Learning Dissipative Neural Dynamical Systems
arXiv:2309.16032 · doi:10.1109/LCSYS.2023.3337851
Abstract
Consider an unknown nonlinear dynamical system that is known to be dissipative. The objective of this paper is to learn a neural dynamical model that approximates this system, while preserving the dissipativity property in the model. In general, imposing dissipativity constraints during neural network training is a hard problem for which no known techniques exist. In this work, we address the problem of learning a dissipative neural dynamical system model in two stages. First, we learn an unconstrained neural dynamical model that closely approximates the system dynamics. Next, we derive sufficient conditions to perturb the weights of the neural dynamical model to ensure dissipativity, followed by perturbation of the biases to retain the fit of the model to the trajectories of the nonlinear system. We show that these two perturbation problems can be solved independently to obtain a neural dynamical model that is guaranteed to be dissipative while closely approximating the nonlinear system.
arXiv comment6 pages
References in corpus (9)
- Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control
- PENLAB: A MATLAB solver for nonlinear semidefinite optimization
- Physics-Guided Deep Learning for Dynamical Systems: A Survey
- Distributed Synthesis of Local Controllers for Networked Systems with Arbitrary Interconnection Topologies
- Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning
- Convex Incremental Dissipativity Analysis of Nonlinear Systems - Extended version
- Distributed Mixed Voltage Angle and Frequency Droop Control of Microgrid Interconnections with Loss of Distribution-PMU Measurements
- Sequential Synthesis of Distributed Controllers for Cascade Interconnected Systems
- Mixed Voltage Angle and Frequency Droop Control for Transient Stability of Interconnected Microgrids with Loss of PMU Measurements