Physics-Informed Deep Learning for Nonlinear Friction Model of Bow-string Interaction

TL;DR

This paper explores physics-informed deep learning models, specifically PINNs and PI-DeepONets, for nonlinear friction modeling in bow-string systems, highlighting their capabilities, limitations, and potential for sound synthesis applications.

Contribution

It introduces the application of physics-informed neural networks and DeepONets to nonlinear bow-string friction modeling, analyzing their performance and limitations across different force scenarios.

Findings

PINNs effectively model the system across various bow forces.

PI-DeepONets perform well at low forces but struggle at higher forces.

Large Hessian eigenvalues indicate highly ill-conditioned optimization landscapes.

Abstract

This study investigates the use of an unsupervised, physics-informed deep learning framework to model a one-degree-of-freedom mass-spring system subjected to a nonlinear friction bow force and governed by a set of ordinary differential equations. Specifically, it examines the application of Physics-Informed Neural Networks (PINNs) and Physics-Informed Deep Operator Networks (PI-DeepONets). Our findings demonstrate that PINNs successfully address the problem across different bow force scenarios, while PI-DeepONets perform well under low bow forces but encounter difficulties at higher forces. Additionally, we analyze the Hessian eigenvalue density and visualize the loss landscape. Overall, the presence of large Hessian eigenvalues and sharp minima indicates highly ill-conditioned optimization. These results underscore the promise of physics-informed deep learning for nonlinear modelling in musical acoustics, while also revealing the limitations of relying solely on physics-based approaches to capture complex nonlinearities. We demonstrate that PI-DeepONets, with their ability to generalize across varying parameters, are well-suited for sound synthesis. Furthermore, we demonstrate that the limitations of PI-DeepONets under higher forces can be mitigated by integrating observation data within a hybrid supervised-unsupervised framework. This suggests that a hybrid supervised-unsupervised DeepONets framework could be a promising direction for future practical applications.