An anomaly detection method for gas turbines in power plants using conditional variational autoencoder optimized with self-attention
An innovative anomaly detection (AD) framework designed for gas turbines (GTs) in power plants working under variable operating conditions (OCs) was proposed based on conditional variational autoencoder (CVAE) optimized with self-attention (SA) in this paper. Three key factors contribute to the mode...
Uložené v:
| Vydané v: | Reliability engineering & system safety Ročník 267; s. 111894 |
|---|---|
| Hlavní autori: | , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier Ltd
01.03.2026
|
| Predmet: | |
| ISSN: | 0951-8320 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | An innovative anomaly detection (AD) framework designed for gas turbines (GTs) in power plants working under variable operating conditions (OCs) was proposed based on conditional variational autoencoder (CVAE) optimized with self-attention (SA) in this paper. Three key factors contribute to the model's superior performance in AD. First, the marginal distributions (MDs) of parameters were transformed into conditional probability distributions (CPDs) by incorporating OC variables as conditional inputs in the variational autoencoder (VAE) model, and decoupled modeling of equipment states and external OCs is achieved. Second, by embedding SA modules, the method dynamically adjusts weight allocation of the parameters to capture complex dependencies among them, which can enhance the capability of the model to represent intricate coupling relationships in multi-dimensional parameters. Third, the logarithmic reconstruction probability (LRP), derived from the probabilistic output of SA-CVAE, serves as a unified health indicator (HI) to evaluate the health condition of the GT. The indicator not only accounts for the discrepancy between the reconstructed and original inputs but also incorporates the influence of latent variable (LV) variance on the reconstruction results. Experiments were carried out on one synthetic, one public, and two real-world datasets, with SA-CVAE compared against six leading AD methods. The results demonstrate that under varying OCs, SA-CVAE exhibits superior performance in AD tasks, achieving leading or competitive results across key evaluation metrics. |
|---|---|
| AbstractList | An innovative anomaly detection (AD) framework designed for gas turbines (GTs) in power plants working under variable operating conditions (OCs) was proposed based on conditional variational autoencoder (CVAE) optimized with self-attention (SA) in this paper. Three key factors contribute to the model's superior performance in AD. First, the marginal distributions (MDs) of parameters were transformed into conditional probability distributions (CPDs) by incorporating OC variables as conditional inputs in the variational autoencoder (VAE) model, and decoupled modeling of equipment states and external OCs is achieved. Second, by embedding SA modules, the method dynamically adjusts weight allocation of the parameters to capture complex dependencies among them, which can enhance the capability of the model to represent intricate coupling relationships in multi-dimensional parameters. Third, the logarithmic reconstruction probability (LRP), derived from the probabilistic output of SA-CVAE, serves as a unified health indicator (HI) to evaluate the health condition of the GT. The indicator not only accounts for the discrepancy between the reconstructed and original inputs but also incorporates the influence of latent variable (LV) variance on the reconstruction results. Experiments were carried out on one synthetic, one public, and two real-world datasets, with SA-CVAE compared against six leading AD methods. The results demonstrate that under varying OCs, SA-CVAE exhibits superior performance in AD tasks, achieving leading or competitive results across key evaluation metrics. |
