---
title: "Comparing model representations and fitting methods for port-Hamiltonian system identification"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05031v1"
permalink: "https://feed.astralor.com/items/itm_60c318d3f8fb3ace4bc9f018"
published: "2026-11-03T15:05:41.000Z"
score: 54
channel: "tech"
tags: ["Comparing","Hamiltonian","Port-Hamiltonian","Learning","Testing"]
---

# Comparing model representations and fitting methods for port-Hamiltonian system identification

## At a glance

Port-Hamiltonian models describe physical systems by separating stored energy, dissipation and external inputs. Learning such models from data requires a choice of representation and fitting method. We compare using neu…

## Key points

- Port-Hamiltonian models describe physical systems by separating stored energy, dissipation and external inputs.
- Learning such models from data requires a choice of representation and fitting method.
- We compare using neural networks, analytic expressions and combinations of the two for representing the different components of the port-Hamiltonian system, and compare fitting the models with gradient-based optimisatio…

## Full text

Port-Hamiltonian models describe physical systems by separating stored energy, dissipation and external inputs. Learning such models from data requires a choice of representation and fitting method. We compare using neural networks, analytic expressions and combinations of the two for representing the different components of the port-Hamiltonian system, and compare fitting the models with gradient-based optimisation or sparse regression. Testing on simulations of mechanical and electrical systems, with and without added noise, we present prediction accuracy and computational cost of the different approaches.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_60c318d3f8fb3ace4bc9f018