Evaluation of prediction performances of deep learning models for the aerodynamic characteristics of flettner rotors

• Autorzy: Seo Janghoon , Park Jung Yoon , Ma Juhwan , Kim Young Bu , Park Dong-Woo

Identyfikatory

DOI

10.2478/pomr-2024-0046

• Języki publikacji: EN

Abstrakty

EN

This study investigates the prediction of the aerodynamic characteristics of Flettner rotors through three deep learning models. Various numbers of Flettner rotors, arrangements, and spin ratios are employed to consider these effects in the dataset. For the training of deep learning models, a dataset of aerodynamic force coefficients and flow fields is generated using Computational Fluid Dynamics (CFD). Three deep learning architectures (U-net, Encoder-Decoder, and Decoder models) are employed and trained to predict the aerodynamic characteristics of Flettner rotors. Three deep learning models are established through a training stage with a hyperparameter study and by altering the number of layers. The aerodynamic force coefficients and flow fields are predicted by established deep learning models and show small absolute errors compared to those from the CFD analysis. Moreover, predicted flow fields reflect the flow characteristics according to the difference of spin ratio and arrangement of Flettner rotors. In conclusion, the established deep learning models demonstrate rapid and robust predictions of aerodynamic force coefficients and flow fields for Flettner rotors under varying arrangements and spin ratios. Furthermore, a significant reduction in computational time is measured when comparing the analysis time of CFD simulations to the training and testing time of the deep learning models.

Słowa kluczowe

EN

deep learning model; Flettner rotor; computational fluid dynamics; aerodynamic performance

• Wydawca: Gdańsk University of Technology, Faculty of Ocean Engineering & Ship Technology
• Czasopismo: Polish Maritime Research
• Rocznik: 2024
• Tom: nr 4
• Strony: 4--20
• Opis fizyczny: Bibliogr. 32 poz., rys., tab.

Twórcy

autor

Seo Janghoon

• Shipbuilding & Marine Simulation Center, Tongmyong University, Busan, Republic of Korea, Korea, Republic of

• https://orcid.org/0000-0003-4567-7106

autor

Park Jung Yoon

• Shipbuilding & Marine Simulation Center, Tongmyong University, Busan, Republic of Korea, Korea, Republic of

autor

Ma Juhwan

• Safety Research Department, Korea Maritime Transportation Safety Authority, Sejong, Republic of Korea, Korea, Republic of

autor

Kim Young Bu

• Department of Computer Science, Tongmyong University, Busan, Republic of Korea, Korea, Republic of

• https://orcid.org/0000-0002-5724-0465

autor

Park Dong-Woo

• Autonomous Vehicle System Engineering Major, School of Electrical and Control Engineering, Tongmyong University, Busan, Republic of Korea, Korea, Republic of

