Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying Non-Autonomous Dynamical Systems

TL;DR

This paper introduces a hybrid physics-guided recurrent neural network approach for modeling non-autonomous systems, balancing physical plausibility with data-driven accuracy improvements.

Contribution

It presents a novel multi-objective training strategy that extends physics-based models with neural networks for better system identification.

Findings

Significant accuracy improvements over purely physics-based models

Physically plausible models achieved through multi-objective training

Effective modeling of non-autonomous systems under control

Abstract

While trade-offs between modeling effort and model accuracy remain a major concern with system identification, resorting to data-driven methods often leads to a complete disregard for physical plausibility. To address this issue, we propose a physics-guided hybrid approach for modeling non-autonomous systems under control. Starting from a traditional physics-based model, this is extended by a recurrent neural network and trained using a sophisticated multi-objective strategy yielding physically plausible models. While purely data-driven methods fail to produce satisfying results, experiments conducted on real data reveal substantial accuracy improvements by our approach compared to a physics-based model.