Evaluation of Prediction Performances of Deep Learning Models for the Aerodynamic Characteristics of Flettner Rotors
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 datase...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2024-12-01
|
| Series: | Polish Maritime Research |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/pomr-2024-0046 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823860432273670144 |
|---|---|
| author | Seo Janghoon Park Jung Yoon Ma Juhwan Kim Young Bu Park Dong-Woo |
| author_facet | Seo Janghoon Park Jung Yoon Ma Juhwan Kim Young Bu Park Dong-Woo |
| author_sort | Seo Janghoon |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-7e28095864ed43bfa697a8769aa704a8 |
| institution | Kabale University |
| issn | 2083-7429 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Polish Maritime Research |
| spelling | doaj-art-7e28095864ed43bfa697a8769aa704a82025-02-10T13:26:04ZengSciendoPolish Maritime Research2083-74292024-12-0131442010.2478/pomr-2024-0046Evaluation of Prediction Performances of Deep Learning Models for the Aerodynamic Characteristics of Flettner RotorsSeo Janghoon0Park Jung Yoon1Ma Juhwan2Kim Young Bu3Park Dong-Woo4Shipbuilding & Marine Simulation Center, Tongmyong University, Busan, Republic of Korea, Korea, Republic ofShipbuilding & Marine Simulation Center, Tongmyong University, Busan, Republic of Korea, Korea, Republic ofSafety Research Department, Korea Maritime Transportation Safety Authority, Sejong, Republic of Korea, Korea, Republic ofDepartment of Computer Science, Tongmyong University, Busan, Republic of Korea, Korea, Republic ofAutonomous Vehicle System Engineering Major, School of Electrical and Control Engineering, Tongmyong University, Busan, Republic of Korea, Korea, Republic ofThis 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.https://doi.org/10.2478/pomr-2024-0046deep learning modelflettner rotorcomputational fluid dynamicsaerodynamic performance |
| spellingShingle | Seo Janghoon Park Jung Yoon Ma Juhwan Kim Young Bu Park Dong-Woo Evaluation of Prediction Performances of Deep Learning Models for the Aerodynamic Characteristics of Flettner Rotors Polish Maritime Research deep learning model flettner rotor computational fluid dynamics aerodynamic performance |
| title | Evaluation of Prediction Performances of Deep Learning Models for the Aerodynamic Characteristics of Flettner Rotors |
| title_full | Evaluation of Prediction Performances of Deep Learning Models for the Aerodynamic Characteristics of Flettner Rotors |
| title_fullStr | Evaluation of Prediction Performances of Deep Learning Models for the Aerodynamic Characteristics of Flettner Rotors |
| title_full_unstemmed | Evaluation of Prediction Performances of Deep Learning Models for the Aerodynamic Characteristics of Flettner Rotors |
| title_short | Evaluation of Prediction Performances of Deep Learning Models for the Aerodynamic Characteristics of Flettner Rotors |
| title_sort | evaluation of prediction performances of deep learning models for the aerodynamic characteristics of flettner rotors |
| topic | deep learning model flettner rotor computational fluid dynamics aerodynamic performance |
| url | https://doi.org/10.2478/pomr-2024-0046 |
| work_keys_str_mv | AT seojanghoon evaluationofpredictionperformancesofdeeplearningmodelsfortheaerodynamiccharacteristicsofflettnerrotors AT parkjungyoon evaluationofpredictionperformancesofdeeplearningmodelsfortheaerodynamiccharacteristicsofflettnerrotors AT majuhwan evaluationofpredictionperformancesofdeeplearningmodelsfortheaerodynamiccharacteristicsofflettnerrotors AT kimyoungbu evaluationofpredictionperformancesofdeeplearningmodelsfortheaerodynamiccharacteristicsofflettnerrotors AT parkdongwoo evaluationofpredictionperformancesofdeeplearningmodelsfortheaerodynamiccharacteristicsofflettnerrotors |