Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
arXiv:1711.05501 · doi:10.1098/rspa.2018.0335
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.
24 pages, 12 figures
References in corpus (4)
Cited by in corpus (56)
- Data-driven discovery of coordinates and governing equations
- Physics-informed learning of governing equations from scarce data
- 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
- Sparse reduced-order modeling : Sensor-based dynamics to full-state estimation
- PySINDy: A comprehensive Python package for robust sparse system identification
- KAN-ODEs: Kolmogorov-Arnold Network Ordinary Differential Equations for Learning Dynamical Systems and Hidden Physics
- Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
- A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledge
- Discovery of Physics from Data: Universal Laws and Discrepancies
- On the Structure of Time-delay Embedding in Linear Models of Non-linear Dynamical Systems
- On spike-and-slab priors for Bayesian equation discovery of nonlinear dynamical systems via sparse linear regression
- Sparse nonlinear models of chaotic electroconvection
- Data-driven modeling of the chaotic thermal convection in an annular thermosyphon
- An Online Data-Driven Method to Locate Forced Oscillation Sources from Power Plants Based on Sparse Identification of Nonlinear Dynamics (SINDy)
- Data-driven nonlinear aeroelastic models of morphing wings for control
- EKF-SINDy: Empowering the extended Kalman filter with sparse identification of nonlinear dynamics
- Quantum Computing for Fusion Energy Science Applications
- Data-driven nonlinear turbulent flow scaling with Buckingham Pi variables
- Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
- A Levenberg-Marquardt algorithm for sparse identification of dynamical systems
- Data-driven discovery and extrapolation of parameterized pattern-forming dynamics
- Detection and Prediction of Equilibrium States in Kinetic Plasma Simulations via Mode Tracking using Reduced-Order Dynamic Mode Decomposition
- Finite-Horizon, Energy-Optimal Trajectories in Unsteady Flows
- Deep learning delay coordinate dynamics for chaotic attractors from partial observable data
- Dynamical System Identification, Model Selection and Model Uncertainty Quantification by Bayesian Inference
- Control of Stochastic Quantum Dynamics by Differentiable Programming
- Deeptime: a Python library for machine learning dynamical models from time series data
- Model predictive control for robust quantum state preparation
- Data-Driven Stabilization of Periodic Orbits
- Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
- Supervised Learning Algorithms for Controlling Underactuated Dynamical Systems
- Nonlinear Model Predictive Control of a Robotic Soft Esophagus
- Virtual twins of nonlinear vibrating multiphysics microstructures: physics-based versus deep learning-based approaches
- Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning
- Latent feedback control of distributed systems in multiple scenarios through deep learning-based reduced order models
- Real-time optimal control of high-dimensional parametrized systems by deep learning-based reduced order models
- Random Feature Models for Learning Interacting Dynamical Systems
- On the sample complexity of stabilizing linear dynamical systems from data
- SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning
- Combining Federated Learning and Control: A Survey
- Koopman analysis in oscillator synchronization
- SPADE4: Sparsity and Delay Embedding based Forecasting of Epidemics
- Data-Driven Dynamics Modeling of Miniature Robotic Blimps Using Neural ODEs With Parameter Auto-Tuning
- Memory-based reduced modelling and data-based estimation of opinion spreading
- Robust discovery of partial differential equations in complex situations
- Statistical Mechanics of Dynamical System Identification
- Adaptive parameters identification for nonlinear dynamics using deep permutation invariant networks
- Discovering dynamical laws for speech gestures
- Identifying Differential Equations to predict Blood Glucose using Sparse Identification of Nonlinear Systems
- Control of dynamical systems with neural networks
- Physics-informed Split Koopman Operators for Data-efficient Soft Robotic Simulation
- Data-driven Initial Gap Identification of Piecewise-linear Systems using Sparse Regression and Universal Approximation Theorem
- Stability of a Parametrically Driven, Coupled Oscillator System: An Auxillary Function Method Approach
- Higher-Order LaSDI: Reduced Order Modeling with Multiple Time Derivatives
- Experimental Design for Missing Physics