Polarized Direct Cross-Attention Message Passing in GNNs for Machinery Fault Diagnosis

TL;DR

This paper introduces PolaDCA, a novel GNN framework with adaptive message passing via data-driven graph construction, significantly improving machinery fault diagnosis accuracy and robustness over traditional methods.

Contribution

PolaDCA enables dynamic, data-driven graph construction in GNNs using a direct cross-attention mechanism, addressing limitations of static graphs in fault diagnosis.

Findings

Achieves state-of-the-art accuracy on industrial datasets.

Demonstrates superior noise robustness compared to traditional GNNs.

Outperforms seven baseline methods in fault diagnosis tasks.

Abstract

The reliability of safety-critical industrial systems hinges on accurate and robust fault diagnosis in rotating machinery. Conventional graph neural networks (GNNs) for machinery fault diagnosis face limitations in modeling complex dynamic interactions due to their reliance on predefined static graph structures and homogeneous aggregation schemes. To overcome these challenges, this paper introduces polarized direct cross-attention (PolaDCA), a novel relational learning framework that enables adaptive message passing through data-driven graph construction. Our approach builds upon a direct cross-attention (DCA) mechanism that dynamically infers attention weights from three semantically distinct node features (such as individual characteristics, neighborhood consensus, and neighborhood diversity) without requiring fixed adjacency matrices. Theoretical analysis establishes PolaDCA's superior noise robustness over conventional GNNs. Extensive experiments on industrial datasets (i.e., XJTUSuprgear, CWRUBearing and Three-Phase Flow Facility datasets) demonstrate state-of-the-art diagnostic accuracy and enhanced generalization under varying noise conditions, outperforming seven competitive baseline methods. The proposed framework provides an effective solution for safety-critical industrial applications.