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...

Full description

Saved in:

Bibliographic Details
Published in:	Machines (Basel) Vol. 13; no. 8; p. 673
Main Authors:	Lee, Seungjoo, Kim, YoungSeok, Choi, Hyun-Jun, Ji, Bongjun
Format:	Journal Article
Language:	English
Published:	Basel MDPI AG 01.08.2025
Subjects:	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
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	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.
AbstractList	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.
Audience	Academic
Author	Choi, Hyun-Jun Ji, Bongjun Kim, YoungSeok Lee, Seungjoo
Author_xml	– sequence: 1 givenname: Seungjoo orcidid: 0009-0002-7284-3800 surname: Lee fullname: Lee, Seungjoo – sequence: 2 givenname: YoungSeok surname: Kim fullname: Kim, YoungSeok – sequence: 3 givenname: Hyun-Jun orcidid: 0000-0003-3647-0621 surname: Choi fullname: Choi, Hyun-Jun – sequence: 4 givenname: Bongjun surname: Ji fullname: Ji, Bongjun
BookMark	eNpdUU1rWzEQFCWFJmnuPT7o-SXSk_SkdzTOJ4QEQn0sYvXlyLUlV5IJ-feR41BKdg-7DLPDsHOCjmKKDqEfBJ9TOuGLDZjnEF0hFEs8CvoFHQ9Y8J4IPBz9t39DZ6WscKuJUMnkMfq9iMblCiHW1372Atl117Bb1-4ywDKmEkqXfPeUKtQQl908bbbZlZJy6RZlj1zuYN3fZNg-d7NaXawhxe7B1ZeU_5Tv6KuHdXFnH_MULa6vfs1v-_vHm7v57L43VNDaA9OMjAyc4NpLTMUI1nDNhOYgLPFy1IYINjjivQTBABtHLGFGW64xHukpujvo2gQrtc1hA_lVJQjqHUh5qSDXYNZOsWkYpRmxZINlQnrQngOwaRqt9FbrpvXzoLXN6e_OlapWaZdjs6_owBhmfOJDY50fWEtooiH6VDOY1tZtgmnp-NDwmeT7Nw8CtwN8ODA5lZKd_2eTYLUPUX0Okb4BAOqTgQ
Cites_doi	10.1016/j.jfranklin.2012.05.004 10.1109/ICDM50108.2020.00093 10.1016/j.cosrev.2019.08.002 10.1016/j.measurement.2020.108774 10.1109/TCYB.2023.3256080 10.1115/IMECE1998-1020 10.3390/pr8070790 10.1109/ICDSAAI59313.2023.10452465 10.1016/j.ejor.2013.07.040 10.1109/TIE.2017.2774777 10.1016/S0967-0661(97)00049-X 10.1109/TEC.2005.847955 10.11591/ijpeds.v12.i2.pp1205-1215 10.1016/j.arcontrol.2004.12.002 10.1109/NAPS58826.2023.10318740 10.1109/ICMECH.2006.252551 10.1115/1.4000147 10.1205/cerd.82.10.1337.46744 10.1109/TEC.2016.2558183 10.1088/1361-6501/ac56f0 10.3390/s21082708 10.1016/j.eswa.2023.122182 10.1016/S1665-6423(15)30014-6 10.3390/math9182336 10.1155/2021/9927151 10.1016/j.rser.2017.08.007 10.1109/TPEL.2009.2038268 10.1109/59.962408 10.1016/j.jsv.2018.04.036 10.1111/j.1539-6924.1993.tb01071.x 10.1088/1748-9326/ac55b6 10.1016/j.measurement.2012.10.026 10.1007/s10462-021-09993-z 10.1016/j.ijhydene.2022.03.208 10.1115/GT2012-68005 10.1006/jsvi.1995.0588 10.1109/IEA.2018.8387124 10.1109/TASE.2020.3035620 10.1016/j.jsv.2024.118562 10.1016/j.jsv.2012.05.006 10.1016/j.cej.2025.165121 10.1016/j.rser.2022.112701 10.1016/j.ijrefrig.2009.08.006 10.1109/MED.2008.4602224 10.1109/TIE.2012.2189534
ContentType	Journal Article
Copyright	COPYRIGHT 2025 MDPI AG 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: COPYRIGHT 2025 MDPI AG – notice: 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	AAYXX CITATION 7TB 8FD 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU COVID DWQXO FR3 HCIFZ L6V M7S PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS PTHSS DOA
DOI	10.3390/machines13080673
