Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Spatial-Temporal Bearing Fault Detection Using Graph Attention Networks and LSTM

Moirangthem Tiken Singh, Rabinder Kumar Prasad, Gurumayum Robert Michael, N. Hemarjit Singh, N. K. Kaphungkui

TL;DR

This research presents a unique combination of GAT and LSTM for fault detection, overcoming the limitations of traditional time series methods by capturing complex spatial-temporal dependencies.

Abstract

Purpose: This paper aims to enhance bearing fault diagnosis in industrial machinery by introducing a novel method that combines Graph Attention Network (GAT) and Long Short-Term Memory (LSTM) networks. This approach captures both spatial and temporal dependencies within sensor data, improving the accuracy of bearing fault detection under various conditions. Methodology: The proposed method converts time series sensor data into graph representations. GAT captures spatial relationships between components, while LSTM models temporal patterns. The model is validated using the Case Western Reserve University (CWRU) Bearing Dataset, which includes data under different horsepower levels and both normal and faulty conditions. Its performance is compared with methods such as K-Nearest Neighbors (KNN), Local Outlier Factor (LOF), Isolation Forest (IForest) and GNN-based method for bearing fault detection (GNNBFD). Findings: The model achieved outstanding results, with precision, recall, and F1-scores reaching 100\% across various testing conditions. It not only identifies faults accurately but also generalizes effectively across different operational scenarios, outperforming traditional methods. Originality: This research presents a unique combination of GAT and LSTM for fault detection, overcoming the limitations of traditional time series methods by capturing complex spatial-temporal dependencies. Its superior performance demonstrates significant potential for predictive maintenance in industrial applications.

Spatial-Temporal Bearing Fault Detection Using Graph Attention Networks and LSTM

TL;DR

This research presents a unique combination of GAT and LSTM for fault detection, overcoming the limitations of traditional time series methods by capturing complex spatial-temporal dependencies.

Abstract

Purpose: This paper aims to enhance bearing fault diagnosis in industrial machinery by introducing a novel method that combines Graph Attention Network (GAT) and Long Short-Term Memory (LSTM) networks. This approach captures both spatial and temporal dependencies within sensor data, improving the accuracy of bearing fault detection under various conditions. Methodology: The proposed method converts time series sensor data into graph representations. GAT captures spatial relationships between components, while LSTM models temporal patterns. The model is validated using the Case Western Reserve University (CWRU) Bearing Dataset, which includes data under different horsepower levels and both normal and faulty conditions. Its performance is compared with methods such as K-Nearest Neighbors (KNN), Local Outlier Factor (LOF), Isolation Forest (IForest) and GNN-based method for bearing fault detection (GNNBFD). Findings: The model achieved outstanding results, with precision, recall, and F1-scores reaching 100\% across various testing conditions. It not only identifies faults accurately but also generalizes effectively across different operational scenarios, outperforming traditional methods. Originality: This research presents a unique combination of GAT and LSTM for fault detection, overcoming the limitations of traditional time series methods by capturing complex spatial-temporal dependencies. Its superior performance demonstrates significant potential for predictive maintenance in industrial applications.

Paper Structure

This paper contains 12 sections, 12 equations, 9 figures, 4 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Methodology
  4. Data Processing
  5. Architecture
  6. Algorithms
  7. Experimental Results
  8. Data Description and Analysis
  9. Model Evaluation Metrics
  10. Result Analysis
  11. Discussion
  12. Conclusion

Figures (9)

  • Figure 1: Graph Construction from Time Series Data. Source: Author's own.
  • Figure 2: Visualization of Time Series Data with Windowing: The top graph displays two channels of time series data, with the initial time window (highlighted in red) applied. The lower graph illustrates how shifting the window by one step captures and converts the time series data into a graph. Source: Author's own.
  • Figure 3: Attention-Based Time Series Analysis Graph Model (ATBTSGM). Source: Author's own.
  • Figure 4: Attention layer in Attention Based Time Series Analysis Graph Model (ATBTSGM). Source: Author's own.
  • Figure 5: T-Test and Kolmogorov-Smirnov (KS) Test results for Datasets A, B, and C. Source: Author's own.
  • ...and 4 more figures

Theorems & Definitions (1)

  • Definition 3.1