A Machine Learning-based Tool to Correlate Coupled and Uncoupled Numerical Simulations for Submerged Plates Subjected to Underwater Explosions

Abstract

In naval engineering, understanding underwater explosions is crucial for structural integrity and safety, particularly for combat ships. Coupled numerical analyses, which account for fluid-structure interaction (FSI), are accurate but computationally expensive and impractical for real-time applications. In contrast, uncoupled methods are efficient but overlook FSI effects. This study introduces a data-driven approach using a feedforward Deep Neural Network (DNN) to estimate FSI-induced displacements from uncoupled simulations. Trained on numerical datasets of blast-loaded plates with varying characteristics, the DNN predicts the coupled displacement field based on structural parameters of uncoupled simulations. Results demonstrate that this framework provides a fast and reliable alternative to coupled simulations, offering a practical engineering tool for underwater blast scenarios. This work serves as proof of concept that deep-learning-enhanced uncoupled simulations can replace coupled ones, with validity beyond the specific structure in the case study.

Keywords

Underwater explosion / Fluid-structure interaction / Numerical simulation / Deep neural network / Uncoupled approach

References

[1] Bardiani J, Bertagna S, Braidotti L, Marinò A, Bucci V, Sbarufatti C, Manes A. Creep assessment of thermoplastic materials for non-structural components in marine engines. Compos Part B Eng, 2024, 287: 111800

[2] Bardiani J, Sbarufatti C, Manes A. Transfer learning with deep neural network toward the prediction of the mass of the charge in underwater explosion events. J Mar Sci Eng, 2025, 13(2): 190

[3] Biglarkhani M, Sadeghi K. Incremental explosive analysis and its application to performance-based assessment of stiffened and unstiffened cylindrical shells subjected to underwater explosion. Shock Vib, 2017, 2017(1): 3754510

[4] Bousmaha R, Hamou RM, Amine A. Automatic selection of hidden neurons and weights in neural networks for data classification using hybrid particle swarm optimization, multiverse optimization based on Lévy flight. Evol Intell, 2022, 15(3): 1695-1714

[5] Brunton SL, Noack BR, Koumoutsakos P. Machine learning for fluid mechanics. Annu Rev Fluid Mech, 2020, 52(1): 477-508

[6] Cole RHUnderwater explosions, 1948

[7] Cui P, Zhang AM, Wang SP. Small-charge underwater explosion bubble experiments under various boundary conditions. Phys Fluids, 2016, 28(11): 117101

[8] De Camargo FV (2019) Survey on experimental and numerical approaches to model underwater explosions. J Mar Sci Eng. https://doi.org/10.3390/jmse7010015

[9] Ding P, Buijk ASimulation of underwater explosion using MSC Dytran, 2006481051001

[10] DNV GLCLASS GUIDELINE Finite element analysis, 2015

[11] Elkaseer A, Abdelaziz A, Saber M, Nassef A. FEM-based study of precision hard turning of stainless steel 316L. Materials, 2019, 12(16): 2522

[12] Flores-Johnson EA, Shen L, Guiamatsia I, Nguyen GD. Numerical investigation of the impact behaviour of bioinspired nacre-like aluminium composite plates. Compos Sci Technol, 2014, 96: 13-22

[13] Ge L, Zhang AM, Wang SP. Investigation of underwater explosion near composite structures using a combined RKDG-FEM approach. J Comput Phys, 2020, 404: 109113

[14] Giuliano D, Lomazzi L, Giglio M, Manes A. On Eulerian-Lagrangian methods to investigate the blast response of composite plates. Int J Impact Eng, 2023, 173: 104469

[15] Hastie T, Tibshirani R, Friedman J. Springer series in statistics: the elements of statistical learning. Math Intell, 2009, 27(2): 83-85

[16] Hinton GE, Osindero S, Teh YW. A fast learning algorithm for deep belief nets. Neural Comput, 2006, 18(7): 1527-1554

[17] Huang H, Jiao QJ, Nie JX, Qin JF. Numerical modeling of underwater explosion by one-dimensional ANSYS-AUTODYN. J Energetic Mater, 2011, 29(4): 292-325

[18] Jha N, Kumar BK. Underwater explosion pressure prediction and validation using ANSYS/AUTODYN. Int J Sci Res, 2014, 3(12): 1162-1166

