Machine-learning prediction of underwater shock loading on structures

Mou Zhang, Dimitris Drikakis, Lei Li, Xiu Yan

Research output: Contribution to journalArticle

Abstract

Due to the complex physics of underwater explosion problems, it is difficult to derive analytical solutions for accurate results. In this study, a machine learning method to train a back propagation neural network for parameters prediction, is presented for the first time in literature. The specific problem is the response of a structure submerged in water subjected to shock loads produced by an underwater explosion with the detonation point being far away from the structure so that the loading wave can be regarded as a planar shock wave. Two rigid parallel plates connected by a linear spring and a linear dashpot that simulate structural stiffness and damping respectively, represent the structure. Taking the Laplace transform of the governing equations, solving the resulting equations, and then taking the inverse Laplace transform, the simplified problem is analysed theoretically. The coupled ordinary differential equations governing the motion of the system are also solved numerically by the fourth-order Runge-Kutta method and then verified by a finite element method using LSDYNA. The parametric training with the BP-Neural Network algorithm has been conducted to delineate effects of structural stiffness and damping on the attenuation of shock waves, the cavitation time, and the time of maximum momentum transfer. The prediction results agree well with the validation and test sample results.
LanguageEnglish
Article number58
Number of pages12
JournalComputation
Volume7
Issue number4
DOIs
Publication statusPublished - 8 Oct 2019

Fingerprint

Underwater explosions
Laplace transforms
Shock waves
Learning systems
Damping
Stiffness
Neural networks
Inverse transforms
Momentum transfer
Runge Kutta methods
Detonation
Backpropagation
Cavitation
Ordinary differential equations
Physics
Finite element method
Water

Keywords

  • machine learning
  • neural networks
  • fluid-structure interaction
  • explosion

Cite this

Zhang, Mou ; Drikakis, Dimitris ; Li, Lei ; Yan, Xiu. / Machine-learning prediction of underwater shock loading on structures. In: Computation. 2019 ; Vol. 7, No. 4.
@article{eaf8194f107142e993e910effc7a0cb1,
title = "Machine-learning prediction of underwater shock loading on structures",
abstract = "Due to the complex physics of underwater explosion problems, it is difficult to derive analytical solutions for accurate results. In this study, a machine learning method to train a back propagation neural network for parameters prediction, is presented for the first time in literature. The specific problem is the response of a structure submerged in water subjected to shock loads produced by an underwater explosion with the detonation point being far away from the structure so that the loading wave can be regarded as a planar shock wave. Two rigid parallel plates connected by a linear spring and a linear dashpot that simulate structural stiffness and damping respectively, represent the structure. Taking the Laplace transform of the governing equations, solving the resulting equations, and then taking the inverse Laplace transform, the simplified problem is analysed theoretically. The coupled ordinary differential equations governing the motion of the system are also solved numerically by the fourth-order Runge-Kutta method and then verified by a finite element method using LSDYNA. The parametric training with the BP-Neural Network algorithm has been conducted to delineate effects of structural stiffness and damping on the attenuation of shock waves, the cavitation time, and the time of maximum momentum transfer. The prediction results agree well with the validation and test sample results.",
keywords = "machine learning, neural networks, fluid-structure interaction, explosion",
author = "Mou Zhang and Dimitris Drikakis and Lei Li and Xiu Yan",
year = "2019",
month = "10",
day = "8",
doi = "10.3390/computation7040058",
language = "English",
volume = "7",
journal = "Computation",
issn = "2079-3197",
number = "4",

}

Machine-learning prediction of underwater shock loading on structures. / Zhang, Mou ; Drikakis, Dimitris; Li, Lei; Yan, Xiu.

In: Computation, Vol. 7, No. 4, 58, 08.10.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Machine-learning prediction of underwater shock loading on structures

AU - Zhang, Mou

AU - Drikakis, Dimitris

AU - Li, Lei

AU - Yan, Xiu

PY - 2019/10/8

Y1 - 2019/10/8

N2 - Due to the complex physics of underwater explosion problems, it is difficult to derive analytical solutions for accurate results. In this study, a machine learning method to train a back propagation neural network for parameters prediction, is presented for the first time in literature. The specific problem is the response of a structure submerged in water subjected to shock loads produced by an underwater explosion with the detonation point being far away from the structure so that the loading wave can be regarded as a planar shock wave. Two rigid parallel plates connected by a linear spring and a linear dashpot that simulate structural stiffness and damping respectively, represent the structure. Taking the Laplace transform of the governing equations, solving the resulting equations, and then taking the inverse Laplace transform, the simplified problem is analysed theoretically. The coupled ordinary differential equations governing the motion of the system are also solved numerically by the fourth-order Runge-Kutta method and then verified by a finite element method using LSDYNA. The parametric training with the BP-Neural Network algorithm has been conducted to delineate effects of structural stiffness and damping on the attenuation of shock waves, the cavitation time, and the time of maximum momentum transfer. The prediction results agree well with the validation and test sample results.

AB - Due to the complex physics of underwater explosion problems, it is difficult to derive analytical solutions for accurate results. In this study, a machine learning method to train a back propagation neural network for parameters prediction, is presented for the first time in literature. The specific problem is the response of a structure submerged in water subjected to shock loads produced by an underwater explosion with the detonation point being far away from the structure so that the loading wave can be regarded as a planar shock wave. Two rigid parallel plates connected by a linear spring and a linear dashpot that simulate structural stiffness and damping respectively, represent the structure. Taking the Laplace transform of the governing equations, solving the resulting equations, and then taking the inverse Laplace transform, the simplified problem is analysed theoretically. The coupled ordinary differential equations governing the motion of the system are also solved numerically by the fourth-order Runge-Kutta method and then verified by a finite element method using LSDYNA. The parametric training with the BP-Neural Network algorithm has been conducted to delineate effects of structural stiffness and damping on the attenuation of shock waves, the cavitation time, and the time of maximum momentum transfer. The prediction results agree well with the validation and test sample results.

KW - machine learning

KW - neural networks

KW - fluid-structure interaction

KW - explosion

UR - https://www.mdpi.com/journal/computation

U2 - 10.3390/computation7040058

DO - 10.3390/computation7040058

M3 - Article

VL - 7

JO - Computation

T2 - Computation

JF - Computation

SN - 2079-3197

IS - 4

M1 - 58

ER -