1/1
2 files

Dynamic Analysis of One-Dimensional Continuum based on Physics-Informed Neural Networks

dataset
posted on 24.11.2021, 04:18 authored by Takashi Miyamoto, Mayuko Nishio, Pang-jo ChunPang-jo Chun

Surrogate models, which reproduce the inputs and outputs of physical phenomena in a data-driven man- ner, are increasingly being used as an alternative means of making fast predictions of physical problems, but there is no guarantee that the solutions will satisfy the physical conditions. Physics-Informed Neural Net- works (PINNs), on the other hand, are neural networks that solve the governing equations in a data-driven manner by introducing a loss function that represents the constraints imposed by the governing equations. In this paper, we present the formulation and code implementation of PINNs for a one-dimensional continuum free vibration problem.

History

Manuscript title

Dynamic Analysis of One-Dimensional Continuum based on Physics-Informed Neural Networks

Article DOI

10.11532/jsceiii.2.J2_152

Corresponding author email address

tmiyamoto@yamanashi.ac.jp

Translated title

Physics-Informed Neural Networksによる 1 次元連続体の動的解析

Translated description

物理現象の入出力をデータ駆動的に再現するサロゲートモデルは,物理問題の高速な予測を行う代替的な手 段としてその利用が進んでいるが,得られた解が物理的な条件を満足する保証がない問題が知られている.こ れに対して,Physics-Informed Neural Networks(PINNs)は支配方程式による拘束を表現した損失関数を導入す ることで,支配方程式をデータ駆動的に求解するニューラルネットワークである.本稿では,1 次元連続体の自 由振動問題に対して PINNs の定式化とコード実装を行う.

Translated manuscript title

Physics-Informed Neural Networksによる 1 次元連続体の動的解析

Translated authors

宮本崇, 西尾真由子, 全邦釘