Deep-reinforcement-learning-based hull form optimization method for stealth submarine design
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The stealth performance of submarines is closely related to their hull forms. In this study, an optimization method based on Deep Reinforcement Learning (DRL) was developed to design submarine hull forms, aimed at maximizing the stealth performance. The DRL optimization technique relied on the decision-making process of an agent for determining actions resulting in changes in the hull form, using stealth performance as the reward. The stealth performance of the submarine was evaluated through a Target Strength (TS) analysis model. Additionally, functional constraints of the examined hull forms were implemented in the optimization process, including geometric constraints related to the hull form and dynamic stability constraints pertaining to the hydrodynamic maneuvering characteristics. The TS of the final optimized hull form was 6.5 dB lower than that of the base model, indicating remarkable stealth performance and improved maneuverability. These results validated the effectiveness of the proposed DRL-based optimization method.
Abstract
The stealth performance of submarines is closely related to their hull forms. In this study, an optimization method based on Deep Reinforcement Learning (DRL) was developed to design submarine hull forms, aimed at maximizing the stealth performance. The DRL optimization technique relied on the decision-making process of an agent for determining actions resulting in changes in the hull form, using stealth performance as the reward. The stealth performance of the submarine was evaluated through a Target Strength (TS) analysis model. Additionally, functional constraints of the examined hull forms were implemented in the optimization process, including geometric constraints related to the hull form and dynamic stability constraints pertaining to the hydrodynamic maneuvering characteristics. The TS of the final optimized hull form was 6.5 dB lower than that of the base model, indicating remarkable stealth performance and improved maneuverability. These results validated the effectiveness of the proposed DRL-based optimization method.
참고문헌 (42)
- A Study of Effects of Viscosity on Flow over Slender Inclined Bodies of Revolution, "Allen, H. J.", ~, pp.No. NACA-TR-1048 (1951)
- Ao, Y., "An artificial intelligence-aided design(AIAD)of ship hull structures", J. Ocean Eng. Sci, 8(1), pp.15~32 (2021)
- The Stability Coefficients of Standard Torpedoes, vol. 909, "Bottaccini, M. R.", ~, pp.NWVORD Report 3346 (1954)
- Chi, Y. A. N. G., "An overview of simulation-based hydrodynamic design of ship hull forms", Journal of Hydrodynamics, Ser. B, 28(6), pp.947~960 (2016)
- Curtis, A. C., "COMPARING TARGET ECHO STRENGTH MODELS of A GENERIC SUBMARINE", Underwater Acoustics Conference and Exhibition (UACE2023) (2019)
- Deraj, R., "Deep reinforcement learning based controller for ship navigation", Ocean Eng, 273, pp.113937~ (2023)
- Fan, Y., "A novel intelligent collision avoidance algorithm based on deep reinforcement learning approach for USV", Ocean Eng, 287, pp.115649~ (2023)
- Feldman, J. P., "Method of Performing Captive-Model Experiments to Predict the Stability and Control Characteristics of Submarines", NAVAL SURFACE WARFARE CENTER CARDEROCK DIV BETHESDA MD HYDROMECHANICS DIRECT ORATE, ~ (1995)
- Finck, R. D., "USAF (United States Air Force) Stability and Control DATCOM (Data Compendium)", MCDONNELL AIRCRAFT CO ST LOUIS MO, ~ (1978)
- Garnier, P., "A review on deep reinforcement learning for fluid mechanics", Comput. Fluid, 225, pp.104973~ (2021)
- Gordon, W., "Far-field approximations to the Kirchoff-Helmholtz representations of scattered fields", IEEE Trans. Antenn. Propag, 23(4), pp.590~592 (1975)
- Ham, J. H., "Actor-Critic reinforcement learning for optimal design of piping support constraint combinations", Int. J. Nav. Archit. Ocean Eng, 14, pp.100485~ (2022)