| ArticleNumber | 111894 |
| Author | Chen, Dongchao Xu, Jingquan Wang, Zhong Li, Xiuxia |
| Author_xml | – sequence: 1 givenname: Dongchao surname: Chen fullname: Chen, Dongchao email: cdc@neepu.edu.cn organization: School of Energy and Power Engineering, Northeast Electric Power University, Jilin 132012, China – sequence: 2 givenname: Xiuxia surname: Li fullname: Li, Xiuxia organization: School of Energy and Power Engineering, Northeast Electric Power University, Jilin 132012, China – sequence: 3 givenname: Jingquan surname: Xu fullname: Xu, Jingquan organization: School of Energy and Power Engineering, Northeast Electric Power University, Jilin 132012, China – sequence: 4 givenname: Zhong surname: Wang fullname: Wang, Zhong organization: China Industrial Control Systems Cyber Emergency Response Team, Beijing 100040, China |
| BookMark | eNp9kL1uwyAURhlSqUnaF-jECzgFbGMjdYmi_kmRurQzwnCdENlgAUmUzn3w2krnTvcO91x931mgmfMOEHqgZEUJ5Y-HVYAYV4ywckUprUUxQ3MiSprVOSO3aBHjgRBSiLKao5-1w8r5XnUXbCCBTtY73EPae4NbH_BORZyOobEOIrYOD_4MAQ-dciniY7Ruh7V3xk6c6vBJBav-dnVMHpz2ZgT8kGxvv8Hgs017HKFrM5USuOn2Dt20qotw_zeX6Ovl-XPzlm0_Xt83622mWZmnTAtW6JIyXXIiKPCGsdqo3JiiYkQLTZq2FJQKYFxz0QKHJi9qwitDlK44yZeIXf_q4GMM0Moh2F6Fi6RETu7kQU7u5OROXt2N0NMVgjHZyUKQUduxFhgbRl3SePsf_gugyH_A |
| Cites_doi | 10.1016/j.engfailanal.2022.106094 10.1016/j.cie.2024.110094 10.1016/j.aei.2025.103571 10.1016/j.ymssp.2025.113204 10.1016/j.eswa.2025.128978 10.1016/j.eswa.2024.124077 10.1016/j.cja.2022.07.021 10.1016/j.asr.2025.06.068 10.1016/j.ymssp.2024.112209 10.1016/j.chemolab.2022.104711 10.1016/j.aei.2025.103455 10.1016/j.ins.2023.119914 10.1016/j.anucene.2024.110973 10.1016/j.nucengdes.2023.112466 10.1016/j.aei.2023.102139 10.1109/TCST.2015.2480003 10.1016/j.engappai.2021.104199 10.3390/data6010005 10.1016/j.oceaneng.2025.122365 10.1016/j.ress.2025.110926 10.1016/j.ymssp.2025.112403 10.1016/j.ress.2025.111558 10.1016/j.energy.2025.134819 10.1016/j.eswa.2024.125521 10.3390/app14114551 10.1016/j.csite.2022.102036 10.1016/j.ress.2025.111060 10.1016/j.ress.2024.110653 10.1109/TMECH.2021.3138834 10.1016/j.procir.2021.03.041 10.1016/j.eswa.2023.123083 10.1016/j.measurement.2025.118236 10.1016/j.ymssp.2025.113122 10.1016/j.engappai.2023.107126 10.1016/j.compind.2023.104007 10.1016/j.ress.2024.110663 10.1016/j.ast.2016.08.008 10.1016/j.eswa.2021.115736 10.1016/j.eswa.2024.125497 10.1016/j.egyr.2023.09.159 10.1016/j.energy.2025.136334 10.1016/j.ymssp.2024.111397 10.1016/j.eswa.2022.119377 10.1109/TKDE.2021.3128667 10.1016/j.applthermaleng.2019.114664 10.1016/j.engappai.2024.108846 10.1016/j.ress.2022.108482 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Ltd |
| Copyright_xml | – notice: 2025 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ress.2025.111894 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| ExternalDocumentID | 10_1016_j_ress_2025_111894 S0951832025010944 |
