Graph-Based Fault Diagnosis for Rotating Machinery: Adaptive Segmentation and Structural Feature Integration

2025-04-29

AI Summary

This paper addresses the poor robustness and limited interpretability in multi-class fault diagnosis of rotating machinery, caused by noise interference and variable operational loads. To this end, we propose a lightweight, graph-structured, interpretable diagnostic framework. Methodologically, it introduces an entropy-driven adaptive signal segmentation scheme, followed by short-time Fourier transform for time-frequency feature extraction and construction of a vibration graph that jointly encodes local dynamics and global topology. Discriminative topological features—including spectral gap and modularity—are incorporated, and classification is performed via logistic regression, eliminating the need for deep neural networks. The framework achieves high accuracy, strong noise robustness, and cross-load generalizability. It attains 99.8% and 100% classification accuracy on the CWRU and Southeast University datasets, respectively; maintains >95.4% accuracy under severe noise (SNR = 0.5); and achieves a 99.7% F1-score under load-condition transfer.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This paper proposes a novel graph-based framework for robust and interpretable multiclass fault diagnosis in rotating machinery. The method integrates entropy-optimized signal segmentation, time-frequency feature extraction, and graph-theoretic modeling to transform vibration signals into structured representations suitable for classification. Graph metrics, such as average shortest path length, modularity, and spectral gap, are computed and combined with local features to capture global and segment-level fault characteristics. The proposed method achieves high diagnostic accuracy when evaluated on two benchmark datasets, the CWRU bearing dataset (under 0-3 HP loads) and the SU gearbox and bearing datasets (under different speed-load configurations). Classification scores reach up to 99.8% accuracy on Case Western Reserve University (CWRU) and 100% accuracy on the Southeast University datasets using a logistic regression classifier. Furthermore, the model exhibits strong noise resilience, maintaining over 95.4% accuracy at high noise levels (standard deviation = 0.5), and demonstrates excellent cross-domain transferability with up to 99.7% F1-score in load-transfer scenarios. Compared to traditional techniques, this approach requires no deep learning architecture, enabling lower complexity while ensuring interpretability. The results confirm the method's scalability, reliability, and potential for real-time deployment in industrial diagnostics.

Problem

• Develops graph-based fault diagnosis for rotating machinery
• Integrates adaptive segmentation and structural features
• Ensures high accuracy and noise resilience

Innovation

• Entropy-optimized signal segmentation for adaptive processing
• Graph-theoretic modeling with structural feature integration
• Noise-resilient logistic regression for high accuracy