arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.14124nlin.CD
收藏

数据驱动的非线性动力学系统非线性模态识别:基于物理约束的归一化流方法

Data-driven nonlinear modal identification of nonlinear dynamical systems with physics-constrained Normalizing Flows

Abdolvahhab Rostamijavanani, Shanwu Li, Yongchao Yang

AI总结:

提出一种物理约束的归一化流数据驱动方法,仅用测量数据识别非线性正规模态及其变换函数,利用归一化流的独立性与可逆性实现非线性模态分解。

摘要:

识别动力学系统的固有坐标或模态,对于理解、分析和表征复杂系统的潜在动力学行为至关重要。对于非线性动力学系统,这提出了一个关键挑战,因为线性模态变换(对线性系统具有普遍性)并不适用于非线性动力学系统。作为线性正规模态的自然扩展,非线性正规模态(NNMs)框架为非线性动力学提供了全面的表示。理论上,NNMs 可以从动力学系统的闭式模型或方程中数值计算或解析求解,或者通过可控的输入-输出测试进行实验识别,然而,这两种方法在实践中通常是未知或不可用的。在本研究中,我们提出了一种物理集成的归一化流(Normalizing Flows)深度学习数据驱动方法,该方法仅使用测量的响应数据来识别 NNMs 及其非线性模态变换函数。具体来说,我们利用了归一化流模型的独特特征:1)利用归一化流自然张成的独立潜在空间,以促进非线性模态分解;2)通过归一化流的可逆变换,实现原始坐标与模态坐标之间高效且精确的非线性变换。因此,我们的框架利用归一化流的独立性和可逆性来构建一个模型,以捕捉未知非线性动力学系统的动力学行为。

英文摘要:

Identifying the intrinsic coordinates or modes of the dynamical systems is essential to understand, analyze, and characterize the underlying dynamical behaviors of complex systems. For nonlinear dynamical systems, this presents a critical challenge as the linear modal transformation, which is universal for linear systems, does not apply to nonlinear dynamical systems. As natural extensions to linear normal modes,the nonlinear normal modes (NNMs) framework provides a comprehensive representation of nonlinear dynamics. Theoretically, NNMs may either be computed numerically or analytically from the closed-form models or equations of dynamical systems, or experimentally identified from controllable input-output tests, both of which, however, are typically unknown or unavailable practically. In this study, we present a physics-integrated Normalizing Flows deep learning-based data-driven approach which identifies the NNMs and the nonlinear modal transformation function of NNMs using measured response data only. Specifically, we leverage the unique features of the Normalizing Flows model: 1) the independent latent spaces, naturally spanned by the Normalizing Flows, are exploited to facilitate nonlinear modal decomposition; 2) the invertible transformation through the Normalizing Flows, enabling efficient and accurate nonlinear transformation between original and modal coordinates transformation. Therefore, our framework leverages the independency feature and invertibility of Normalizing Flows to create a model that captures the dynamics of unknown nonlinear dynamical 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。

↑