[19] Jin QK, Ding GY. A finite element analysis of ship sections subjected to underwater explosion. Int J Impact Eng, 2011, 38(7): 558-566

[20] Keil AH. The response of ships to underwater explosion. SNAME, 1961, 69: 366-410

[21] Kiciński R, Szturomski B. Pressure wave caused by trinitrotoluene (TNT) underwater explosion—short review. Appl Sci, 2020, 10(10): 3433

[22] Kong XS, Gao H, Jin Z, Zheng C, Wang Y. Predictions of the responses of stiffened plates subjected to underwater explosion based on machine learning. Ocean Eng, 2023, 283: 115216

[23] Kumar L, Tummalapalli S, Rathi SC, Murthy LB, Krishna A, Misra S. Machine learning with word embedding for detecting web-services anti-patterns. J Comput Lang, 2023, 75: 101207

[24] Kwon YW, Fox PK. Underwater shock response of a cylinder subjected to a side-on explosion. Comput Struct, 1993, 48(4): 637-646

[25] Lee T, Kwak BJ, Yu J, Lee JH, Noh Y, Moon YH. Deep-learning approach to predict a severe plastic anisotropy of caliber-rolled Mg alloy. Mater Lett, 2020, 269: 127652

[26] Lee YJ, Hsu CH, Huang CH. Pressure hull analysis under shock loading. Shock Vib, 2008, 15(1): 19-32

[27] Liu WT, Ming FR, Zhang AM, Miao XH, Liu YL. Continuous simulation of the whole process of underwater explosion based on Eulerian finite element approach. Appl Ocean Res, 2018, 80: 125-135

[28] Liu Y, Li Z, Sun Q, Fan X, Wang W. Separation dynamics of large-scale fairing section: A fluid–structure interaction study. Proc Inst Mech Eng G J Aerosp Eng, 2013, 227(11): 1767-1779

[29] Liu YZ, Ren SF, Zhao PF. Application of the deep neural network to predict dynamic responses of stiffened plates subjected to near-field underwater explosion. Ocean Eng, 2022, 247: 110537

[30] Löhner R, Li L, Soto OA, Baum JD. An arbitrary Lagrangian–Eulerian method for fluid–structure interactions due to underwater explosions. Int J Numer Methods Heat Fluid Flow, 2023, 33(6): 2308-2349

[31] Lomazzi L, Morin D, Cadini F, Manes A, Aune V. Deep learning-based analysis to identify fluid-structure interaction effects during the response of blast-loaded plates. Int J Protect Struct, 2024, 15(4): 722-752

[32] Luo J, Ying K, He P, Bai J. Properties of Savitzky–Golay digital differentiators. Digit Signal Process, 2005, 15(2): 122-136

[33] Ming FR, Zhang AM, Xue YZ, Wang SP. Damage characteristics of ship structures subjected to shockwaves of underwater contact explosions. Ocean Eng, 2016, 117: 359-382

[34] Mumuni A, Mumuni F. Data augmentation: A comprehensive survey of modern approaches. Array, 2022, 16: 100258

[35] Murugesan M, Jung DW. Johnson Cook material and failure model parameters estimation of AISI-1045 medium carbon steel for metal forming applications. Materials, 2019, 12(4): 609

[36] Nayak S, Lyngdoh GA, Shukla A, Das S. Predicting the near field underwater explosion response of coated composite cylinders using multiscale simulations, experiments, and machine learning. Compos Struct, 2022, 283: 115157

[37] Neto LB, Saleh M, Pickerd V, Yiannakopoulos G, Mathys Z, Reid W. Rapid mechanical evaluation of quadrangular steel plates subjected to localised blast loadings. Int J Impact Eng, 2020, 137: 103461

[38] Nguyen AT. A numerical research on the interaction between underwater explosion bubble and deformable structure using CEL technique. EUREKA: Phys Eng, 2023, 2023(1): 134-151

[39] Nguyen G, Dlugolinsky S, Bobák M, Tran V, López García Á, Heredia I, Hluchý L. Machine learning and deep learning frameworks and libraries for large-scale data mining: a survey. Artif Intell Rev, 2019, 52: 77-124

[40] Nguyen VT, Phan TH, Duy TN, Park WG. Numerical modeling for compressible two-phase flows and application to near-field underwater explosions. Comput Fluids, 2021, 215: 104805