Bibliografia

• 1. International Maritime Organization (IMO). Marine Environment Protection Committee (MEPC 80), 3-7 July 2023 – preview. 2023. https://www.imo.org/en/MediaCentre/MeetingSummaries/Pages/MEPC-80.aspx.
• 2. Zhang C, Zhu J, Guo H, Xue S, Wang X, Wang Z, Su P. Technical Requirement for 2023 IMO GHG Strategy. Sustainability 2024; vol. 16, no. 7; 2766. https://doi.org/10.3390/su16072766.
• 3. Khan L, Macklin J, Peck B, Morton O, Souppez JBRG. A review of wind-assisted ship propulsion for sustainable commercial shipping: latest developments and future stakes. In Wind Propulsion Conference. R. Inst. Nav. Archit 2021. https://research.aston.ac.uk/en/publications/a-review-ofwind-assisted-ship-propulsion-for-sustainable-commerc.
• 4. Hastings RB. The Flettner rotor ship. Science Activities 1971; 117-120. https://doi.org/10.1080/00368121.1971.10113354.
• 5. Badalamenti C, Prince S. Effects of endplates on a rotating cylinder in crossflow. In 26th AIAA Applied Aerodynamics Conference 2008; 7063. https://doi.org/10.2514/6.2008-7063.
• 6. Bordogna G, Muggiasca S, Giappino S, Belloli M, Keuning JA, Huijsmans RHM, Van’t Veer AP. Experiments on a Flettner rotor at critical and supercritical Reynolds numbers. Journal of Wind Engineering and Industrial Aerodynamics 2019; vol. 188; 19-29. https://doi.org/10.1016/j.jweia.2019.02.006.
• 7. Bordogna G, Muggiasca S, Giappino S, Belloli M, Keuning JA, Huijsmans RHM. The effects of the aerodynamic interaction on the performance of two Flettner rotors. Journal of Wind Engineering and Industrial Aerodynamics 2020; 196, 104024. https://doi.org/10.1016/j.jweia.2019.104024.
• 8. Chen W, Wang H, Liu X. Experimental investigation of the aerodynamic performance of Flettner rotors for marine applications. Ocean Engineering 2023; 281, 115006. https://doi.org/10.1016/j.oceaneng.2023.115006.
• 9. de Marco A, Mancini S, Pensa C, Calise G, de Luca F. Flettner rotor concept for marine applications: A systematic study. International Journal of Rotating Machinery 2016; 1, 3458750. https://doi.org/10.1155/2016/3458750.
• 10. Kwon CS, Yeon SM, Kim YC, Kim YG, Kim YH, Kang HJ. A parametric study for a flettner rotor in standalone condition using CFD. International Journal of Naval Architecture and Ocean Engineering 2022; 14, 100493. https://doi.org/10.1016/j.ijnaoe.2022.100493.
• 11. Li B, Zhang R, Li Y, Zhang B, Guo C. Study of a new type of Flettner rotor in merchant ships. Polish Maritime Research 2021; vol. 28, no. 1; 28-41. https://doi.org/10.2478/pomr-2021-0003.
• 12. Garzon F, Figueroa A. The study on the flow generated by an array of four Flettner rotors: theory and experiment. Applied Mathematics 2017; vol. 8, no. 12; 1851-1858.10.4236/am.2017.812132.
• 13. Kume K, Hamada T, Kobayashi H, Yamanaka S. Evaluation of aerodynamic characteristics of a ship with flettner rotors by wind tunnel tests and RANS-based CFD. Ocean Engineering 2022; 254, 111345. https://doi.org/10.1016/j.oceaneng.2022.111345.
• 14. Lv J, Lin Y, Zhang R, Li B, Yang H. Assisted propulsion device of a semi-submersible ship based on the Magnus effect. Polish Maritime Research 2022; vol. 29, no. 3; 33-46. https://doi.org/10.2478/pomr-2022-0023.
• 15. Seo J, Park DW. Numerical Study on the Aerodynamic Performance of Four Flettner Rotors by Varying Distance and Spin Ratio. Journal of Marine Science and Technology 2024; vol. 32, no. 2. https://doi.org/10.51400/2709-6998.2735.
• 16. Tilling F, Ringsberg JW. Design, operation and analysis of wind-assisted cargo ships. Ocean Engineering. 2020; 211, 107603. https://doi.org/10.1016/j.oceaneng.2020.107603.
• 17. Reche-Vilanova M, Hansen H, Bingham HB. Performance prediction program for wind-assisted cargo ships. Journal of Sailing Technology 2021; vol. 6, no. 01; 91-117. https://doi.org/10.5957/jst/2021.6.1.91.
• 18. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; vol. 521, no. 7553; 436-444. https://doi.org/10.1038/nature14539.
• 19. Lee S, You D. Prediction of laminar vortex shedding over a cylinder using deep learning. arXiv preprint arXiv, 2017. https://doi.org/10.48550/arXiv.1712.07854.
• 20. Lee S, You D. Data-driven prediction of unsteady flow over a circular cylinder using deep learning. Journal of Fluid Mechanics 2019; vol. 879; 217-254. https://doi.org/10.1017/jfm.2019.700.
• 21. Han R, Wang Y, Zhang Y, Chen G. A novel spatial-temporal prediction method for unsteady wake flows based on hybrid deep neural network. Physics of Fluids 2019; vol. 31, no. 12. https://doi.org/10.1063/1.5127247.
• 22. Hasegawa K, Fukami K, Murata T, Fukagata K. CNNLSTM based reduced order modeling of two-dimensional unsteady flows around a circular cylinder at different Reynolds numbers. Fluid Dynamics Research 2020; vol. 52, no. 6, 065501. 10.1088/1873-7005/abb91d.
• 23. Ye S, Zhang Z, Song X, Wang Y, Chen Y, Huang C. A flow feature detection method for modeling pressure distribution around a cylinder in non-uniform flows by using a convolutional neural network. Scientific reports 2020; vol. 10, no. 1; 4459. https://doi.org/10.1038/s41598-020-61450-z.
• 24. Jin X, Cheng P, Chen WL, Li H. Prediction model of velocity field around circular cylinder over various Reynolds numbers by fusion convolutional neural networks based on pressure on the cylinder. Physics of Fluids 2018; vol. 30, no. 4. https://doi.org/10.1063/1.5024595.
• 25. Xu H, Zhang W, Deng J, Rabault J. Active flow control with rotating cylinders by an artificial neural network trained by deep reinforcement learning. Journal of Hydrodynamics 2020; vol. 32, no. 2; 254-258. https://doi.org/10.1007/s42241-020-0027-z.
• 26. Tokarev M, Palkin E, Mullyadzhanov R. Deep reinforcement learning control of cylinder flow using rotary oscillations at low Reynolds number. Energies 2020; vol. 13, no. 20; 5920. https://doi.org/10.3390/en13225920.
• 27. SIEMENS, “STAR-CCM+ 2021. 3. 16.06 User Guide”, 2021.
• 28. de Marco A, Mancini S, Pensa C. Preliminary analysis for marine application of Flettner rotors. In Proceedings of the 2nd International Symposium on Naval Architecture and Maritime, Istanbul, Turkey, 2014; 23-24. https://www.iris.unina.it/handle/11588/598037.
• 29. Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9 2015; 234-241. Proceedings Part III 18, 2015. https://doi.org/10.1007/978-3-319-24574-4_28.
• 30. Badrinarayanan V, Kendall A, Cipolla R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. pattern Anal. Mach. Intell. 2017; vol. 39, no. 12; 2481-2495. https://doi.org/10.1109/TPAMI.2016.2644615.
• 31. Nair V, Hinton GE. Rectified linear units improve restricted Boltzmann machines. In Proceedings of the 27th International Conference on machine learning (ICML-10). 2010; 807-814. https://www.cs.toronto.edu/~hinton/absps/reluICML.pdf.
• 32. Kingma DP, Ba J. Adam: A method for stochastic optimisation. arXiv preprint arXiv, 2014. https://doi.org/10.48550/arXiv.1412.6980.

Uwagi

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).