- Hui, X., "Multi-object aerodynamic design optimization using deep reinforcement learning", AIP Adv, 11(8), pp.085311~ (2021)
- Joubert, P. N., "Some Aspects of Submarine Design: Part 1: Hydrodynamics", Australian Department of Defence, ~ (2004)
- Keramati, H., "Deep reinforcement learning for heat exchanger shape optimization", Int. J. Heat Mass Tran, 194, pp.123112~ (2022)
- Kim, J. H., "Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning", Int. J. Nav. Archit. Ocean Eng, 14, pp.100490~ (2022)
- Knott, E. F., "Radar Cross Section" (2004), SciTech Publishing
- Kwon, H. W., "A study for acoustic target strength characteristics of submarines using Kirchhoff approximation", Mar. Technol. Soc. J, 51(4), pp.52~58 (2017)
- The Effect of Changes in the Stability Derivatives on the Dynamic Behavior of a Torpedo, vol. 3143, "Lambert, J. D.", Admiralty Research Laboratory, Aeronautical Research Council Reports and Memoranda, ~ (1956)
- Lee, J. B., "Prediction of ship power based on variation in deep feed-forward neural network", Int. J. Nav. Archit. Ocean Eng, 13, pp.641~649 (2021)
- Liu, X., "A cross-entropy algorithm based on Quasi-Monte Carlo estimation and its application in hull form optimization", Int. J. Nav. Archit. Ocean Eng, 13, pp.115~125 (2021)
- Lottati, I., "Flutter and divergence aeroelastic characteristics for composite forward swept cantilevered wing", J. Aircraft, 22(11), pp.1001~1007 (1985)
- Nolte, B., "BeTSSi II benchmark on target strength simulation", Proceedings of Forum Acusticum (2014)
- Okumura, T., "Acoustic scattering by an arbitrarily shaped body: an application of the boundary-element method", ICES (Int. Counc. Explor. Sea) J. Mar. Sci, 60(3), pp.563~570 (2003)
- Rabault, J., "Deep reinforcement learning in fluid mechanics : a promising method for both active flow control and shape optimization", J. Hydrodyn, 32, pp.234~246 (2020)
- Manoeuvring Studies of Underwater Vehicles-A Review, vol. 150, "Ray, A.", Transactions of royal institution of naval architects, ~ (2008)
- Reijmers, J. J., "Bottoming of a submarine", Proceedings of the Undersea Defence Technology (UDT) Conference (2012)
- Schneider, H. G., "Acoustic Scattering by a Submarine: Results from a Benchmark Target Strength Simulation Workshop", ICSV10, pp.2475~2482 (2003)
- Simonich, J. C., "Role of leading-edge vortex flows in prop-fan interaction noise", J. Aircraft, 30(2), pp.255~261 (1993)
- Nomenclature for Treating the Motion of a Submerged Body through a Fluid, "SNAME, T.", The Society of Naval Architects and Marine Engineers, 1~5 (1950)
- Sun, Y., "Numerical investigation of the submarine sail with different aspect ratio for acoustic target strength reduction", INTER-NOISE and NOISE-CON Congress and Conference Proceedings, 261, pp.4304~4310 (2020), Institute of Noise Control Engineering
- Sutton, R. S., "Reinforcement Learning : an Introduction" (2018), MIT press
- Tang, Y., "Optimum design of acoustic stealth shape of underwater vehicle model with conning tower", Frontiers in Physics, 11, pp.44~ (2023)
- Thompson, L. L., "A space-time finite element method for the exterior acoustics problem", J. Acoust. Soc. Am, 99(6), pp.3297~3311 (1996)
- Tran, T. G., "Optimization strategy for planing hull design", Int. J. Nav. Archit. Ocean Eng, 14, pp.100471~ (2022)
- Urick, R. J., "Principles of Underwater Sound", pp.303~ (1983), McGraw-Hill
- Viquerat, J., "Direct shape optimization through deep reinforcement learning", J. Comput. Phys, 428, pp.110080~ (2021)
- Wang, Y., "Three-dimensional ship hull encoding and optimization via deep neural networks", J. Mech. Des, 144(10), pp.101701~ (2022)
- Whicker, L. F., "Free-stream Characteristics of a Family of Low-Aspect-Ratio, All-Movable Control Surfaces for Application to Ship Design" (1958), David Taylor Model Basin
- Zhang, S., "Computational fluid dynamicsbased hull form optimization using approximation method", Engineering Applications of Computational Fluid Mechanics, 12(1), pp.74~88 (2018)