Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
From MaRDI portal
Publication:5243602
Abstract: The data-driven discovery of dynamics via machine learning is currently pushing the frontiers of modeling and control efforts, and it provides a tremendous opportunity to extend the reach of model predictive control. However, many leading methods in machine learning, such as neural networks, require large volumes of training data, may not be interpretable, do not easily include known constraints and symmetries, and often do not generalize beyond the attractor where models are trained. These factors limit the use of these techniques for the online identification of a model in the low-data limit, for example following an abrupt change to the system dynamics. In this work, we extend the recent sparse identification of nonlinear dynamics (SINDY) modeling procedure to include the effects of actuation and demonstrate the ability of these models to enhance the performance of model predictive control (MPC), based on limited, noisy data. SINDY models are parsimonious, identifying the fewest terms in the model needed to explain the data, making them interpretable, generalizable, and reducing the burden of training data. We show that the resulting SINDY-MPC framework has higher performance, requires significantly less data, and is more computationally efficient and robust to noise than neural network models, making it viable for online training and execution in response to rapid changes to the system. SINDY-MPC also shows improved performance over linear data-driven models, although linear models may provide a stopgap until enough data is available for SINDY. SINDY-MPC is demonstrated on a variety of dynamical systems with different challenges, including the chaotic Lorenz system, a simple model for flight control of an F8 aircraft, and an HIV model incorporating drug treatment.
Recommendations
- SINDy-PI: a robust algorithm for parallel implicit sparse identification of nonlinear dynamics
- Data-driven sparse identification of nonlinear dynamical systems using linear multistep methods
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
- Weak SINDy: Galerkin-based data-driven model selection
Cites work
- scientific article; zbMATH DE number 6678650 (Why is no real title available?)
- scientific article; zbMATH DE number 3810550 (Why is no real title available?)
- scientific article; zbMATH DE number 829791 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 1418964 (Why is no real title available?)
- A Sparse Bayesian Approach to the Identification of Nonlinear State-Space Systems
- A data-driven approximation of the koopman operator: extending dynamic mode decomposition
- A fast nonlinear model identification method
- A model predictive control based scheduling method for HIV therapy
- An eigensystem realization algorithm for modal parameter identification and model reduction
- Analytical Foundations of Volterra Series
- Applied Koopmanism
- Automated reverse engineering of nonlinear dynamical systems
- Compressive sensing and low-rank libraries for classification of bifurcation regimes in nonlinear dynamical systems
- Constrained sparse Galerkin regression
- Design of nonlinear automatic flight control systems
- Deterministic Nonperiodic Flow
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Dynamic mode decomposition of numerical and experimental data
- Dynamic mode decomposition with control
- Fitting autoregressive models for prediction
- Global optimal feedback control for general nonlinear systems with nonquadratic performance criteria
- Identifiability of affine linear parameter-varying models
- Just relax: convex programming methods for identifying sparse signals in noise
- Kernel methods in system identification, machine learning and function estimation: a survey
- Learning partial differential equations via data discovery and sparse optimization
- Mathematical Analysis of HIV-1 Dynamics in Vivo
- Model predictive control: Theory and practice - a survey
- Model predictive control: recent developments and future promise
- Model selection for dynamical systems via sparse regression and information criteria
- Multilayer feedforward networks are universal approximators
- Nonlinear system identification. NARMAX methods in the time, frequency, and spatio-temporal domains
- Nonlinear total variation based noise removal algorithms
- Numerical differentiation of noisy, nonsmooth data
- On dynamic mode decomposition: theory and applications
- Sparse identification of posynomial models
- Sparse reduced-order modelling: sensor-based dynamics to full-state estimation
- Spectral analysis of nonlinear flows
- Spectral properties of dynamical systems, model reduction and decompositions
- System Identification Via Sparse Multiple Kernel-Based Regularization Using Sequential Convex Optimization Techniques
- System identification in the presence of outliers and random noises: a compressed sensing approach
- The influence of diseases on Lotka-Volterra systems
- Turbulence, coherent structures, dynamical systems and symmetry.
