Modelling Ships Main and Auxiliary Engine Powers with Regression-Based Machine Learning Algorithms

Okumuş, Fatih; Ekmekçioğlu, Araks; Kara, Selin Soner

doi:10.2478/pomr-2021-0008

Abstract

Based on data from seven different ship types, this paper provides mathematical relationships that allow us to estimate the main and auxiliary engine power of new ships. With these mathematical relationships we can estimate the power of the engine based on the ship’s length (L), gross tonnage (GT) and age. We developed these approaches using simple linear regression, polynomial regression, K-nearest neighbours (KNN) regression and gradient boosting machine (GBM) regression algorithms. The relationships presented here have a practical application: during the pre-parametric design of new ships, our mathematical relationships can be used to estimate the power of the engines so that more environmentally friendly ships may be built. In addition, with the machine learning methodology, the prediction of the main engine (ME) and auxiliary engine (AE) powers used in the numerical calculation of ship-based emissions provides data for researchers working on emission calculations. We conclude that the GBM regression algorithm provides more accurate solutions to estimate the main and auxiliary engine power of a ship than other algorithms used in the study.

References

1. A. Ekmekçioğlu, K. Ünlügençoğlu, and U. B. Çelebi, ‘Ship emission estimation for Izmir and Mersin international ports – Turkey’, Journal of Thermal Engineering, vol. 5, no. 6, pp. 184–195, 2019, doi: 10.18186/thermal.654319.10.18186/thermal.654319
Search in Google Scholar Back to article
2. C. Trozzi, ‘Emission estimate methodology for maritime navigation’, Co-leader of the Combustion & Industry Expert Panel, 2010.
Search in Google Scholar Back to article
3. R. Yan, S. Wang, and Y. Du, ‘Development of a two-stage ship fuel consumption prediction and reduction model for a dry bulk ship’, Transportation Research Part E: Logistics and Transportation Review, vol. 138, no. July 2019, p. 101930, 2020, doi: 10.1016/j.tre.2020.101930.10.1016/j.tre.2020.101930
Search in Google Scholar Back to article
4. L. Huang, Y. Wen, Y. Zhang, C. Zhou, F. Zhang, and T. Yang, ‘Dynamic calculation of ship exhaust emissions based on real-time AIS data’, Transportation Research Part D: Transport and Environment, vol. 80, no. August 2019, p. 102277, 2020, doi: 10.1016/j.trd.2020.102277.10.1016/j.trd.2020.102277
Search in Google Scholar Back to article
5. T. A. Tran, ‘Effect of ship loading on marine diesel engine fuel consumption for bulk carriers based on the fuzzy clustering method’, Ocean Engineering, vol. 207, no. January 2019, p. 107383, 2020, doi: 10.1016/j.oceaneng.2020.107383.10.1016/j.oceaneng.2020.107383
Search in Google Scholar Back to article
6. X. Yan, K. Wang, Y. Yuan, X. Jiang, and R. R. Negenborn, ‘Energy-efficient shipping: An application of big data analysis for optimizing engine speed of inland ships considering multiple environmental factors’, Ocean Engineering, vol. 169, no. August, pp. 457–468, 2018, doi: 10.1016/j. oceaneng.2018.08.050.
Search in Google Scholar Back to article
7. T. Cepowski, ‘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’, Polish Maritime Research, vol. 26, no. 1, pp. 82–94, Mar. 2019, doi: 10.2478/pomr-2019-0010.10.2478/pomr-2019-0010
Search in Google Scholar Back to article
8. W. J. Requia, B. A. Coull, and P. Koutrakis, ‘Evaluation of predictive capabilities of ordinary geostatistical interpolation, hybrid interpolation, and machine learning methods for estimating PM2.5 constituents over space’, Environmental Research, vol. 175, no. April, pp. 421–433, 2019, doi: 10.1016/j.envres.2019.05.025.10.1016/j.envres.2019.05.02531154232