DatabaseName	CrossRef Mechanical & Transportation Engineering Abstracts Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials - QC ProQuest Central ProQuest Technology Collection ProQuest One Coronavirus Research Database ProQuest Central Korea Engineering Research Database SciTech Premium Collection ProQuest Engineering Collection Engineering Database ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Publicly Available Content Database Technology Collection Technology Research Database ProQuest One Academic Middle East (New) Mechanical & Transportation Engineering Abstracts ProQuest Central Essentials ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest Engineering Collection ProQuest Central Korea ProQuest Central (New) Engineering Collection Engineering Database ProQuest One Academic Eastern Edition Coronavirus Research Database ProQuest Technology Collection ProQuest SciTech Collection ProQuest One Academic UKI Edition Materials Science & Engineering Collection Engineering Research Database ProQuest One Academic ProQuest One Academic (New)
DatabaseTitleList	CrossRef Publicly Available Content Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2075-1702
ExternalDocumentID	oai_doaj_org_article_49268c60842d478fabf5aa4996d8fdbb A853848270 10_3390_machines13080673
GeographicLocations	New York United States
GeographicLocations_xml	– name: New York – name: United States
GroupedDBID	5VS 8FE 8FG AADQD AAFWJ AAYXX ABJCF ACIWK ADBBV ADMLS AFFHD AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS BCNDV BENPR BGLVJ CCPQU CITATION GROUPED_DOAJ HCIFZ IAO ITC KQ8 L6V M7S MODMG M~E OK1 PHGZM PHGZT PIMPY PQGLB PROAC PTHSS RNS 7TB 8FD ABUWG AZQEC COVID DWQXO FR3 PKEHL PQEST PQQKQ PQUKI PRINS
ID	FETCH-LOGICAL-c373t-a4b4164ae75bf80376adc5b47b5a7d1f86bc1742e1ff8a74a0ce1d14cbd5b0063
IEDL.DBID	PIMPY
ISICitedReferencesCount	1
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001558054100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2075-1702
IngestDate	Fri Oct 03 12:35:14 EDT 2025 Sat Nov 01 15:06:34 EDT 2025 Tue Nov 04 18:12:19 EST 2025 Sat Nov 29 07:12:03 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	8
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c373t-a4b4164ae75bf80376adc5b47b5a7d1f86bc1742e1ff8a74a0ce1d14cbd5b0063
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0002-7284-3800 0000-0003-3647-0621
OpenAccessLink	https://www.proquest.com/publiccontent/docview/3244045952?pq-origsite=%requestingapplication%
PQID	3244045952
PQPubID	2032370
ParticipantIDs	doaj_primary_oai_doaj_org_article_49268c60842d478fabf5aa4996d8fdbb proquest_journals_3244045952 gale_infotracacademiconefile_A853848270 crossref_primary_10_3390_machines13080673
PublicationCentury	2000
PublicationDate	2025-08-01
PublicationDateYYYYMMDD	2025-08-01
PublicationDate_xml	– month: 08 year: 2025 text: 2025-08-01 day: 01
PublicationDecade	2020
PublicationPlace	Basel
PublicationPlace_xml	– name: Basel
PublicationTitle	Machines (Basel)
PublicationYear	2025
Publisher	MDPI AG
Publisher_xml	– name: MDPI AG
References	Cheng (ref_45) 2012; 46 (ref_24) 1993; 13 Hu (ref_61) 2022; 33 ref_14 Kumar (ref_29) 2021; 2021 Sree (ref_53) 2014; 5 ref_56 ref_55 ref_10 ref_52 ref_51 Li (ref_32) 2023; 54 Stevens (ref_12) 2018; 71 Matania (ref_19) 2024; 590 Chen (ref_38) 1995; 188 ref_18 Capisani (ref_40) 2012; 59 Isermann (ref_42) 2005; 29 Han (ref_11) 2004; 82 Yan (ref_60) 2020; 19 Payne (ref_26) 2010; 77 Widell (ref_13) 2009; 33 Huang (ref_59) 2022; 55 Wen (ref_57) 2017; 65 Jackson (ref_9) 2022; 17 ref_25 Bazdar (ref_4) 2022; 167 ref_20 ref_63 ref_62 Soother (ref_30) 2021; 69 Zhang (ref_58) 2021; 171 ref_28 ref_27 (ref_48) 2015; 13 Hmida (ref_39) 2012; 349 ref_36 Zhu (ref_34) 2025; 519 ref_35 Kurz (ref_16) 2010; 132 Patton (ref_43) 1997; 5 Haddad (ref_47) 2016; 31 Nandi (ref_21) 2005; 20 ref_37 Hanga (ref_22) 2019; 34 Endrenyi (ref_23) 2001; 16 Mack (ref_50) 2018; 66 Silva (ref_17) 2013; 232 ref_46 ref_44 Dawoud (ref_8) 2017; 82 ref_1 Haugland (ref_15) 2011; 21 ref_2 Wu (ref_33) 2024; 238 Salmasi (ref_41) 2010; 25 Arsad (ref_3) 2022; 47 Priyanka (ref_6) 2020; 6 Wang (ref_49) 2012; 331 ref_5 Jyothi (ref_31) 2021; 12 ref_7 Li (ref_54) 2018; 428
