arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.05337math.NAcs.LGcs.NAmath.DS
收藏

用于常微分方程初值问题和指数1微分代数方程的简约物理信息随机投影神经网络

Parsimonious Physics-Informed Random Projection Neural Networks for Initial-Value Problems of ODEs and index-1 DAEs

Scuola Superiore Meridionale(南方高等学院);Università degli Studi di Napoli Federico II(那不勒斯费德里科二世大学);Consiglio Nazionale delle Ricerche(意大利国家研究委员会)

Gianluca Fabiani, Evangelos Galaris, Lucia Russo, Constantinos Siettos

AI总结:

本研究提出一种基于随机投影的简约物理信息神经网络,用于求解线性隐式ODE初值问题与指数1DAE,通过变步长、延拓法等优化,在7个基准问题上验证了其在高刚性/陡梯度场景下的精度优势与可比的计算成本。

摘要:

我们针对线性隐式形式的非线性常微分方程(ODE)初值问题(IVP)以及指数1微分代数方程(DAE)——这类问题也可由偏微分方程(PDE)的空间离散化产生——的数值求解,提出了一种基于随机投影概念的物理信息神经网络。该架构包含单隐藏层(配备经适当随机参数化的高斯核)和线性输出层,内部权重固定为1。隐藏层与输出层之间的未知权重通过牛顿迭代计算:针对中小规模系统使用Moore-Penrose伪逆,针对中大规模系统则采用带正则化的稀疏QR分解。为处理刚性和陡梯度问题,我们提出了一种用于调整积分区间的变步长方案,并研究了一种为牛顿迭代提供良好初始猜测的延拓法。基于此前关于随机投影的研究,我们证明了该方案对标准形式ODE和半显式形式指数1DAE的逼近能力。均匀分布的最优界基于偏差-方差权衡进行简约选择。我们通过7个基准问题评估了该方案的性能:4个指数1DAE问题,即Robertson模型、描述珠子运动的5个DAE模型、描述放电控制问题的6个DAE模型、Akzo Nobel化学问题;以及3个刚性问题,即Belousov-Zhabotinsky问题、Allen-Cahn PDE和Kuramoto-Sivashinsky PDE。我们将该方案的效率与MATLAB ODE套件中的三个求解器ode23t、ode23s、ode15s进行了对比。结果表明,所提方案在多种情况下优于刚性求解器,尤其在出现高刚性或陡梯度的场景中数值精度更优,而计算成本在实际应用中与现有求解器相当。

英文摘要:

We address a physics-informed neural network based on the concept of random projections for the numerical solution of IVPs of nonlinear ODEs in linear-implicit form and index-1 DAEs, which may also arise from the spatial discretization of PDEs. The scheme has a single hidden layer with appropriately randomly parametrized Gaussian kernels and a linear output layer, while the internal weights are fixed to ones. The unknown weights between the hidden and output layer are computed by Newton's iterations, using the Moore-Penrose pseudoinverse for low to medium, and sparse QR decomposition with regularization for medium to large scale systems. To deal with stiffness and sharp gradients, we propose a variable step size scheme for adjusting the interval of integration and address a continuation method for providing good initial guesses for the Newton iterations. Based on previous works on random projections, we prove the approximation capability of the scheme for ODEs in the canonical form and index-1 DAEs in the semiexplicit form. The optimal bounds of the uniform distribution are parsimoniously chosen based on the bias-variance trade-off. The performance of the scheme is assessed through seven benchmark problems: four index-1 DAEs, the Robertson model, a model of five DAEs describing the motion of a bead, a model of six DAEs describing a power discharge control problem, the chemical Akzo Nobel problem and three stiff problems, the Belousov-Zhabotinsky, the Allen-Cahn PDE and the Kuramoto-Sivashinsky PDE. The efficiency of the scheme is compared with three solvers ode23t, ode23s, ode15s of the MATLAB ODE suite. Our results show that the proposed scheme outperforms the stiff solvers in several cases, especially in regimes where high stiffness or sharp gradients arise in terms of numerical accuracy, while the computational costs are for any practical purposes comparable.

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。

↑