混乱的
序列(生物学)
偏微分方程
人工神经网络
航程(航空)
算法
计算机科学
数学
操作员(生物学)
应用数学
微分方程
简单(哲学)
空格(标点符号)
数值分析
系列(地层学)
数学优化
动力系统理论
动力系统(定义)
差速器(机械装置)
图层(电子)
弹道
信号处理
期限(时间)
时滞微分方程
作者
Jin Ming Song,Zhenya Yan
摘要
Abstract. Physics-informed neural networks (PINNs) have been widely applied in solving various physical models, including partial differential equations (PDEs). However, they have a considerable probability of failure when simulating dynamical systems with multiscale, high-frequency, or chaotic behaviors. The possible reason might be that the majority of PINNs methodologies regard space and time as a unified entity, thereby neglecting temporal dependencies across previous or subsequent time steps. In this paper, an advanced network structure, referred to as AttnPINNs, is proposed by stacking self-attention blocks behind a pretrained PINN. We introduce a sequence operator to transform the inputs from spatio-temporal points into sequential formats and a self-attention layer to capture the correlation of solution sequences. Furthermore, we provide a rigorous proof of convergence, indicating that merely the introduction of self-attention blocks is sufficient to bring about significant performance improvements by comparing the AttnPINNs with other advanced architectures (e.g., PINNs, QRes, first-layer sine, and PINNsFormer). Meanwhile, the numerical experiment results show that AttnPINNs method demonstrates superior performance and outperforms most of the other strategies on a wide range of PDEs, the solutions of which tend to have abrupt changes or exhibit multiscale, high-frequency, and chaotic properties.
科研通智能强力驱动
Strongly Powered by AbleSci AI