References_xml	– volume: 349 start-page: 2369 year: 2012 ident: ref_39 article-title: Three-stage Kalman filter for state and fault estimation of linear stochastic systems with unknown inputs publication-title: J. Frankl. Inst. doi: 10.1016/j.jfranklin.2012.05.004 – ident: ref_62 doi: 10.1109/ICDM50108.2020.00093 – volume: 34 start-page: 100191 year: 2019 ident: ref_22 article-title: Machine learning and multi-agent systems in oil and gas industry applications: A survey publication-title: Comput. Sci. Rev. doi: 10.1016/j.cosrev.2019.08.002 – volume: 171 start-page: 108774 year: 2021 ident: ref_58 article-title: Fault diagnosis of rotating machinery based on recurrent neural networks publication-title: Measurement doi: 10.1016/j.measurement.2020.108774 – volume: 54 start-page: 506 year: 2023 ident: ref_32 article-title: Filter-informed spectral graph wavelet networks for multiscale feature extraction and intelligent fault diagnosis publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2023.3256080 – ident: ref_37 doi: 10.1115/IMECE1998-1020 – ident: ref_28 doi: 10.3390/pr8070790 – ident: ref_56 doi: 10.1109/ICDSAAI59313.2023.10452465 – volume: 232 start-page: 630 year: 2013 ident: ref_17 article-title: A computational analysis of multidimensional piecewise-linear models with applications to oil production optimization publication-title: Eur. J. Oper. Res. doi: 10.1016/j.ejor.2013.07.040 – ident: ref_1 – ident: ref_35 – volume: 21 start-page: 524 year: 2011 ident: ref_15 article-title: Optimization methods for pipeline transportation of natural gas with variable specific gravity and compressibility publication-title: TOP – volume: 69 start-page: 393 year: 2021 ident: ref_30 article-title: A Novel Method Based on UNET for Bearing Fault Diagnosis publication-title: Comput. Mater. Contin. – volume: 65 start-page: 5990 year: 2017 ident: ref_57 article-title: A new convolutional neural network-based data-driven fault diagnosis method publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2017.2774777 – volume: 5 start-page: 671 year: 1997 ident: ref_43 article-title: Observer-based fault detection and isolation: Robustness and applications publication-title: Control Eng. Pract. doi: 10.1016/S0967-0661(97)00049-X – volume: 20 start-page: 719 year: 2005 ident: ref_21 article-title: Condition monitoring and fault diagnosis of electrical motors—A review publication-title: IEEE Trans. Energy Convers. doi: 10.1109/TEC.2005.847955 – volume: 12 start-page: 1205 year: 2021 ident: ref_31 article-title: Machine learning based multi class fault diagnosis tool for voltage source inverter driven induction motor publication-title: Int. J. Power Electron. Drive Syst. doi: 10.11591/ijpeds.v12.i2.pp1205-1215 – ident: ref_27 – volume: 29 start-page: 71 year: 2005 ident: ref_42 article-title: Model-based fault-detection and diagnosis–status and applications publication-title: Annu. Rev. Control doi: 10.1016/j.arcontrol.2004.12.002 – ident: ref_55 doi: 10.1109/NAPS58826.2023.10318740 – ident: ref_44 doi: 10.1109/ICMECH.2006.252551 – volume: 132 start-page: 062402 year: 2010 ident: ref_16 article-title: Assessment of Compressors in Gas