| GroupedDBID | --K --M .~1 0R~ 123 1B1 1~. 1~5 29P 4.4 457 4G. 5VS 7-5 71M 8P~ 9DU 9JN 9JO AABNK AAEDT AAEDW AAFJI AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYWO ABEFU ABFNM ABJNI ABMAC ABMMH ABWVN ABXDB ACDAQ ACGFS ACIWK ACLOT ACNNM ACRLP ACRPL ACVFH ADBBV ADCNI ADEZE ADMUD ADNMO ADTZH AEBSH AECPX AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFRAH AFTJW AGHFR AGQPQ AGUBO AGYEJ AHHHB AHJVU AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOMHK APXCP ASPBG AVARZ AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFKBS EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HVGLF HZ~ IHE J1W JJJVA KOM LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PRBVW Q38 R2- ROL RPZ SDF SDG SES SET SEW SPC SPCBC SSB SSO SST SSZ T5K TN5 WUQ XPP ZMT ZY4 ~G- ~HD AAYXX CITATION |
| ID | FETCH-LOGICAL-c253t-c924c512c56091e6b228da3dd4720c9c0bf59119e26c69fe6eb348067d0ac7603 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001613977100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0951-8320 |
| IngestDate | Thu Nov 27 01:05:13 EST 2025 Sat Nov 29 17:13:50 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | COAT HI RCAT GTP TET RDCT CIAT Self-attention LS DL LV LRP FNR AMFormer KDE OCSVM EGDP HI-FM PCC DS Variable operating conditions MD LSD ML Pr FWT AD EH AE DCD IS EP LOP Anomaly detection LPT_flow_mod PCA ET RA LOT MAE AS LPT_eff_mod FGMMP FGTFCVP FGHOT ANI SIS HPT_eff_mod IGVCSO CBVP BPT FM CVAE AUROC FPR SA SVR Conditional variational autoencoder R Re OC PHM MFPLCSO SA-CVAE GD SP MSE Acc CC CSP OS COP GL RUL CPFM CP GT LFCPF TE EGT CPD CPF IGV IGVP Gas turbine GCV VAE TEP TIT HRSG |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c253t-c924c512c56091e6b228da3dd4720c9c0bf59119e26c69fe6eb348067d0ac7603 |
| ParticipantIDs | crossref_primary_10_1016_j_ress_2025_111894 elsevier_sciencedirect_doi_10_1016_j_ress_2025_111894 |
| PublicationCentury | 2000 |
| PublicationDate | March 2026 2026-03-00 |
| PublicationDateYYYYMMDD | 2026-03-01 |
| PublicationDate_xml | – month: 03 year: 2026 text: March 2026 |
| PublicationDecade | 2020 |
| PublicationTitle | Reliability engineering & system safety |
| PublicationYear | 2026 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Hu, He, Lin, Lu, Jiang, Ma (bib0011) 2023; 36 Chao, Kulkarni, Goebel, Fink (bib0048) 2021; 6 Song, Sun, Gao, You, Xu (bib0043) 2025; 256 Abdelhak, Tott-Buswell, Prendergast, Ghiasi, Malekjafarian (bib0019) 2025; 340 Pourbabaee, Meskin, Khorasani (bib0012) 2016; 24 Qian, Song, Yao, Zhu, Zhang (bib0026) 2022; 231 Gao, Shao, Yan, Wang, Liu (bib0029) 2026; 265 Fu, Zhong, Lin, Zhao (bib0014) 2021; 101 González-Muñiz, Díaz, Cuadrado, García-Pérez (bib0037) 2022; 224 Cannarile, Compare, Baraldi, Yang, Zio (bib0047) 2020 Amiri, Hashjin, Najafabadib, Beheshtic, Khodadadi (bib0018) 2025; 263 Yao, Bing, Zhu, Xiang, Hu (bib0039) 2024; 214 Antwarg, Miller, Shapira, Rokach (bib0051) 2021; 186 Amjad, Rashid (bib0021) 2024; 182 Yue, Wang, Zhang, Gu (bib0005) 2025; 224 Gallon, Schiemenz, Menicucci, Gill (bib0022) 2025; 76 Li, Li, Li, Sun, Wang, Su, Shi, Zhou (bib0035) 2025; 318 Fahmi, Kashyzadeh, Ghorbani (bib0034) 2024; 14 Brahimi, Hadroug, Iratni, Hafaifa, Colak (bib0013) 2024; 191 Jin, Na, Oh, Kim, Youn (bib0030) 2022; 189 Ramírez, Silva, Tamssaouet, Rojas, Orchard (bib0049) 2025; 228 Chae, Bae (bib0031) 2025; 259 Kumar, Raouf, Kim (bib0008) 2023; 126 Wang, Li, Zhang, Yu, Li, Sun, Shi (bib0015) 2023; 412 Bourdalos, Sakellariou (bib0041) 2025; 238 Sun, Song, Song, Zhao, Yang (bib0016) 2025; 211 Hu, Li, Wang, Chu (bib0040) 2025; 237 Zulfauzi, Dahlan, Sintuya, Setthapun (bib0024) 2023; 9 Fahmi, Kashyzadeh, Ghorbani (bib0020) 2024; 37 Danti, Innocenti (bib0036) 2023; 58 Seo, Noh, Kang, Lim, Ahn, Song, Kim (bib0023) 2024; 135 Abed, Ping (bib0004) 2024; 252 Hu, Zhang, Yang, Fang (bib0028) 2025; 261 