Search in Google Scholar Back to article
9. T. Uyanık, Ç. Karatuğ, and Y. Arslanoğlu, ‘Machine learning approach to ship fuel consumption: A case of container vessel’, Transportation Research Part D: Transport and Environment, vol. 84, 2020, doi: 10.1016/j.trd.2020.102389.10.1016/j.trd.2020.102389
Search in Google Scholar Back to article
10. L. Barua, B. Zou, and Y. Zhou, ‘Machine learning for international freight transportation management: A comprehensive review’, Research in Transportation Business and Management, no. July 2019, p. 100453, 2020, doi: 10.1016/j.rtbm.2020.100453.10.1016/j.rtbm.2020.100453
Search in Google Scholar Back to article
11. Y. Peng, H. Liu, X. Li, J. Huang, and W. Wang, ‘Machine learning method for energy consumption prediction of ships in port considering green ports’, Journal of Cleaner Production, vol. 264, p. 121564, 2020, doi: 10.1016/j. jclepro.2020.121564.
Search in Google Scholar Back to article
12. J. H. Jeong, J. H. Woo, and J. G. Park, ‘Machine learning methodology for management of shipbuilding master data’, International Journal of Naval Architecture and Ocean Engineering, vol. 12, pp. 428–439, 2020, doi: 10.1016/j. ijnaoe.2020.03.005.
Search in Google Scholar Back to article
13. C. Gkerekos, I. Lazakis, and G. Theotokatos, ‘Machine learning models for predicting ship main engine fuel oil consumption: A comparative study’, Ocean Engineering, vol. 188, no. August, p. 106282, 2019, doi: 10.1016/j. oceaneng.2019.106282.
Search in Google Scholar Back to article
14. A. Jonquais and F. Krempl, ‘Predicting Shipping Time with Machine Learning’, 2019.
Search in Google Scholar Back to article
15. O. Bodunov, F. Schmidt, A. Martin, A. Brito, and C. Fetzer, ‘Grand challenge: Real-time destination and ETA prediction for maritime traffic’, DEBS 2018 – Proceedings of the 12th ACM International Conference on Distributed and Event-Based Systems, pp. 198–201, 2018, doi: 10.1145/3210284.3220502.10.1145/3210284.3220502
Search in Google Scholar Back to article
16. J. Yuan and V. Nian, ‘Ship energy consumption prediction with Gaussian process metamodel’, Energy Procedia, vol. 152, pp. 655–660, 2018, doi: 10.1016/j.egypro.2018.09.226.10.1016/j.egypro.2018.09.226
Search in Google Scholar Back to article
17. Y. B. A. Farag and A. I. Ölçer, ‘The development of a ship performance model in varying operating conditions based on ANN and regression techniques’, Ocean Engineering, vol. 198, no. July 2019, 2020, doi: 10.1016/j. oceaneng.2020.106972.
Search in Google Scholar Back to article
18. L. Bui-Duy and N. Vu-Thi-Minh, ‘Utilization of a deep learning-based fuel consumption model in choosing a liner shipping route for container ships in Asia’, Asian Journal of Shipping and Logistics, 2020, doi: 10.1016/j.ajsl.2020.04.003.10.1016/j.ajsl.2020.04.003
Search in Google Scholar Back to article
19. H. Cui, O. Turan, and P. Sayer, ‘Learning-based ship design optimization approach’, CAD Computer Aided Design, vol. 44, no. 3, pp. 186–195, 2012, doi: 10.1016/j.cad.2011.06.011.10.1016/j.cad.2011.06.011
Search in Google Scholar Back to article
20. M. Peker, O. Özkaraca, and B. Kesimal, ‘Modeling heating and cooling loads by regression-based machine learning techniques for energy-efficient building design’, International Journal of Informatics Technologies, pp. 443–449, 2017, doi: 10.17671/gazibtd.310154.10.17671/gazibtd.310154
Search in Google Scholar Back to article
21. V. Bertram and H. Schneekluth, Ship Design for Efficiency and Economy. Elsevier, 1998.
Search in Google Scholar Back to article

Modelling Ships Main and Auxiliary Engine Powers with Regression-Based Machine Learning Algorithms

Abstract

Paradigm

My account