Storage Applications publication-title: J. Eng. Gas Turbines Power doi: 10.1115/1.4000147 – volume: 77 start-page: 18 year: 2010 ident: ref_26 article-title: Offshore operations and maintenance: A growing market publication-title: Pet. Econ. – volume: 82 start-page: 1337 year: 2004 ident: ref_11 article-title: Optimization of the air-and gas-supply network of a chemical plant publication-title: Chem. Eng. Res. Des. doi: 10.1205/cerd.82.10.1337.46744 – volume: 31 start-page: 924 year: 2016 ident: ref_47 article-title: On the accuracy of fault detection and separation in permanent magnet synchronous machines using MCSA/MVSA and LDA publication-title: IEEE Trans. Energy Convers. doi: 10.1109/TEC.2016.2558183 – volume: 33 start-page: 065013 year: 2022 ident: ref_61 article-title: A deep feature extraction approach for bearing fault diagnosis based on multi-scale convolutional autoencoder and generative adversarial networks publication-title: Meas. Sci. Technol. doi: 10.1088/1361-6501/ac56f0 – ident: ref_10 doi: 10.3390/s21082708 – volume: 238 start-page: 122182 year: 2024 ident: ref_33 article-title: Deep dual graph attention auto-encoder for community detection publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2023.122182 – ident: ref_7 – volume: 13 start-page: 160 year: 2015 ident: ref_48 article-title: Fused empirical mode decomposition and MUSIC algorithms for detecting multiple combined faults in induction motors publication-title: J. Appl. Res. Technol. doi: 10.1016/S1665-6423(15)30014-6 – ident: ref_20 doi: 10.3390/math9182336 – volume: 66 start-page: 291 year: 2018 ident: ref_50 article-title: Combining expert knowledge and unsupervised learning techniques for anomaly detection in aircraft flight data publication-title: At-Autom. – volume: 2021 start-page: 9927151 year: 2021 ident: ref_29 article-title: The Importance of Feature Processing in Deep-Learning-Based Condition Monitoring of Motors publication-title: Math. Probl. Eng. doi: 10.1155/2021/9927151 – volume: 82 start-page: 2039 year: 2017 ident: ref_8 article-title: Hybrid renewable microgrid optimization techniques: A review publication-title: Renew. Sustain. Energy Rev. doi: 10.1016/j.rser.2017.08.007 – volume: 25 start-page: 1310 year: 2010 ident: ref_41 article-title: An adaptive flux observer with online estimation of DC-link voltage and rotor resistance for VSI-based induction motors publication-title: IEEE Trans. Power Electron. doi: 10.1109/TPEL.2009.2038268 – volume: 5 start-page: 124 year: 2014 ident: ref_53 article-title: Anomaly detection using principal component analysis publication-title: J. Computer. Sci. Technol. – ident: ref_14 – volume: 16 start-page: 638 year: 2001 ident: ref_23 article-title: The present status of maintenance strategies and the impact of maintenance on reliability publication-title: IEEE Trans. Power Syst. doi: 10.1109/59.962408 – ident: ref_63 – volume: 428 start-page: 72 year: 2018 ident: ref_54 article-title: Early fault diagnosis of rolling bearings based on hierarchical symbol dynamic entropy and binary tree support vector machine publication-title: J. Sound Vib. doi: 10.1016/j.jsv.2018.04.036 – volume: 6 start-page: 77 year: 2020 ident: ref_6 article-title: Review analysis on cloud computing based smart grid technology in the oil pipeline sensor network system publication-title: Pet. Res. – ident: ref_18 – volume: 71 start-page: 1 year: 2018 ident: ref_12 article-title: The role of oil and gas in the economic