barua L, Zou B, Zhou Y. Machine learning for international freight transportation management: A comprehensive review. Res Transp Bus Manag 2020;34:100453. [CrossRef]
3. [3] Bodunov O, Schmidt F, Martin A, Brito A, Fetzer C. Real-time Destination and ETA Prediction for Maritime Traffic. Proc. 12th ACM Int. Conf. Distrib. Event-Based Syst., New York, NY, USA: Association for Computing Machinery; 2018, p. 198–201. [CrossRef]
4. [4] Bui-Duy L, Vu-Thi-Minh N. Utilization of a deep learning-based fuel consumption model in choosing a liner shipping route for container ships in Asia. Asian J Shipp Logist 2021;37:1–11.[CrossRef]
5. [5] Cepowski T, Chorab P. The Use of Artificial Neural Networks to Determine the Engine Power and Fuel Consumption of Modern Bulk Carriers, Tankers and Container Ships. Energies 2021;14:4827. [CrossRef]
6. [6] Cui H, Turan O, Sayer P. Learning-based ship design optimization approach. Comput-Aided Des 2012;44:186–195. [CrossRef]
7. [7] Jeong JH, Woo JH, Park J. Machine Learning Methodology for Management of Shipbuilding Master Data. Int J Nav Archit Ocean Eng 2020;12:428–439. [CrossRef]
8. [8] Cepowski T. Prediction of the main engine power of a new container ship at the preliminary design Stage. Manag Syst Prod Eng 2017;25:97–99. [CrossRef]

9. [9] Cepowski T. Regression formulas for the estimation of engine total power for tankers, container ships and bulk carriers on the basis of cargo capacity and design speed. Pol Marit Res 2019;26:82–94. [CrossRef]
10. [10] Cepowski T, Chorab P. Determination of design for-mulas for container ships at the preliminary design stage using artificial neural network and multiple nonlinear regression. Ocean Eng 2021;238:106972.[CrossRef]
11. [11] Uyanık T, Karatuğ Ç, Arslanoğlu Y. Machine learn-ing approach to ship fuel consumption: A case of container vessel. Transp Res Part Transp Environ 2020;84:102389. [CrossRef]
12. [12] Gkerekos C, Lazakis I, Theotokatos G. Machine learning models for predicting ship main engine Fuel Oil Consumption: A comparative study. Ocean Eng 2019;188:106282. [CrossRef]
13. [13] Farag YBA. A decision support system for ship’s energy efficient operation: based on artificial neural network method. World Maritime University, 2017.
14. [14] Tarelko W, Rudzki K. Applying artificial neural net-works for modelling ship speed and fuel consump-tion. Neural Comput Appl 2020;32:17379–17395.[CrossRef]
15. [15] Farag YBA, Olcer AI. The development of a ship performance model in varying operating conditions based on ANN and regression techniques. Ocean Eng 2020;198:106972. [CrossRef]
16. [16] Peng Y, Liu H, Li X, Huang J, Wang W. Machine learning method for energy consumption predition of ships in port considering green ports. J Clean Prod 2020;264:121564. [CrossRef]
17. [17] Yan X, Wang K, Yuan Y, Jiang X, Negenborn RR. Energy-efficient shipping: An application of big data analysis for optimizing engine speed of inland ships considering multiple environmental factors. Ocean Eng 2018;169:457–468. [CrossRef]
18. [18] Yan R, Wang S, Du Y. Development of a two-stage ship fuel consumption prediction and reduction model for a dry bulk ship. Transp Res Part E Logist Transp Rev 2020;138:101930. [CrossRef]
19. [19] Yuan J, Nian V. Ship energy consumption prediction with gaussian process metamodel. Energy Proced 2018;152:655–660. [CrossRef]
20. [20] Tran TA. Design the prediction model of low-sul-fur-content fuel oil consumption for M/V NORD VENUS 80,000 DWT sailing on emission control areas by artificial neural networks. Proc Inst Mech Eng Part M J Eng Marit Environ 2019;233:345–362. [CrossRef]
21. [21] Tran TA. Comparative analysis on the fuel con-sumption prediction model for bulk carriers from ship launching to current states based on sea trial data and machine learning technique. J Ocean Eng Sci 2021;6:317-339. [CrossRef]
22. [22] Parkes AI, Sobey AJ, Hudson DA. Physics-based shaft power prediction for large merchant ships using neural networks. Ocean Eng 2018;166:92–104. [CrossRef]
23. [23] Goksu B, Erginer E. Prediction of ship main engine failures by artificial neural networks. J ETA Marit Sci 2020;8. https://doi.org/10.5505/jems.2020.90377.
24. [24] Bal Besikci E, Arslan O, Turan O, Ölçer AI. An arti-ficial neural network based decision support system for energy efficient ship operations. Comput Oper Res 2016;66:393–401. [CrossRef]
25. [25] Alexiou K, Pariotis EG, Zannis TC, Leligou HC. Prediction of a ship’s operational parameters using artificial intelligence techniques. J Mar Sci Eng 2021;9:681. [CrossRef]
26. [26] Ekmekcioglu A. Ship emission estimation for Izmir and Mersin international ports – Turkey. J Therm Eng 2019;5:184–195. [CrossRef]
27. [27] Huang L, Wen Y, Zhang Y, Zhou C, Zhang F, Yang T. Dynamic calculation of ship exhaust emissions based on real-time AIS data. Transp Res Part Transp Environ 2020;80:102277. [CrossRef]
28. [28] Csáji BC. Approximation with Artificial Neural Networks. Eötvös Loránd University (ELTE), 2001.
29. [29] Haykin S. Neural Networks and Learning Machines. 3rd ed. New Jersey: Pearson; 2008.
30. [30] Talaat M, Gobran MH, Wasfi M. A hybrid model of an artificial neural network with thermodynamic model for system diagnosis of electrical power plant gas turbine. Eng Appl Artif Intell 2018;68:222–235.[CrossRef]
31. [31] Lv C, Xing Y, Zhang J, Na X, Li Y, Liu T, et al. Levenberg–marquardt backpropagation training of multilayer neural networks for state estimation of a safety- critical cyber-physical system. IEEE Trans Ind Inform 2018;14:3436–3446. [CrossRef]