Graph Neural Networks for Dynamic Modeling of Roller Bearing

TL;DR

This paper introduces a graph neural network framework to model and predict the complex dynamics of roller bearings, enabling scalable and interpretable real-time health monitoring of rotating machinery.

Contribution

The work applies GNNs to bearing dynamics, demonstrating improved generalization and interpretability for real-time digital twin applications.

Findings

GNN accurately predicts bearing dynamics across configurations.

The approach generalizes well to unseen bearing setups.

Potential for real-time health monitoring systems.

Abstract

In the presented work, we propose to apply the framework of graph neural networks (GNNs) to predict the dynamics of a rolling element bearing. This approach offers generalizability and interpretability, having the potential for scalable use in real-time operational digital twin systems for monitoring the health state of rotating machines. By representing the bearing's components as nodes in a graph, the GNN can effectively model the complex relationships and interactions among them. We utilize a dynamic spring-mass-damper model of a bearing to generate the training data for the GNN. In this model, discrete masses represent bearing components such as rolling elements, inner raceways, and outer raceways, while a Hertzian contact model is employed to calculate the forces between these components. We evaluate the learning and generalization capabilities of the proposed GNN framework by testing different bearing configurations that deviate from the training configurations. Through this approach, we demonstrate the effectiveness of the GNN-based method in accurately predicting the dynamics of rolling element bearings, highlighting its potential for real-time health monitoring of rotating machinery.