arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.09663math.NAcs.NA
收藏

基于最小二乘法的正则化神经网络(LS-ReCoNNs)用于求解参数传输问题

A Least-Squares-Based Regularity-Conforming Neural Networks (LS-ReCoNNs) for Solving Parametric Transmission Problems

University of the Basque Country (UPV/EHU)(巴斯克大学);CUNEF Universidad(CUNEF大学);Basque Center for Applied Mathematics (BCAM)(巴斯克应用数学中心);Ikerbasque (Basque Foundation For Sciences)(伊克尔巴斯基奎(巴斯克科学基金会))

Shima Baharlouei, Jamie Taylor, David Pardo

AI总结:

LS-ReCoNN通过最小二乘法和正则化神经网络解决参数传输问题,有效捕捉奇异性并保持解的准确性。

摘要:

本文专注于解决一维和二维空间中的参数传输问题。这些问题属于一类出现在异质材料系统建模中的偏微分方程,通常表现出界面处的不连续性和界面相交点处的奇异性。为解决这些问题,我们提出了一种新的深度学习方法,称为基于最小二乘法的正则化神经网络(LS-ReCoNN)。该方法提出了一种损失函数,该函数被证明是能量范数误差的一致上界。该方法将解表示为主成分和奇异成分之和。主成分被分解为平滑部分和梯度跳跃部分,分别捕捉了一维和二维问题中的正则解行为和界面处的降低正则性。奇异成分用于建模交汇奇异性,并通过从一维有限元本征值问题计算得到的基函数进行近似。对于主成分,采用分离表示,包括参数依赖的系数和空间依赖的函数。深度神经网络近似空间依赖的函数,而参数依赖的系数则通过最小二乘求解器确定,其中每个参数实例的最优系数通过求解低维最小二乘问题在线获得。一维和二维的数值实验表明,LS-ReCoNN能够有效捕捉奇异性,同时在广泛参数值范围内保持解的准确性。

英文摘要:

This article focuses on solving parametric transmission problems in one and two spatial dimensions. These problems belong to a class of partial differential equations that arise in the modeling of physical systems with heterogeneous materials. They often exhibit discontinuities across interfaces and singularities at points where interfaces intersect. To address these problems, we propose a new deep learning approach named {\it{Least-Squares-Based Regularity-Conforming Neural Network (LS-ReCoNN)}}. This approach proposes a loss function that is shown to be a consistent upper bound for the energy-norm error. The method represents the solution as the sum of a principal component and a singular component. The principal component is decomposed into smooth and gradient-jump parts, which capture both the regular solution behavior and reduced regularity across interfaces in one- and two-dimensional problems. The singular component is introduced to model junction singularities and it is approximated using basis functions computed from a one-dimensional finite element eigenvalue problem. For the principal component, a separated representation is employed, consisting of parameter-dependent coefficients and space-dependent functions. A deep neural network approximates the space-dependent functions, while the parameter-dependent coefficients are determined by a least-squares solver, where the optimal coefficients for each parameter instance are obtained online by solving a low-dimensional least-squares problem. Numerical experiments in one and two dimensions demonstrate that LS-ReCoNN effectively captures singularities while maintaining solution accuracy across a wide range of parameter values.

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。

↑