The Koopman operator is a powerful approach to global stability analysis of nonlinear systems, which provides a systematic procedure for Lyapunov function design. In this framework, Lyapunov functions are obtained through the eigenfunctions of the Koopman operator associated with the eigenvalues of the Jacobian matrix at the equilibrium. In practice, the eigenfunctions are approximated via a finite-dimensional representation of the operator, and there is no guarantee that the approximated spectrum accurately matches the true one. In this paper, we develop a kernel-based method to compute Koopman eigenfunctions and preserve the spectrum of the Jacobian matrix. This approach is suitable for stability analysis of high-dimensional systems thanks to the kernel trick. Moreover, the Lyapunov function candidate is validated through a scenario-based optimization technique that provides a reliable estimation of the region of attraction of the system.
Koopman spectra in reproducing kernel Hilbert spaces
每一个可逆的保测度动力系统都包含一个Koopman算子,它是一个线性的酉演化算子,作用于与不变测度相关的观测量的$L^2$空间。Koopman本征函数表示动力学的准周期或非混合分量。从给定的时间序列中提取这些本征函数及其相关的本征频率是一个重要的问题,当底层系统具有密集的点谱,或连续谱行为类似于噪声。本文介绍了识别Koopman特征频率和特征函数的方法,从离散采样的时间序列所产生的这样一个系统与未知的动态。我们的主要结果给出了傅立叶函数的充要条件,定义在$N$状态采样沿轨道的动态,可扩展到Koopman特征函数的整个状态空间,躺在再生核希尔伯特空间(RKHS)。特别是,我们表明,这样的扩展存在当且仅当傅立叶函数的RKHS范数不发散为$ N \to \infty $,在这种情况下,相应的傅立叶频率也是库普曼本征频率。如果这样的RKHS扩展不存在,我们仍然可以构造本征函数的$L^2$近似。对具有弱周期分量的混合谱系统的数值实验表明,与传统的基于离散傅里叶变换的谱估计方法相比,该方法在识别Koopman特征频率方面具有更高的技巧.
Kernel Methods for Stochastic Dynamical Systems with Application to Koopman Eigenfunctions: Feynman-Kac Representations and RKHS Approximation
Department of Computing and Mathematical Sciences, Caltech(加州理工学院计算与数学科学系);The Alan Turing Institute(艾伦·图灵研究所);Department of Mechanical Engineering, Clemson University(克莱姆森大学机械工程系)
Kernel Methods for the Construction of Certified Lyapunov Functions via Approximate Koopman Eigenfunctions
University of Sussex(萨塞克斯大学);University of Iceland(冰岛大学);Caltech(加州理工学院);Alan Turing Institute(艾伦·图灵研究所);Ca’ Foscari University of Venice(威尼斯卡福斯卡里大学);Clemson University(克莱姆森大学)
Kernel Methods for Some Transport Equations with Application to Learning Kernels for the Approximation of Koopman Eigenfunctions: A Unified Approach via Variational Methods, Green's Functions and the Method of Characteristics
Department of Computing and Mathematical Sciences, Caltech(加州理工学院计算与数学科学系);The Alan Turing Institute(艾伦·图灵研究所);Department of Mechanical Engineering, Clemson University(克莱姆森大学机械工程系)
Verifiable Regularity Criterion for Conditional Expectation Operators and Conditional Mean Embeddings with Applications to Nonparametric Regression, Bayesian Inverse Problems, and Koopman Operators
Technische Universität Ilmenau(伊尔梅瑙工业大学);Freie Universität Berlin(柏林自由大学);Chemnitz University of Technology(开姆尼茨工业大学)
Trustworthy Koopman Operator Learning: Invariance Diagnostics and Error Bounds
Centre for Mathematical Sciences, University of Cambridge, UK(剑桥大学数学科学中心,英国);Department of Mathematics, Imperial College London, UK(伦敦帝国理工学院数学系,英国);Department of Mechanical Engineering, University of Washington, USA(美国华盛顿大学机械工程系)
Data-driven Stabilization of Discrete-time Control-affine Nonlinear Systems: A Koopman Operator Approach
近年来,数据驱动的动力系统分析引起了人们的广泛关注,Perron-Frobenius算子和Koopman算子等传递算子技术也得到了广泛的应用。由于数据总是在离散时间获得的,在本文中,我们提出了一个纯粹的数据驱动的方法设计的稳定反馈控制律的一般类的离散时间控制仿射非线性系统。特别是,我们使用Koopman算子提升一个控制仿射系统到一个高维空间,其中控制系统的演化是双线性的。我们分析了提升的双线性系统的可控性,并将其与潜在的非线性系统的可控性联系起来。然后,我们利用控制李雅普诺夫函数(CLF)的概念,设计一个状态反馈法,稳定的原点。此外,我们证明了该方法的有效性,以稳定的起源的Van der Pol振荡器和混沌Henon映射的时间序列数据。