development of the global economy publication-title: Extr. Ind. Soc. – volume: 13 start-page: 215 year: 1993 ident: ref_24 article-title: Learning from the Piper Alpha accident: A postmortem analysis of technical and organizational factors publication-title: Risk Anal. doi: 10.1111/j.1539-6924.1993.tb01071.x – volume: 17 start-page: 031001 year: 2022 ident: ref_9 article-title: Global fossil carbon emissions rebound near pre-COVID-19 levels publication-title: Environ. Res. Lett. doi: 10.1088/1748-9326/ac55b6 – volume: 46 start-page: 1137 year: 2012 ident: ref_45 article-title: Gear fault identification based on Hilbert–Huang transform and SOM neural network publication-title: Measurement doi: 10.1016/j.measurement.2012.10.026 – ident: ref_25 – volume: 55 start-page: 1289 year: 2022 ident: ref_59 article-title: A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems publication-title: Artif. Intell. Rev. doi: 10.1007/s10462-021-09993-z – volume: 47 start-page: 17285 year: 2022 ident: ref_3 article-title: Hydrogen energy storage intergrated hybrid renewable energy systems: A review analysis for future research directions publication-title: Int. J. Hydrog. Energy doi: 10.1016/j.ijhydene.2022.03.208 – ident: ref_5 doi: 10.1115/GT2012-68005 – volume: 188 start-page: 227 year: 1995 ident: ref_38 article-title: Fault features of large rotating machinery and diagnosis using sensor fusion publication-title: J. Sound Vib. doi: 10.1006/jsvi.1995.0588 – ident: ref_51 doi: 10.1109/IEA.2018.8387124 – ident: ref_2 – ident: ref_46 – volume: 19 start-page: 387 year: 2020 ident: ref_60 article-title: Chiller fault diagnosis based on VAE-enabled generative adversarial networks publication-title: IEEE Trans. Autom. Sci. Eng. doi: 10.1109/TASE.2020.3035620 – volume: 590 start-page: 118562 year: 2024 ident: ref_19 article-title: A systematic literature review of deep learning for vibration-based fault diagnosis of critical rotating machinery: Limitations and challenges publication-title: J. Sound Vib. doi: 10.1016/j.jsv.2024.118562 – volume: 331 start-page: 4379 year: 2012 ident: ref_49 article-title: Clustering diagnosis of rolling element bearing fault based on integrated Autoregressive/Autoregressive Conditional Heteroscedasticity model publication-title: J. Sound Vib. doi: 10.1016/j.jsv.2012.05.006 – volume: 519 start-page: 165121 year: 2025 ident: ref_34 article-title: Hybrid triboelectric-piezoelectric nanogenerator assisted intelligent condition monitoring for aero-engine pipeline system publication-title: Chem. Eng. J. doi: 10.1016/j.cej.2025.165121 – volume: 167 start-page: 112701 year: 2022 ident: ref_4 article-title: Compressed air energy storage in integrated energy systems: A review publication-title: Renew. Sustain. Energy Rev. doi: 10.1016/j.rser.2022.112701 – ident: ref_36 – volume: 33 start-page: 88 year: 2009 ident: ref_13 article-title: Reducing power consumption in multi-compressor refrigeration systems publication-title: Int. J. Refrig. doi: 10.1016/j.ijrefrig.2009.08.006 – ident: ref_52 doi: 10.1109/MED.2008.4602224 – volume: 59 start-page: 3979 year: 2012 ident: ref_40 article-title: Manipulator fault diagnosis via higher order sliding-mode observers publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2012.2189534
SSID	ssj0000913848
Score	2.3060782
Snippet	Rotating compressors are foundational in various industrial processes, particularly in the oil-and-gas sector, where reliable fault detection is crucial for...
