Unet 기반 인공지능 모델을 활용한 잠수함의 표면 압력 분포 예측
Pressure Distribution Prediction for Submarine Using Unet-Based AI Model
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this study, a preprocessing method for submarine hull form and hydrodynamic pressure distribution were developed to enable an AI model to predict pressure distribution for the corresponding hull form. An Unet-based symmetric model including convolution layers was trained. The training hull form data set was generated by modifying DARPA Suboff 5475 model and the corresponding pressure distribution data set was calculated by solving RANS equation. The AI model was designed to extract the feature maps of body, sail, and stern parallelly to learn their hydrodynamic interaction. As a result, the trained model's predicted pressure distribution closely matched the CFD results, showing not only similar contours but also a total resistance coefficient within 2% error margin. However, the model shows limitations in predicting highly non-linear behavior of pressure distribution for the combination of two deformation on stern: afterbody and stern appendages.
Abstract
In this study, a preprocessing method for submarine hull form and hydrodynamic pressure distribution were developed to enable an AI model to predict pressure distribution for the corresponding hull form. An Unet-based symmetric model including convolution layers was trained. The training hull form data set was generated by modifying DARPA Suboff 5475 model and the corresponding pressure distribution data set was calculated by solving RANS equation. The AI model was designed to extract the feature maps of body, sail, and stern parallelly to learn their hydrodynamic interaction. As a result, the trained model's predicted pressure distribution closely matched the CFD results, showing not only similar contours but also a total resistance coefficient within 2% error margin. However, the model shows limitations in predicting highly non-linear behavior of pressure distribution for the combination of two deformation on stern: afterbody and stern appendages.
참고문헌 (25)
- Ai-guo, C., "Research on the genetic neural network for the computation of ship resistance", 2009 International Conference on Computational Intelligence and Natural Computing, 1, pp.366~369 (2009), IEEE
- Chase, N., "Simulations of the DARPA Suboff submarine including self-propulsion with the E 1619 propeller", M.S, pp.2012
- Chen, G, "Optimization of submarine resistance and manoeuvrability based on SBD technique", ISOPE International Ocean and Polar Engineering Conference, pp.ISOPE-I~ (2022)
- Cho, Y. J., "Maneuvering simulation of an X-plane submarine using computational fluid dynamics", International Journal of Naval Architecture and Ocean Engineering, 12, pp.843~855 (2020)
- Resistance for DARPA SUBOFF as represented by model 5470, "Crook, B", David Taylor Research Center, ~ (1990)
- Demo, N., "An efficient shape parametrisation by free-form deformation enhanced by active subspace for hull hydrodynamic ship design problems in open source environment", ISOPE International Ocean and Polar Engineering Conference, pp.ISOPE-I~ (2018)
- Diez, M., "Design-space dimensionality reduction in shape optimization by Karhunen–Loève expansion", Computer Methods in Applied Mechanics and Engineering, 283, pp.1525~1544 (2015)
- Geometric characteristics of DARPA SUBOFF models (DTRC Model Nos. 5470 and 5471), "Groves, N. C.", David Taylor Research Center, ~ (1989)
- Hou, Y., "A novel deep U-Net-LSTM framework for time-s equenced hydrodynamics prediction of the SUBOFF AFF-8", Engineering Applications of Computational Fluid Mechanics, 16(1), pp.630~645 (2022)
- Summary of DARPA SUBOFF experimental program data, "Liu, H. L.", ~ (1998)
- Luo, W., "Hull optimization of an underwater vehicle based on dynamic surrogate model", Ocean Engineering, 230, pp.109050~ (2021)
- Mai, T. L., "Establishment of empirical formulae for hydrodynamic derivatives of submarine considering design parameters", International Journal of Naval Architecture and Ocean Engineering, 15, pp.100537~ (2023)
- Özden, Y. A, "Experimental and numerical investigation of DARPA Suboff submarine propelled with INSEAN E1619 propeller for self-propulsion", Journal of ship research, 63(04), pp.235~250 (2019)
- Park, J. Y., "Experimental study on hydrodynamic coefficients for high-incidence-angle maneuver of a submarine", International Journal of Naval Architecture and Ocean Engineering, 9(1), pp.100~113 (2017)
- Park, J., "Computational analysis of strut effects on a BB2 submarine at drift angle 0, 6, and 12°", International Journal of Naval Architecture and Ocean Engineering, 15, pp.100555~ (2023)
- Investigation of the stability and control characteristics of several configurations of the DARPA SUBOFF model (DTRC Model 5470) from captive-model experiments, "Roddy, R. F", David Taylor Research Center, Ship Hydromechanics Department, ~, pp.DTRC (1990), SHD-1298-08
- Ronneberger, O., "U-net:Convolutional networks for biomedical image segmentation", Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pp.234~241 (2015), Springer International Publishing
- Siemens Digital Industries Software, "Simcenter STAR-CCM+, version 2020.3.1", ~ (2020)
- Thuerey, N., "Deep learning methods for Reynolds-averaged Navier–Stokes simulations of airfoil flows", AIAA Journal, 58(1), pp.25~36 (2020)
- Wang, B., "Application of artificial intelligence in computational fluid dynamics", Industrial &Engineering Chemistry Research, 60(7), pp.2772~2790 (2021)
- Wu, S. J., "Robust design on the arrangement of a sail and control planes for improvement of underwater Vehicle’s maneuverability", International Journal of Naval Architecture and Ocean Engineering, 12, pp.617~635 (2020)
- Yang, C., "September. Prediction of flows over an axisymmetric body with appendages", The 8th International Conference on Numerical Ship Hydrodynamics (2003)
- Zhang, S., "Research on the hull form optimization using the surrogate models", Engineering Applications of Computational Fluid Mechanics, 15(1), pp.747~761 (2021)
- Zhu, Z., "Fast and highprecision compressible flowfield inference method of transonic airfoils based on attention UNet", Physics of Fluids, 36(3), pp.036111~ (2024)
- Zuo, K., "Fast simulation of airfoil flow field via deep neural network", Aerospace Science and Technology, 150, pp.109207~ (2024)