arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.01835cs.LG
收藏

基于子系统控制方程信息的耦合系统Koopman算子学习

Learning Koopman operators for coupled systems via information on governing equations of subsystems

Saitama University(埼玉大学)

Tatsuya Naoi, Jun Ohkubo

AI总结:

本文针对纯数据驱动的EDMD在有限数据下对耦合系统建模不稳定的问题,提出利用子系统控制方程作为先验的Koopman算子学习方法,经耦合振子系统数值实验验证了有效性。

摘要:

非线性耦合系统在科学与工程领域普遍存在,由于其高维性及子系统间复杂的相互作用,对这类系统的分析与建模颇具挑战性。近年来,基于Koopman算子的算子理论方法作为分析和建模非线性动力系统的有力工具受到关注,扩展动态模式分解(EDMD)是近似Koopman算子最常用的方法之一。然而,EDMD是纯数据驱动的方法,在数据量有限的耦合系统中可能不稳定且精度不足。本文提出一种利用各子系统控制微分方程构建耦合系统有限维Koopman近似的方法,该方法通过将已知子系统动力学作为先验信息,从有限数量的快照中学习耦合诱导的修正项,以提高数据效率,还通过耦合振子系统的数值实验验证了其有效性。

英文摘要:

Nonlinear coupled systems are ubiquitous in science and engineering. The analysis and modeling of such systems are challenging due to their high dimensionality and complex interactions among subsystems. In recent years, operator-theoretic methods based on the Koopman operator have attracted attention as a powerful tool for analyzing and modeling nonlinear dynamical systems. Extended dynamic mode decomposition (EDMD) is one of the most popular methods for approximating the Koopman operator. However, EDMD is a purely data-driven method, and it may be unstable and inaccurate for coupled systems under limited data availability. In this paper, we propose a method to construct a finite-dimensional Koopman matrix for coupled systems using the differential equations governing each subsystem. By regularizing the Koopman matrix toward a prior constructed from the subsystem equations, the proposed method improves prediction accuracy when only a limited number of snapshot pairs are available. We also demonstrate its effectiveness through numerical experiments on coupled oscillator systems.

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。

↑