### Abstract

Original language | English |
---|---|

Article number | 58 |

Number of pages | 12 |

Journal | Computation |

Volume | 7 |

Issue number | 4 |

DOIs | |

Publication status | Published - 8 Oct 2019 |

### Fingerprint

### Keywords

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

### Cite this

*Computation*,

*7*(4), [58]. https://doi.org/10.3390/computation7040058

}

*Computation*, vol. 7, no. 4, 58. https://doi.org/10.3390/computation7040058

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

Research output: Contribution to journal › Article

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

JF - Computation

SN - 2079-3197

IS - 4

M1 - 58

ER -