Data-Driven Modeling and Prediction of Non-Linearizable Dynamics via Spectral Submanifolds

Abstract

We develop a methodology to construct low-dimensional predictive models from data sets representing essentially nonlinear (or non-linearizable) dynamical systems with a hyperbolic linear part that are subject to external forcing with finitely many frequencies. Our data-driven, sparse, nonlinear models are obtained as extended normal forms of the reduced dynamics on low-dimensional, attracting spectral submanifolds (SSMs) of the dynamical system. We illustrate the power of data-driven SSM reduction on high-dimensional numerical data sets and experimental measurements involving beam oscillations, vortex shedding and sloshing in a water tank. We find that SSM reduction trained on unforced data also predicts nonlinear response accurately under additional external forcing.

arXiv commentUnder consideration at Nature Communications

References in corpus (17)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Deep learning for universal linear embeddings of nonlinear dynamics
• Tipping points in open systems: bifurcation, noise-induced and rate-dependent examples in the climate system
• Koopman invariant subspaces and finite linear representations of nonlinear dynamical systems for control
• Data-Driven Modeling and Prediction of Non-Linearizable Dynamics via Spectral Submanifolds
• How to Compute Invariant Manifolds and their Reduced Dynamics in High-Dimensional Finite-Element Models
• Automated Computation of Autonomous Spectral Submanifolds for Nonlinear Modal Analysis
• Low-order model for successive bifurcations of the fluidic pinball
• Exact Nonlinear Model Reduction for a von Karman beam: Slow-Fast Decomposition and Spectral Submanifolds
• Explicit Backbone Curves from Spectral Submanifolds of Forced-Damped Nonlinear Mechanical Systems
• Data-driven Nonlinear Model Reduction to Spectral Submanifolds in Mechanical Systems
• Koopman mode expansions between simple invariant solutions
• A spectral characterization of nonlinear normal modes
• Nonlinear model identification and spectral submanifolds for multi-degree-of-freedom mechanical vibrations
• Nondestructive Prediction of the Buckling Load of Imperfect Shells
• Koopman analysis of Burgers equation
• Exact Model Reduction for Damped-Forced Nonlinear Beams: An Infinite-Dimensional Analysis

Cited by in corpus (19)

• Enhancing Computational Fluid Dynamics with Machine Learning
• Data-Driven Modeling and Prediction of Non-Linearizable Dynamics via Spectral Submanifolds
• Data-driven Nonlinear Model Reduction to Spectral Submanifolds in Mechanical Systems
• Nonlinear Model Reduction to Fractional and Mixed-Mode Spectral Submanifolds
• Experimental continuation in nonlinear dynamics: recent advances and future challenges
• Data-driven discovery and extrapolation of parameterized pattern-forming dynamics
• Data-Assisted Non-Intrusive Model Reduction for Forced Nonlinear Finite Elements Models
• Data-free Non-intrusive Model Reduction for Nonlinear Finite Element Models via Spectral Submanifolds
• Data-driven modeling of the regular and chaotic dynamics of an inverted flag from experiments
• Domain decomposition for data-driven reduced modeling of large-scale systems
• Distributed computing for physics-based data-driven reduced modeling at scale: Application to a rotating detonation rocket engine
• Data-driven reduced order models using invariant foliations, manifolds and autoencoders
• Active vibration control of nonlinear flexible structures via reduction on spectral submanifolds
• Data-driven guessing and gluing of unstable periodic orbits
• Machine-Learning Enhanced Predictors for Accelerated Convergence of Partitioned Fluid-Structure Interaction Simulations
• A discrete physics-informed training for projection-based reduced order models with neural networks
• Numerical analysis of non-local calculus on finite weighted graphs, with application to reduced-order modelling of dynamical systems
• Model reduction of nonlinear time-delay systems via ODE approximation and spectral submanifolds
• Dynamics-based machine learning of transitions in Couette flow