SourceID	doaj proquest gale crossref
SourceType	Open Website Aggregation Database Index Database
StartPage	673
SubjectTerms	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
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LaxRBEG4keDCH4CMhG1fpgyA5NJlHz3b1cTWuHmQRMZBLaKpfIZDshplZxX9vV89ENgHJxevMHIr6uqqrqG--YuwdpoOr0DlhZVRCqqiFlioIrdNpAQcRbBZx_aqWSzg_19-2Vn0RJ2yQBx4cd0KCduBmBcjKSwURbWwQU50-8xC9tZR9C6W3mqmcg3VZg4RhLlmnvv7kJnMTQ5dyNtBylnv3UJbr_1dSzjfN4jnbG0tEPh9Me8GehNVLtrslHPiKXZwlrPIsv_8t5r-wDXyBm-uenw7MuauOryP_vqY5--qSU9BTW71uO545Avx0g9fiM4lV83nfD5RHvhwo4d0-O1t8-vHxixgXJQhXq7oXKG2qqyQG1dgIRcoZ6F1jpbINKl9GmFmXOo8qlDECKomFC6UvpbO-obCrD9jOar0Kh4wDBO_RNumdlrayCNoGVFFWEQNaNWHHd24zt4Mehkl9BLnYPHTxhH0gv_79jpSs84OErxnxNY_hO2HvCRVD8da36HD8bSCZS8pVZp7qDSAt02LCpnfAmTEQO5PqRZmqVt1UR__DmtfsWUULgDMDcMp2-nYT3rCn7md_1bVv8xn8A7WV5SA priority: 102 providerName: Directory of Open Access Journals
Title	Uncertainty-Aware Fault Diagnosis of Rotating Compressors Using Dual-Graph Attention Networks
URI	https://www.proquest.com/docview/3244045952 https://doaj.org/article/49268c60842d478fabf5aa4996d8fdbb
Volume	13
WOSCitedRecordID	wos001558054100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2075-1702 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913848 issn: 2075-1702 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2075-1702 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913848 issn: 2075-1702 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Engineering Database customDbUrl: eissn: 2075-1702 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913848 issn: 2075-1702 databaseCode: M7S dateStart: 20130301 isFulltext: true titleUrlDefault: http://search.proquest.com providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2075-1702 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913848 issn: 2075-1702 databaseCode: BENPR dateStart: 20130301 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2075-1702 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913848 issn: 2075-1702 databaseCode: PIMPY dateStart: 20130301 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LbxMxEB5BwgEOlFdFaBv5gIQ4WNlsvLH3hFKaABJEUaFSOaDV-FVVKtmyuwFx6W_H492UhwQnLntY-2BpZj7P2J-_AXiKwXElGsO18JIL6XOeC-l4ngdvUUZ5paOI61u5XKrT03zVPY-uO1rlFhMjULdqz8TbDiA8sqWhE_NRSANESEbyLH1x-YVTDym6a-0aatyEPglvJT3or968W328PnMhDUwlVHtbOQnV_uhzZCy6OiC5opYtv-1OUcT_b1Ad95_Fzv9d-T242-WhbNY6zn244dYP4M4v6oQP4dNJcIhIGGi-89k3rBxb4OaiYUctPe-8ZqVnxyVd5q_PGCEL1e5lVbNIRGBHG7zgr0gRm82apuVVsmXLO68fwcli_uHla951Y-BmIicNR6FD8ibQyUx7lQRgQmsyLaTOUNqxV1NtQnmTurH3CqXAxLixHQujbUaxPdmF3rpcu8fAlHLWos7CWC50qlHl2qH0IvXoUMsBPN9aobhsRTeKUKyQxYo_LTaAQzLT9TySy44_yuqs6KKvIFVEZaaJEqkVUnnUPkMMxd7UKm-1HsAzMnJBQd1UaLB7mxCWS_JYxSwkNYoEU5MB7G-NXHTRXhc_bfrk38N7cDul_sGRQLgPvabauAO4Zb4253U1hP7hfLk6HsZzgSGxUN_T92o-7Bz5B2cBBDU
