DeepAI AI Chat
Log In Sign Up

Port-Hamiltonian Neural Networks with State Dependent Ports

by   Sølve Eidnes, et al.

Hybrid machine learning based on Hamiltonian formulations has recently been successfully demonstrated for simple mechanical systems. In this work, we stress-test the method on both simple mass-spring systems and more complex and realistic systems with several internal and external forces, including a system with multiple connected tanks. We quantify performance under various conditions and show that imposing different assumptions greatly affect the performance during training presenting advantages and limitations of the method. We demonstrate that port-Hamiltonian neural networks can be extended to larger dimensions with state-dependent ports. We consider learning on systems with known and unknown external forces and show how it can be used to detect deviations in a system and still provide a valid model when the deviations are removed. Finally, we propose a symmetric high-order integrator for improved training on sparse and noisy data.


page 9

page 11

page 18

page 21


Pseudo-Hamiltonian neural networks for learning partial differential equations

Pseudo-Hamiltonian neural networks (PHNN) were recently introduced for l...

Learning Hamiltonian Systems with Mono-Implicit Runge-Kutta Methods

Numerical integrators could be used to form interpolation conditions whe...

Discrete Hamilton-Jacobi theory for systems with external forces

This paper is devoted to discrete mechanical systems subject to external...

Symplectic Learning for Hamiltonian Neural Networks

Machine learning methods are widely used in the natural sciences to mode...

Pseudo-Hamiltonian system identification

Identifying the underlying dynamics of physical systems can be challengi...

Learning Trajectories of Hamiltonian Systems with Neural Networks

Modeling of conservative systems with neural networks is an area of acti...

Dissipative Hamiltonian Neural Networks: Learning Dissipative and Conservative Dynamics Separately

Understanding natural symmetries is key to making sense of our complex a...