Guaranteed Stable Quadratic Models and their applications in SINDy and Operator Inference

by   Pawan Goyal, et al.

Scientific machine learning for learning dynamical systems is a powerful tool that combines data-driven modeling models, physics-based modeling, and empirical knowledge. It plays an essential role in an engineering design cycle and digital twinning. In this work, we primarily focus on an operator inference methodology that builds dynamical models, preferably in low-dimension, with a prior hypothesis on the model structure, often determined by known physics or given by experts. Then, for inference, we aim to learn the operators of a model by setting up an appropriate optimization problem. One of the critical properties of dynamical systems isstability. However, such a property is not guaranteed by the inferred models. In this work, we propose inference formulations to learn quadratic models, which are stable by design. Precisely, we discuss the parameterization of quadratic systems that are locally and globally stable. Moreover, for quadratic systems with no stable point yet bounded (e.g., Chaotic Lorenz model), we discuss an attractive trapping region philosophy and a parameterization of such systems. Using those parameterizations, we set up inference problems, which are then solved using a gradient-based optimization method. Furthermore, to avoid numerical derivatives and still learn continuous systems, we make use of an integration form of differential equations. We present several numerical examples, illustrating the preservation of stability and discussing its comparison with the existing state-of-the-art approach to infer operators. By means of numerical examples, we also demonstrate how proposed methods are employed to discover governing equations and energy-preserving models.


page 1

page 16

page 19


Inference of Continuous Linear Systems from Data with Guaranteed Stability

Machine-learning technologies for learning dynamical systems from data p...

Lift Learn: Physics-informed machine learning for large-scale nonlinear dynamical systems

We present Lift Learn, a physics-informed method for learning low-di...

Physics-informed regularization and structure preservation for learning stable reduced models from data with operator inference

Operator inference learns low-dimensional dynamical-system models with p...

Non-Intrusive Reduced Models based on Operator Inference for Chaotic Systems

This work explores the physics-driven machine learning technique Operato...

Generalized Kalman Smoothing: Modeling and Algorithms

State-space smoothing has found many applications in science and enginee...

Analysis and Design of Quadratic Neural Networks for Regression, Classification, and Lyapunov Control of Dynamical Systems

This paper addresses the analysis and design of quadratic neural network...

Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability

The Koopman operator has emerged as a powerful tool for the analysis of ...

Please sign up or login with your details

Forgot password? Click here to reset