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3LbtQwFL0qUyRgwRt1oIAXIMTCaiZxxs4CoSnToVWHqKpaqRtkrl9VpXZSkgxVf4pvxM6jPCTYdcE2jqIkPr4vH58L8Ao9cDlqTRVznDLuMpoxbmmWebQILZxQjYjrnOe5ODrK9lbge38WJtAqe5vYGGpT6FAj3_COn_nwI0vj9-dfaegaFXZX-xYaLSx27eWFT9mqdztTP7-v43i2dfBhm3ZdBahOeFJTZMoHIQwtT5UTkV9gaHSqGFcpcjNyYqy0D9NjO3JOIGcYaTsyI6aVSQNGE__cG7DKEjZOB7C6uZXv7V9VdYLKpmCi3Q9NkizaOGs4kbbyvkKEpjC_-b-mTcDfnEHj4Wb3_rd_cx_udrE0mbTgfwArdvEQ7vyisPgIPh96UDekh_qSTi6wtGSGy9OaTFuK4UlFCkf2i0BIWByTYB1D_aEoK9KQKch0iaf0Y1D1JpO6brmhJG-589VjOLyW73sCg0WxsGtAhLDGoEr9WMZUrFBkyiJ3LHZoUfEhvO3nWZ63wiHSJ1wBE_JPTAxhMwDh6r4g-d1cKMpj2VkQGZQdhR5HgsWGceFQuRTRJ6xjI5xRaghvAoxkMEx1iRq78xX-dYPEl5z4wEwE0ddoCOs9jGRnsSr5E0NP_z38Em5tH3yay_lOvvsMbsehH3JDiFyHQV0u7XO4qb_VJ1X5olscBL5cN-Z-ADDVUnc
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3LbtQwFL0qU4RgwRt1oIAXIMTCmkzijJ0FQlOmA1WraFRRqRvkXr-qSmXSJhmq_hpfh51HeUiw64JtHEVJfO7LPj4X4BV64HLUmirmOGXcZTRj3NIs82gRWjihGhHXPZ7n4vAwW6zB9_4sTKBV9j6xcdSm0GGNfOQDP_PpR5bGI9fRIhaz-fuzcxo6SIWd1r6dRguRXXt54cu36t3OzM_16zieb3_-8Il2HQaoTnhSU2TKJyQMLU-VE5E3NjQ6VYyrFLkZOzFR2qfssR07J5AzjLQdmzHTyqQBr4l_7g1Y54kvegawvrWdL_avVniC4qZgot0bTZIsGn1t-JG28nFDhAYxv8XCpmXA3wJDE-3m9_7n_3Qf7nY5Npm2RvEA1uzyIdz5RXnxEXw58GBvyBD1JZ1eYGnJHFenNZm11MOTihSO7BeBqLA8JsFrhnWJoqxIQ7IgsxWe0o9B7ZtM67rljJK85dRXj-HgWr7vCQyWxdJuABHCGoMq9WMZU7FCkSmL3LHYoUXFh_C2n3N51gqKSF-IBXzIP_ExhK0Aiqv7ghR4c6Eoj2XnWWRQfBR6EgkWG8aFQ-VSRF_IToxwRqkhvAmQksFh1SVq7M5d-NcN0l9y6hM2EcRgoyFs9pCSnSer5E88Pf338Eu45YEm93by3WdwOw5tkhue5CYM6nJln8NN_a0-qcoXnZ0QOLpuyP0Aqh9bOg
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Uncertainty-Aware+Fault+Diagnosis+of+Rotating+Compressors+Using+Dual-Graph+Attention+Networks&rft.jtitle=Machines+%28Basel%29&rft.au=Lee%2C+Seungjoo&rft.au=Kim%2C+YoungSeok&rft.au=Choi%2C+Hyun-Jun&rft.au=Ji%2C+Bongjun&rft.date=2025-08-01&rft.pub=MDPI+AG&rft.issn=2075-1702&rft.eissn=2075-1702&rft.volume=13&rft.issue=8&rft_id=info:doi/10.3390%2Fmachines13080673&rft.externalDocID=A853848270
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2075-1702&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2075-1702&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2075-1702&client=summon