[41] Olmi F, Nascimento KD. Small debris impact simulation using MSC/DYTRAN. 1999 MSC Worldwide Aerospace Conference Proceedings, 1999Vol. 1

[42] Peng YX, Zhang AM, Ming FR. Numerical simulation of structural damage subjected to the near-field underwater explosion based on SPH and RKPM. Ocean Eng, 2021, 222: 108576

[43] Rackwitz F. Possibilities and limitations of ALE large deformations analyses in geotechnical engineering. Recent Developments of Soil Mechanics and Geotechnics in Theory and Practice, 202097-112

[44] Rajendran R, Narasimhan K. Damage prediction of clamped circular plates subjected to contact underwater explosion. Int J Impact Eng, 2001, 25(4): 373-386

[45] Ramajeyathilagam K, Vendhan CP. Deformation and rupture of thin rectangular plates subjected to underwater shock. Int J Impact Eng, 2004, 30(6): 699-719

[46] Ren SF, Zhao PF, Wang SP, Liu YZ. Damage prediction of stiffened plates subjected to underwater contact explosion using the machine learning-based method. Ocean Eng, 2022, 266: 112839

[47] Rolfe E, Quinn R, Irven G, Brick D, Dear JP, Arora H. Underwater blast loading of partially submerged sandwich composite materials in relation to air blast loading response. Int J Lightweight Mater Manuf, 2020, 3(4): 387-402

[48] Sagar HJ, El Moctar O. Dynamics of a cavitation bubble between oblique plates. Phys Fluids, 2023, 35(1): 017105

[49] Sagar HJ, el Moctar O. Hydroelasticity effects induced by a single cavitation bubble collapse. J Fluids Struct, 2024, 127: 104131

[50] Shehu E, Lomazzi L, Giglio M, Manes A. Computational modeling of confined blast waves with focus on interaction with structures. In: IOP Conf Ser Mater Sci Eng, 2023, 1275(1): 012028

[51] Sigrist JF, Broc D. A versatile method to calculate the response of equipment mounted on ship hulls subjected to underwater shock waves. Finite Elem Anal Des, 2023, 218: 103917

[52] Spear DG, Palazotto AN, Kemnitz RA. Modeling and simulation techniques used in high strain rate projectile impact. Mathematics, 2021, 9(3): 274

[53] Tran P, Wu C, Saleh M, Neto LB, Nguyen-Xuan H, Ferreira AJM. Composite structures subjected to underwater explosive loadings: A comprehensive review. Compos Struct, 2021, 263: 113684

[54] Venkatesan J, Iqbal MA, Gupta NK, Bratov V, Kazarinov N, Morozov F. Ballistic characteristics of bi-layered armour with various aluminium backing against ogive nose projectile. Procedia Struct Integr, 2017, 6: 40-47

[55] Walters AP, Didoszak JM, Kwon YW. Explicit modeling of solid ocean floor in shallow underwater explosions. Shock Vib, 2013, 20(1): 189-197

[56] Wang H, Cheng YS, Liu J, Gan L. The fluid-solid interaction dynamics between underwater explosion bubble and corrugated sandwich plate. Shock Vib, 2016, 2016(1): 6057437

[57] Wang H, Liu B, Lei J, Zhao N. Improved deep neural network for predicting structural response of stiffened cylindrical shells to far-field underwater explosion. Ocean Eng, 2024, 298: 117258

[58] Wang Y, Dong H, Dong T, Xu X. Dumbbell-shaped damage effect of closed cylindrical shell subjected to far-field side-on underwater explosion shock wave. J Mar Sci Eng, 2022, 10(12): 1874

[59] Yu J, Liu JH, Wang HK, Wang J, Zhou ZT, Mao HB. Application of two-phase transition model in underwater explosion cavitation based on compressible multiphase flows. AIP Adv, 2022, 12(2): 025117

[60] Zhang ZF, Wang C, Wang LK, Zhang AM, Silberschmidt VV. Underwater explosion of cylindrical charge near plates: Analysis of pressure characteristics and cavitation effects. Int J Impact Eng, 2018, 121: 91-105

[61] Zhou ZHMachine learning, 2021

RIGHTS & PERMISSIONS

Harbin Engineering University and Springer-Verlag GmbH Germany, part of Springer Nature