Sparse reduced-order modeling : Sensor-based dynamics to full-state estimation

Abstract

We propose a general dynamic reduced-order modeling framework for typical experimental data: time-resolved sensor data and optional non-time-resolved PIV snapshots. This framework contains four steps. First, the sensor signals are lifted to a dynamic feature space. Second, we identify a sparse human-interpretable nonlinear dynamical system for the feature state based on the sparse identification of nonlinear dynamics (SINDy). Third, if PIV snapshots are available, a local linear mapping from the feature state to velocity fields is shown to be orders of magnitudes more accurate than optimal modal expansions of the same order. Fourth, a generalized feature-based modal decomposition identifies coherent structures that are most dynamically correlated with the linear and nonlinear interaction terms in the sparse model, adding interpretability. Steps 1 and 2 define a black-box model. Optional steps 3 and 4 lift the black-box dynamics to a 'gray-box' model of the coherent structures, if non-time-resolved full-state data is available. This gray-box modeling strategy is successfully applied to the transient and post-transient laminar cylinder wake, and compares favorably with a POD model. We foresee numerous applications of this highly flexible modeling strategy, including estimation, prediction and control. Moreover, the feature space may be based on intrinsic coordinates, which are unaffected by a key challenge of modal expansion: the slow change of low-dimensional coherent structures with changing geometry and varying parameters.

References in corpus (3)

• Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
• Model selection for dynamical systems via sparse regression and information criteria
• Network-theoretic approach to sparsified discrete vortex dynamics

Cited by in corpus (56)

• Physics-informed learning of governing equations from scarce data
• Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
• Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and control
• SINDy-PI: A Robust Algorithm for Parallel Implicit Sparse Identification of Nonlinear Dynamics
• Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data
• Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
• A deep learning enabler for non-intrusive reduced order modeling of fluid flows
• Robust flow field reconstruction from limited measurements via sparse representation
• Multi-Scale Proper Orthogonal Decomposition of Complex Fluid Flows
• On closures for reduced order models $-$ A spectrum of first-principle to machine-learned avenues
• Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
• Reinforcement-learning-based control of confined cylinder wakes with stability analyses
• Data-driven recovery of hidden physics in reduced order modeling of fluid flows
• Physics-constrained, low-dimensional models for MHD: First-principles and data-driven approaches
• Low-order model for successive bifurcations of the fluidic pinball
• Discovery of Physics from Data: Universal Laws and Discrepancies
• Cluster-based feedback control of turbulent post-stall separated flows
• Nonlinear stochastic modeling with Langevin regression
• Feature engineering and symbolic regression methods for detecting hidden physics from sparse sensors
• Dynamic Feature-based Deep Reinforcement Learning for Flow Control of Circular Cylinder with Sparse Surface Pressure Sensing
• Leveraging reduced-order models for state estimation using deep learning
• Cluster-based network model
• Memory embedded non-intrusive reduced order modeling of non-ergodic flows
• Parametric Dynamic Mode Decomposition for Reduced Order Modeling
• Sparse nonlinear models of chaotic electroconvection
• Data-driven modeling of the chaotic thermal convection in an annular thermosyphon
• Linear and Nonlinear Dimensionality Reduction from Fluid Mechanics to Machine Learning
• An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modelling
• Data-driven nonlinear aeroelastic models of morphing wings for control
• Dimensionality Reduction and Reduced Order Modeling for Traveling Wave Physics
• Interplay of Sensor Quantity, Placement and System Dimensionality on Energy Sparse Reconstruction of Fluid Flows
• Cluster-based hierarchical network model of the fluidic pinball -- Cartographing transient and post-transient, multi-frequency, multi-attractor behaviour
• Reinforcement-learning-based control of convectively-unstable flows
• Galerkin force model for transient and post-transient dynamics of the fluidic pinbal
• WeakIdent: Weak formulation for Identifying Differential Equations using Narrow-fit and Trimming
• Sampling and resolution characteristics in reduced order models of shallow water equations: intrusive vs non-intrusive
• Learning physically consistent mathematical models from data using group sparsity
• Data-driven Modeling of Rotating Detonation Waves
• An accuracy-enhanced transonic flow prediction method fusing deep learning and reduced-order model
• Seismic Wavefield Reconstruction based on Compressed Sensing using Data-Driven Reduced-Order Model
• Optimization of Sparse Sensor Placement for Estimation of Wind Direction and Surface Pressure Distribution Using Time-Averaged Pressure-Sensitive Paint Data on Automobile Model
• Adaptive sparse interpolation for accelerating nonlinear stochastic reduced-order modeling with time-dependent bases
• Metric for attractor overlap
• Machine-learned control-oriented flow estimation for multiactuator multi-sensor systems exemplified for the fluidic pinball
• Data-Driven Stabilization of Periodic Orbits
• Sparse Convolution-based Markov Models for Nonlinear Fluid Flows
• Randomized methods to characterize large-scale vortical flow network
• Data-driven Discovery of Delay Differential Equations with Discrete Delays
• A data-based, reduced-order, dynamic estimator for reconstruction of non-linear flows exhibiting limit-cycle oscillations
• Self-tuning model predictive control for wake flows
• Actuation manifold from snapshot data
• Promoting global stability in data-driven models of quadratic nonlinear dynamics
• Model-Based Estimation of Vortex Shedding in Unsteady Cylinder Wakes
• A Supervised Machine-Learning Approach For Turboshaft Engine Dynamic Modeling Under Real Flight Conditions
• Extending the trapping theorem to provide local stability guarantees for quadratically nonlinear models
• Spatiotemporal wall pressure forecast of a rectangular cylinder with physics-aware DeepU-Fourier neural network