Few-shot fault diagnosis based on multi-scale graph convolution filtering for industry

TL;DR

This paper proposes a novel Multi-Scale Graph Convolution Filtering method to improve fault diagnosis in industrial equipment under limited data conditions, effectively capturing intrinsic fault features across domains.

Contribution

It introduces MSGCF, an enhanced GNN framework with local and global information fusion, addressing over-smoothing and overfitting in few-shot fault diagnosis.

Findings

MSGCF outperforms existing methods in accuracy on PU dataset.

The approach effectively mitigates over-smoothing in deep GNNs.

Enhanced fault feature extraction under limited data scenarios.

Abstract

Industrial equipment fault diagnosis often encounter challenges such as the scarcity of fault data, complex operating conditions, and varied types of failures. Signal analysis, data statistical learning, and conventional deep learning techniques face constraints under these conditions due to their substantial data requirements and the necessity for transfer learning to accommodate new failure modes. To effectively leverage information and extract the intrinsic characteristics of faults across different domains under limited sample conditions, this paper introduces a fault diagnosis approach employing Multi-Scale Graph Convolution Filtering (MSGCF). MSGCF enhances the traditional Graph Neural Network (GNN) framework by integrating both local and global information fusion modules within the graph convolution filter block. This advancement effectively mitigates the over-smoothing issue associated with excessive layering of graph convolutional layers while preserving a broad receptive field. It also reduces the risk of overfitting in few-shot diagnosis, thereby augmenting the model's representational capacity. Experiments on the University of Paderborn bearing dataset (PU) demonstrate that the MSGCF method proposed herein surpasses alternative approaches in accuracy, thereby offering valuable insights for industrial fault diagnosis in few-shot learning scenarios.