arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.04056physics.comp-phmath-phmath.MP
收藏

用于研究变系数方程正反问题的带残差单元的梯度增强PINN

Gradient-enhanced PINN with residual unit for studying forward-inverse problems of variable coefficient equations

Hui-Juan Zhou, Yong Chen

AI总结:

本研究提出R-gPINN方法,通过引入残差单元缓解梯度消失并统一线性和非线性问题,同时利用变系数梯度项惩罚配置点以增强物理约束,显著提升了变系数偏微分方程正反问题中预测解与变系数的精度。

摘要:

物理信息神经网络(PINN)是一种强大的新兴方法,即使在样本数据有限的情况下也能用于研究偏微分方程(PDEs)的正反问题。变系数PDEs模拟现实世界现象,具有相当大的物理意义和研究价值。本研究提出一种带残差单元的梯度增强PINN(R-gPINN)方法,以求解变系数PDEs的数据驱动解和函数发现。一方面,该方法将残差单元引入神经网络以缓解梯度消失和网络退化,统一线性和非线性系数问题。我们在本工作中提出两种类型的残差单元结构,以在问题求解中提供更灵活的解决方案。另一方面,通过包含变系数的梯度项,该方法惩罚未能满足物理性质的配置点。这种增强提高了网络对物理约束的遵守程度,并使预测函数更接近目标函数。数值实验包括求解变系数Burgers方程、变系数KdV方程、变系数Sine-Gordon方程和高维变系数Kadomtsev-Petviashvili方程的正反问题。结果表明,使用R-gPINN方法能极大提高求解变系数方程时预测解和预测变系数的精度。

英文摘要:

Physics-informed neural network (PINN) is a powerful emerging method for studying forward-inverse problems of partial differential equations (PDEs), even from limited sample data. Variable coefficient PDEs, which model real-world phenomena, are of considerable physical significance and research value. This study proposes a gradient-enhanced PINN with residual unit (R-gPINN) method to solve the data-driven solution and function discovery for variable coefficient PDEs. On the one hand, the proposed method incorporates residual units into the neural networks to mitigate gradient vanishing and network degradation, unify linear and nonlinear coefficient problem. We present two types of residual unit structures in this work to offer more flexible solutions in problem-solving. On the other hand, by including gradient terms of variable coefficients, the method penalizes collocation points that fail to satisfy physical properties. This enhancement improves the network's adherence to physical constraints and aligns the prediction function more closely with the objective function. Numerical experiments including solve the forward-inverse problems of variable coefficient Burgers equation, variable coefficient KdV equation, variable coefficient Sine-Gordon equation, and high-dimensional variable coefficient Kadomtsev-Petviashvili equation. The results show that using R-gPINN method can greatly improve the accuracy of predict solution and predict variable coefficient in solving variable coefficient equations.

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。

↑