PINO-MBD: Physics-informed Neural Operator for Solving Coupled ODEs in Multi-body Dynamics

TL;DR

PINO-MBD is a novel physics-informed neural operator designed to efficiently solve coupled ODEs in multi-body dynamics, enabling rapid solution generation for varying parameters with high accuracy.

Contribution

It introduces a new neural operator architecture with physics embedding methods tailored for coupled ODEs, addressing multiple solutions in multi-body dynamics.

Findings

Achieves state-of-the-art accuracy on vehicle-track dynamics problems.

Efficiently predicts solutions and derivatives with a single network pass.

Handles multiple solutions in coupled ODEs effectively.

Abstract

In multi-body dynamics, the motion of a complicated physical object is described as a coupled ordinary differential equation system with multiple unknown solutions. Engineers need to constantly adjust the object to meet requirements at the design stage, where a highly efficient solver is needed. The rise of machine learning-based partial differential equation solvers can meet this need. These solvers can be classified into two categories: approximating the solution function (Physics-informed neural network) and learning the solution operator (Neural operator). The recently proposed physics-informed neural operator (PINO) gains advantages from both categories by embedding physics equations into the loss function of a neural operator. Following this state-of-art concept, we propose the physics-informed neural operator for coupled ODEs in multi-body dynamics (PINO-MBD), which learns the mapping between parameter spaces and solution spaces. Once PINO-MBD is trained, only one forward pass of the network is required to obtain the solutions for a new instance with different parameters. To handle the difficulty that coupled ODEs contain multiple solutions (instead of only one in normal PDE problems), two new physics embedding methods are also proposed. The experimental results on classic vehicle-track coupled dynamics problem show state-of-art performance not only on solutions but also the first and second derivatives of solutions.