- Volterra series and geometric control theory
Cited in
(69)- Learning-based model predictive current control for synchronous machines: an LSTM approach
- Learning equations from biological data with limited time samples
- The \(l_1\)-based sparsification of energy interactions in unsteady lid-driven cavity flow
- Some applications of compressed sensing in computational mechanics: model order reduction, manifold learning, data-driven applications and nonlinear dimensionality reduction
- Sparse reduced-order modelling: sensor-based dynamics to full-state estimation
- On the convergence of the SINDy algorithm
- Hybrid analysis and modeling, eclecticism, and multifidelity computing toward digital twin revolution
- On the differential realization of a second-order bilinear system in a Hilbert space
- Recovery guarantees for polynomial coefficients from weakly dependent data with outliers
- Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
- Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning
- Proximal policy optimization‐based controller for chaotic systems
- Probabilistic forecast of nonlinear dynamical systems with uncertainty quantification
- On the universal transformation of data-driven models to control systems
- Phase-based control of periodic flows
- Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
- Supervised learning algorithms for controlling underactuated dynamical systems
- Robust Identification of Differential Equations by Numerical Techniques from a Single Set of Noisy Observation
- Deep reinforcement learning for adaptive mesh refinement
- Detection and prediction of equilibrium states in kinetic plasma simulations via mode tracking using reduced-order dynamic mode decomposition
- Data‐enabled predictive control for quadcopters
- Koopman Linear Quadratic Regulator Using Complex Eigenfunctions for Nonlinear Dynamical Systems
- Group projected subspace pursuit for identification of variable coefficient differential equations (GP-IDENT)
- Memory-based reduced modelling and data-based estimation of opinion spreading
- Learning sparse nonlinear dynamics via mixed-integer optimization
- Neural network-based parametric system identification: a review
- Model selection via reweighted partial sparse recovery
- Conditional space-time POD extensions for stability and prediction analysis
- Local parameter identification with neural ordinary differential equations
- Data-driven identification of parametric partial differential equations
- Deep learning discrete calculus (DLDC): a family of discrete numerical methods by universal approximation for STEM education to frontier research
- Modern Koopman theory for dynamical systems
- Thermodynamically consistent physics-informed neural networks for hyperbolic systems
- On the structure of time-delay embedding in linear models of non-linear dynamical systems
- SubTSBR to tackle high noise and outliers for data-driven discovery of differential equations
- Poincaré maps for multiscale physics discovery and nonlinear Floquet theory
- From the POD-Galerkin method to sparse manifold models
- On Bilinear Time-Domain Identification and Reduction in the Loewner Framework
- Data-driven approximation of the Koopman generator: model reduction, system identification, and control
- Discovery of Nonlinear Multiscale Systems: Sampling Strategies and Embeddings
- A Bayesian framework for learning governing partial differential equation from data
- A framework based on symbolic regression coupled with eXtended physics-informed neural networks for gray-box learning of equations of motion from data
- Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutions
- Deep learning‐based reduced order models for the real‐time simulation of the nonlinear dynamics of microstructures
- DL-PDE: Deep-Learning Based Data-Driven Discovery of Partial Differential Equations from Discrete and Noisy Data
- Discovering stochastic partial differential equations from limited data using variational Bayes inference
- Kernel functions embed into the autoencoder to identify the sparse models of nonlinear dynamics
- Sparse identification of dynamical systems by reweighted \(l_1\)-regularized least absolute deviation regression
- SINDy-PI: a robust algorithm for parallel implicit sparse identification of nonlinear dynamics
- Simultaneous Identification and Denoising of Dynamical Systems
- IDENT: identifying differential equations with numerical time evolution
- On higher order drift and diffusion estimates for stochastic SINDy
- Distributed sparse identification for stochastic dynamic systems under cooperative non-persistent excitation condition
- SPADE4: sparsity and delay embedding based forecasting of epidemics
- On the sample complexity of stabilizing linear dynamical systems from data
- Deep learning discovery of macroscopic governing equations for viscous gravity currents from microscopic simulation data
- EKF-SINDy: empowering the extended Kalman filter with sparse identification of nonlinear dynamics
- Data-driven transient lift attenuation for extreme vortex gust-airfoil interactions
- Reinforcement learning based MPC with neural dynamical models
- Dictionary-based model reduction for state estimation
- Dynamical system identification, model selection, and model uncertainty quantification by Bayesian inference
- Online identification and control of PDEs via reinforcement learning methods
- Structured model selection via ℓ1−ℓ2 optimization
- Self-tuning model predictive control for wake flows
- A thermodynamics-informed neural network for elastoplastic constitutive modeling of granular materials
- KAN-ODEs: Kolmogorov-Arnold network ordinary differential equations for learning dynamical systems and hidden physics
- A stochastic gradient-based two-step sparse identification algorithm for multivariate ARX systems
- Forecasting and predicting stochastic agent-based model data with biologically-informed neural networks
- Model predictive complex system control from observational and interventional data
This page was built for publication: Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5243602)
