arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.03643math.NAcs.NAmath-phmath.MP
收藏

用于求解正问题和反问题动态问题的谱积分神经网络(SINNs)

Spectral integrated neural networks (SINNs) for solving forward and inverse dynamic problems

Lin Qiu, Fajie Wang, Wenzhen Qu, Yan Gu, Qing-Hua Qin

AI总结:

本文提出谱积分神经网络(SINNs),通过谱积分方法进行时间离散并结合全连接神经网络求解空间域偏微分方程,用于解决三维正反动态问题,在收敛速度、精度和效率上优于传统物理信息神经网络,且能稳定处理长时间动态问题。

摘要:

本文提出了一种新的神经网络框架,称为谱积分神经网络(SINNs),用于求解三维正问题和反问题动态问题。在SINNs中,应用谱积分方法进行时间离散化,然后采用全连接神经网络在空间域上求解所得的偏微分方程(PDEs)。具体而言,在网络架构中以空间坐标作为输入,输出层配置为多个输出,每个输出专门用于近似在谱方法中使用的高斯点所表征的不同时间实例的解。通过利用自动微分技术和谱积分方案,SINNs最小化基于控制PDEs和边界条件构建的损失函数,以获得动态问题的解。此外,我们利用多项式基函数展开未知函数,旨在增强SINNs在处理反问题时的性能。所构思的框架在六个涉及非线性PDEs的正问题和反问题动态问题上进行了测试。数值结果表明,在收敛速度、计算精度和效率方面,SINNs优于广泛使用的物理信息神经网络。还值得注意的是,SINNs表现出能够为长时间动态问题提供准确且稳定解的能力。

英文摘要:

This paper proposes a novel neural network framework, denoted as spectral integrated neural networks (SINNs), for resolving three-dimensional forward and inverse dynamic problems. In the SINNs, the spectral integration method is applied to perform temporal discretization, and then a fully connected neural network is adopted to solve resulting partial differential equations (PDEs) in the spatial domain. Specifically, spatial coordinates are employed as inputs in the network architecture, and the output layer is configured with multiple outputs, each dedicated to approximating solutions at different time instances characterized by Gaussian points used in the spectral method. By leveraging the automatic differentiation technique and spectral integration scheme, the SINNs minimize the loss function, constructed based on the governing PDEs and boundary conditions, to obtain solutions for dynamic problems. Additionally, we utilize polynomial basis functions to expand the unknown function, aiming to enhance the performance of SINNs in addressing inverse problems. The conceived framework is tested on six forward and inverse dynamic problems, involving nonlinear PDEs. Numerical results demonstrate the superior performance of SINNs over the popularly used physics-informed neural networks in terms of convergence speed, computational accuracy and efficiency. It is also noteworthy that the SINNs exhibit the capability to deliver accurate and stable solutions for long-time dynamic problems.

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。

↑