arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.17331cs.CE
收藏

使用物理信息神经网络求解渗流问题的一种新方法

A novel solution for seepage problems using physics-informed neural networks

Tianfu Luo, Yelin Feng, Qingfu Huang, Zongliang Zhang, Mingjiao Yan, Zaihong Yang, Dawei Zheng, Yang Yang

AI总结:

本研究提出利用物理信息神经网络(PINN)求解渗流问题,通过设计包含微分算子、边界条件和初始条件的综合损失函数来逼近水头分布,在四个基准测试中展现出超越传统有限元方法(FEM)的准确性与鲁棒性。

摘要:

物理信息神经网络(PINN)通过将神经网络的能力与问题的控制物理定律相结合,提供了独特的优势。在本研究中,我们提出了一种利用PINN求解渗流问题的创新方法,借助深度神经网络(DNNs)的能力来逼近渗流分析中的水头分布。为了有效训练PINN模型,我们引入了一个包含三个部分的综合损失函数:一个用于评估微分算子,另一个用于评估边界条件,第三个用于评估初始条件。PINN的验证涉及求解四个基准渗流问题。结果明确表明了PINN在求解渗流问题上的卓越准确性,在处理稳态和自由表面渗流问题时超越了FEM的准确性。因此,所提出的方法突显了PINN的鲁棒性,并强调了其在有效应对一系列渗流挑战时的精确性。这种融合使得能够推导出准确的解决方案,克服了传统方法中固有的网格生成和对复杂几何形状适应性等局限性。

英文摘要:

A Physics-Informed Neural Network (PINN) provides a distinct advantage by synergizing neural networks' capabilities with the problem's governing physical laws. In this study, we introduce an innovative approach for solving seepage problems by utilizing the PINN, harnessing the capabilities of Deep Neural Networks (DNNs) to approximate hydraulic head distributions in seepage analysis. To effectively train the PINN model, we introduce a comprehensive loss function comprising three components: one for evaluating differential operators, another for assessing boundary conditions, and a third for appraising initial conditions. The validation of the PINN involves solving four benchmark seepage problems. The results unequivocally demonstrate the exceptional accuracy of the PINN in solving seepage problems, surpassing the accuracy of FEM in addressing both steady-state and free-surface seepage problems. Hence, the presented approach highlights the robustness of the PINN and underscores its precision in effectively addressing a spectrum of seepage challenges. This amalgamation enables the derivation of accurate solutions, overcoming limitations inherent in conventional methods such as mesh generation and adaptability to complex geometries.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