Uncertainty-Aware Fault Diagnosis of Rotating Compressors Using Dual-Graph Attention Networks

Rotating compressors are foundational in various industrial processes, particularly in the oil-and-gas sector, where reliable fault detection is crucial for maintaining operational continuity. While Graph Attention Network (GAT) frameworks are widely available, this study advances the state of the a...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Machines (Basel) Ročník 13; číslo 8; s. 673
Hlavní autoři:	Lee, Seungjoo, Kim, YoungSeok, Choi, Hyun-Jun, Ji, Bongjun
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Basel MDPI AG 01.08.2025
Témata:	Accuracy Attention Bayesian analysis Compressors Decision trees Deep learning digital twin simulation Digital twins Energy consumption Epistemology Fault detection Fault diagnosis Forecasting Forecasts and trends Fourier transforms Machine learning Mathematical models Misalignment Neural networks Parameter estimation Parameter identification Predictive maintenance Preventive maintenance Process controls rotating compressor fault diagnosis Rotating machinery Rotor dynamics Sensors Simulation methods Statistical inference Support vector machines Uncertainty analysis vibration-based condition monitoring Waveforms Wavelet transforms New York United States
ISSN:	2075-1702, 2075-1702
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Rotating compressors are foundational in various industrial processes, particularly in the oil-and-gas sector, where reliable fault detection is crucial for maintaining operational continuity. While Graph Attention Network (GAT) frameworks are widely available, this study advances the state of the art by introducing a Bayesian GAT method specifically tailored for vibration-based compressor fault diagnosis. The approach integrates domain-specific digital-twin simulations built with Rotordynamic software (1.3.0), and constructs dual adjacency matrices to encode both physically informed and data-driven sensor relationships. Additionally, a hybrid forecasting-and-reconstruction objective enables the model to capture short-term deviations as well as long-term waveform fidelity. Monte Carlo dropout further decomposes prediction uncertainty into aleatoric and epistemic components, providing a more robust and interpretable model. Comparative evaluations against conventional Long Short-Term Memory (LSTM)-based autoencoder and forecasting methods demonstrate that the proposed framework achieves superior fault-detection performance across multiple fault types, including misalignment, bearing failure, and unbalance. Moreover, uncertainty analyses confirm that fault severity correlates with increasing levels of both aleatoric and epistemic uncertainty, reflecting heightened noise and reduced model confidence under more severe conditions. By enhancing GAT fundamentals with a domain-tailored dual-graph strategy, specialized Bayesian inference, and digital-twin data generation, this research delivers a comprehensive and interpretable solution for compressor fault diagnosis, paving the way for more reliable and risk-aware predictive maintenance in complex rotating machinery.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	2075-1702 2075-1702
DOI:	10.3390/machines13080673