arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.02895math.NAcs.LGcs.NAphysics.comp-phphysics.flu-dyn
收藏

求解线性和非线性偏微分方程的局部极值学习机和区域分解

Local Extreme Learning Machines and Domain Decomposition for Solving Linear and Nonlinear Partial Differential Equations

Purdue University(普渡大学)

Suchuan Dong, Zongwei Li

摘要:

结合极限学习机(ELM)、区域分解和局部神经网络的思想,提出了一种求解线性和非线性偏微分方程的神经网络方法.每个子域上的场解由一个局部前馈神经网络表示,子域边界上施加$C^k$连续性。每个局部神经网络由少量的隐藏层组成,而其最后一个隐藏层可以很宽。局部神经网络的所有隐层中的权重/偏置系数被预先设置为随机值并且是固定的,并且只有输出层中的权重系数是训练参数。整个神经网络通过线性或非线性最小二乘计算来训练,而不是通过反向传播型算法来训练。我们介绍了一个块时间推进计划与所提出的方法进行长时间的动态模拟。目前的方法表现出一个清晰的意义上的收敛相对于神经网络中的自由度。其数值误差通常随自由度的增加而呈指数或接近指数下降。大量的数值实验已经进行了证明所提出的方法的计算性能。我们比较了目前的方法与深度Galerkin方法(DGM)和物理信息神经网络(PINN)的精度和计算成本。目前的方法表现出明显的优越性,其数值误差和网络训练时间大大小于(通常由数量级)比DGM和PINN。我们还比较了目前的方法与经典的有限元法(FEM)。当前方法的计算性能与FEM性能相当,并且经常超过FEM性能。

英文摘要:

We present a neural network-based method for solving linear and nonlinear partial differential equations, by combining the ideas of extreme learning machines (ELM), domain decomposition and local neural networks. The field solution on each sub-domain is represented by a local feed-forward neural network, and $C^k$ continuity is imposed on the sub-domain boundaries. Each local neural network consists of a small number of hidden layers, while its last hidden layer can be wide. The weight/bias coefficients in all hidden layers of the local neural networks are pre-set to random values and are fixed, and only the weight coefficients in the output layers are training parameters. The overall neural network is trained by a linear or nonlinear least squares computation, not by the back-propagation type algorithms. We introduce a block time-marching scheme together with the presented method for long-time dynamic simulations. The current method exhibits a clear sense of convergence with respect to the degrees of freedom in the neural network. Its numerical errors typically decrease exponentially or nearly exponentially as the number of degrees of freedom increases. Extensive numerical experiments have been performed to demonstrate the computational performance of the presented method. We compare the current method with the deep Galerkin method (DGM) and the physics-informed neural network (PINN) in terms of the accuracy and computational cost. The current method exhibits a clear superiority, with its numerical errors and network training time considerably smaller (typically by orders of magnitude) than those of DGM and PINN. We also compare the current method with the classical finite element method (FEM). The computational performance of the current method is on par with, and oftentimes exceeds, the FEM performance.

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。

↑