Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning
When designing a ship's hull form, a designer creates various candidate hull forms and performs a Computational Fluid Dynamics (CFD) analysis to evaluate the performance of each candidate. Designers consider quantitative indicators, such as the total resistance and wake coefficient, and qualita...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-01-01
|
| Series: | International Journal of Naval Architecture and Ocean Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2092678222000565 |
| _version_ | 1811182644556201984 |
|---|---|
| author | Jin-Hyeok Kim Myung-Il Roh Ki-Su Kim In-Chang Yeo Min-Jae Oh Jung-Woo Nam Sahng-Hyon Lee Young-Hun Jang |
| author_facet | Jin-Hyeok Kim Myung-Il Roh Ki-Su Kim In-Chang Yeo Min-Jae Oh Jung-Woo Nam Sahng-Hyon Lee Young-Hun Jang |
| author_sort | Jin-Hyeok Kim |
| collection | DOAJ |
| description | When designing a ship's hull form, a designer creates various candidate hull forms and performs a Computational Fluid Dynamics (CFD) analysis to evaluate the performance of each candidate. Designers consider quantitative indicators, such as the total resistance and wake coefficient, and qualitative indicators, such as the wave height and pressure distributions, when evaluating the performance of a hull form. During the design process, quantitative and qualitative indicators are often used to determine the superiority of two hull forms. However, in the case of quantitative indicators, the difference between the two hull forms is often minimal; thus, superiority cannot be readily determined. Furthermore, because qualitative indicators are in the form of images, it is challenging to determine the superiority in many cases, even for experienced designers. To solve this problem, we propose a convolutional neural network-based model for predicting the superiority of hull form performance from a qualitative indicator of the image form derived from CFD analysis. The proposed prediction model received various types of hull form performance images. From these results, the hull form performance characteristics were well fused for prediction with high accuracy. CFD analysis images and quantitative indicators for 1600 hull forms were used to determine the superiority of the prediction model. The learned model was verified using 240 hulls. The result confirmed that the proposed model accurately predicted superiority with an accuracy of approximately 94%. |
| first_indexed | 2024-04-11T09:35:16Z |
| format | Article |
| id | doaj.art-1f1cd90821cf42c6acbdb21f57b7f8b0 |
| institution | Directory Open Access Journal |
| issn | 2092-6782 |
| language | English |
| last_indexed | 2024-04-11T09:35:16Z |
| publishDate | 2022-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Naval Architecture and Ocean Engineering |
| spelling | doaj.art-1f1cd90821cf42c6acbdb21f57b7f8b02022-12-22T04:31:44ZengElsevierInternational Journal of Naval Architecture and Ocean Engineering2092-67822022-01-0114100490Prediction of the superiority of the hydrodynamic performance of hull forms using deep learningJin-Hyeok Kim0Myung-Il Roh1Ki-Su Kim2In-Chang Yeo3Min-Jae Oh4Jung-Woo Nam5Sahng-Hyon Lee6Young-Hun Jang7Department of Naval Architecture and Ocean Engineering, Seoul National University, Seoul, Republic of KoreaDepartment of Naval Architecture and Ocean Engineering, and Research Institute of Marine Systems Engineering, Seoul National University, Seoul, Republic of Korea; Corresponding author.School of Naval Architecture and Ocean Engineering, University of Ulsan, Ulsan, Republic of KoreaDepartment of Naval Architecture and Ocean Engineering, Seoul National University, Seoul, Republic of KoreaSchool of Naval Architecture and Ocean Engineering, University of Ulsan, Ulsan, Republic of KoreaShip and Ocean R&D Institute, Daewoo Shipbuilding and Marine Engineering Co., Ltd., Siheung, Kyeonggi-do, Republic of KoreaShip and Ocean R&D Institute, Daewoo Shipbuilding and Marine Engineering Co., Ltd., Siheung, Kyeonggi-do, Republic of KoreaShip and Ocean R&D Institute, Daewoo Shipbuilding and Marine Engineering Co., Ltd., Siheung, Kyeonggi-do, Republic of KoreaWhen designing a ship's hull form, a designer creates various candidate hull forms and performs a Computational Fluid Dynamics (CFD) analysis to evaluate the performance of each candidate. Designers consider quantitative indicators, such as the total resistance and wake coefficient, and qualitative indicators, such as the wave height and pressure distributions, when evaluating the performance of a hull form. During the design process, quantitative and qualitative indicators are often used to determine the superiority of two hull forms. However, in the case of quantitative indicators, the difference between the two hull forms is often minimal; thus, superiority cannot be readily determined. Furthermore, because qualitative indicators are in the form of images, it is challenging to determine the superiority in many cases, even for experienced designers. To solve this problem, we propose a convolutional neural network-based model for predicting the superiority of hull form performance from a qualitative indicator of the image form derived from CFD analysis. The proposed prediction model received various types of hull form performance images. From these results, the hull form performance characteristics were well fused for prediction with high accuracy. CFD analysis images and quantitative indicators for 1600 hull forms were used to determine the superiority of the prediction model. The learned model was verified using 240 hulls. The result confirmed that the proposed model accurately predicted superiority with an accuracy of approximately 94%.http://www.sciencedirect.com/science/article/pii/S2092678222000565Hull form designHydrodynamic performanceSuperiority predictionDeep learningConvolutional Neural Network (CNN)Computational Fluid Dynamics (CFD) |
| spellingShingle | Jin-Hyeok Kim Myung-Il Roh Ki-Su Kim In-Chang Yeo Min-Jae Oh Jung-Woo Nam Sahng-Hyon Lee Young-Hun Jang Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning International Journal of Naval Architecture and Ocean Engineering Hull form design Hydrodynamic performance Superiority prediction Deep learning Convolutional Neural Network (CNN) Computational Fluid Dynamics (CFD) |
| title | Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning |
| title_full | Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning |
| title_fullStr | Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning |
| title_full_unstemmed | Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning |
| title_short | Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning |
| title_sort | prediction of the superiority of the hydrodynamic performance of hull forms using deep learning |
| topic | Hull form design Hydrodynamic performance Superiority prediction Deep learning Convolutional Neural Network (CNN) Computational Fluid Dynamics (CFD) |
| url | http://www.sciencedirect.com/science/article/pii/S2092678222000565 |
| work_keys_str_mv | AT jinhyeokkim predictionofthesuperiorityofthehydrodynamicperformanceofhullformsusingdeeplearning AT myungilroh predictionofthesuperiorityofthehydrodynamicperformanceofhullformsusingdeeplearning AT kisukim predictionofthesuperiorityofthehydrodynamicperformanceofhullformsusingdeeplearning AT inchangyeo predictionofthesuperiorityofthehydrodynamicperformanceofhullformsusingdeeplearning AT minjaeoh predictionofthesuperiorityofthehydrodynamicperformanceofhullformsusingdeeplearning AT jungwoonam predictionofthesuperiorityofthehydrodynamicperformanceofhullformsusingdeeplearning AT sahnghyonlee predictionofthesuperiorityofthehydrodynamicperformanceofhullformsusingdeeplearning AT younghunjang predictionofthesuperiorityofthehydrodynamicperformanceofhullformsusingdeeplearning |