Learning Subsystem Dynamics in Nonlinear Systems via Port-Hamiltonian Neural Networks

TL;DR

This paper introduces a novel method using port-Hamiltonian neural networks to identify and model individual subsystem dynamics within larger interconnected systems solely from input-output data, even in noisy conditions.

Contribution

The paper presents a new approach for subsystem identification using pHNNs based on system compositionality, without needing internal state access, and demonstrates its effectiveness on complex interconnected systems.

Findings

Successfully identifies subsystem dynamics from input-output data.

Handles measurement noise effectively with an output error model.

Demonstrates applicability on multi-physics interconnected systems.

Abstract

Port-Hamiltonian neural networks (pHNNs) are emerging as a powerful modeling tool that integrates physical laws with deep learning techniques. While most research has focused on modeling the entire dynamics of interconnected systems, the potential for identifying and modeling individual subsystems while operating as part of a larger system has been overlooked. This study addresses this gap by introducing a novel method for using pHNNs to identify such subsystems based solely on input-output measurements. By utilizing the inherent compositional property of the port-Hamiltonian systems, we developed an algorithm that learns the dynamics of individual subsystems, without requiring direct access to their internal states. On top of that, by choosing an output error (OE) model structure, we have been able to handle measurement noise effectively. The effectiveness of the proposed approach is demonstrated through tests on interconnected systems, including multi-physics scenarios, demonstrating its potential for identifying subsystem dynamics and facilitating their integration into new interconnected models.