arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.01124math.OC
收藏

学习用于预测和控制的参数化Koopman分解

Learning Parametric Koopman Decompositions for Prediction and Control

Yue Guo, Milan Korda, Ioannis G. Kevrekidis, Qianxiao Li

AI总结:

本文提出一种参数化Koopman分解方法,通过神经网络联合学习不变子空间和投影算子族,在预测和最优控制中显著优于现有方法,尤其适用于高维和强非线性系统。

摘要:

我们提出了一种方法,用于构造依赖于静态或时变参数的动态系统的近似Koopman型分解。我们的方法同时构造一个不变子空间和作用于该子空间的投影Koopman算子的参数化族。我们通过神经网络对投影Koopman算子族和跨越不变子空间的字典进行参数化,并使用轨迹数据联合训练它们。我们从理论上证明了我们方法的有效性,并通过数值实验表明,在解决预测问题方面,它比现有方法有显著改进,尤其是在具有大状态或参数维度以及强非线性动态的问题上。此外,我们的方法能够实现涉及非线性动态的最优控制问题的数据驱动求解,对可控性具有有趣的影响。

英文摘要:

We present an approach to construct approximate Koopman-type decompositions for dynamical systems depending on static or time-varying parameters. Our method simultaneously constructs an invariant subspace and a parametric family of projected Koopman operators acting on this subspace. We parametrize both the projected Koopman operator family and the dictionary that spans the invariant subspace by neural networks and jointly train them with trajectory data. We show theoretically the validity of our approach, and demonstrate via numerical experiments that it exhibits significant improvements over existing methods in solving prediction problems, especially those with large state or parameter dimensions, and those possessing strongly non-linear dynamics. Moreover, our method enables data-driven solution of optimal control problems involving non-linear dynamics, with interesting implications on controllability.

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。

↑