Ignacio, Pablo, Antonio (bib0046) 2023; 134 Watban Khalid Fahmia, Reza Kashyzadeh, Ghorbani (bib0002) 2022; 134 Saeed, Jan, Ahmad, Shah, Alshehri, Ghadi, Pitropakis, Buchanan (bib0027) 2026; 296 Zhong, Liu, Jiang, Wang, Chen (bib0050) 2024; 656 Strem, Dhamia, Schmidt, Klöpperc, Kersting (bib0025) 2025; 261 Naeim, Hegazi, Awad, El-Emam (bib0006) 2022; 34 Robles, Martín, Díaz (bib0053) 2023; 152 Wilhelm, Reimann, Gauchel, Mitschang (bib0009) 2021; 99 Zhou, Wang, Zio, Lei, Wen, Chen (bib0042) 2025; 256 Surase, K.Ramakrishna (bib0001) 2025; 327 Chen, Wang, Chai, Chen, Qin (bib0044) 2025; 66 Mousavi, Chaibakhsh, Jamali, Kordestani, Saif (bib0003) 2022; 27 Kim, Ko, Na, Lee, Kim, Son, Yoon, Youn (bib0032) 2023; 215 Bai, Liu, Chai, Zhao, Yu (bib0017) 2020; 166 Liu, Chang, Wang, Yu (bib0045) 2025; 67 Du, Sun, Ye, Cheng, Wang, Sun (bib0038) 2023; 35 Guo, Li, Shen (bib0052) 2024; 245 Fahmi, Kashyzadeh, Ghorbani (bib0033) 2024; 160 Lu, Ju, Huang (bib0010) 2016; 58 Cheng, Ahmad, Gao, Xing, Nie, Chen, Xu, Zhang (bib0007) 2025; 255 Hu (10.1016/j.ress.2025.111894_bib0040) 2025; 237 Ramírez (10.1016/j.ress.2025.111894_bib0049) 2025; 228 Pourbabaee (10.1016/j.ress.2025.111894_bib0012) 2016; 24 Seo (10.1016/j.ress.2025.111894_bib0023) 2024; 135 Robles (10.1016/j.ress.2025.111894_bib0053) 2023; 152 Zhong (10.1016/j.ress.2025.111894_bib0050) 2024; 656 Qian (10.1016/j.ress.2025.111894_bib0026) 2022; 231 Gao (10.1016/j.ress.2025.111894_bib0029) 2026; 265 Amiri (10.1016/j.ress.2025.111894_bib0018) 2025; 263 Fu (10.1016/j.ress.2025.111894_bib0014) 2021; 101 Liu (10.1016/j.ress.2025.111894_bib0045) 2025; 67 Cannarile (10.1016/j.ress.2025.111894_bib0047) 2020 Chae (10.1016/j.ress.2025.111894_bib0031) 2025; 259 Mousavi (10.1016/j.ress.2025.111894_bib0003) 2022; 27 Amjad (10.1016/j.ress.2025.111894_bib0021) 2024; 182 Bourdalos (10.1016/j.ress.2025.111894_bib0041) 2025; 238 Kumar (10.1016/j.ress.2025.111894_bib0008) 2023; 126 Jin (10.1016/j.ress.2025.111894_bib0030) 2022; 189 Abdelhak (10.1016/j.ress.2025.111894_bib0019) 2025; 340 Guo (10.1016/j.ress.2025.111894_bib0052) 2024; 245 Wang (10.1016/j.ress.2025.111894_bib0015) 2023; 412 Gallon (10.1016/j.ress.2025.111894_bib0022) 2025; 76 Fahmi (10.1016/j.ress.2025.111894_bib0033) 2024; 160 Cheng (10.1016/j.ress.2025.111894_bib0007) 2025; 255 Kim (10.1016/j.ress.2025.111894_bib0032) 2023; 215 Watban Khalid Fahmia (10.1016/j.ress.2025.111894_bib0002) 2022; 134 Li (10.1016/j.ress.2025.111894_bib0035) 2025; 318 Hu (10.1016/j.ress.2025.111894_bib0028) 2025; 261 Bai (10.1016/j.ress.2025.111894_bib0017) 2020; 166 Fahmi (10.1016/j.ress.2025.111894_bib0020) 2024; 37 Surase (10.1016/j.ress.2025.111894_bib0001) 2025; 327 Sun (10.1016/j.ress.2025.111894_bib0016) 2025; 211 González-Muñiz (10.1016/j.ress.2025.111894_bib0037) 2022; 224 Chao (10.1016/j.ress.2025.111894_bib0048) 2021; 6 Hu (10.1016/j.ress.2025.111894_bib0011) 2023; 36 Antwarg (10.1016/j.ress.2025.111894_bib0051) 2021; 186 Saeed (10.1016/j.ress.2025.111894_bib0027) 2026; 296 Ignacio (10.1016/j.ress.2025.111894_bib0046) 2023; 134 Danti (10.1016/j.ress.2025.111894_bib0036) 2023; 58 Du (10.1016/j.ress.2025.111894_bib0038) 2023; 35 Yue (10.1016/j.ress.2025.111894_bib0005) 2025; 224 Strem (10.1016/j.ress.2025.111894_bib0025) 2025; 261 Naeim (10.1016/j.ress.2025.111894_bib0006) 2022; 34 Fahmi (10.1016/j.ress.2025.111894_bib0034) 2024; 14 Song (10.1016/j.ress.2025.111894_bib0043) 2025; 256 Abed (10.1016/j.ress.2025.111894_bib0004) 2024; 252 Chen (10.1016/j.ress.2025.111894_bib0044) 2025; 66 Zulfauzi (10.1016/j.ress.2025.111894_bib0024) 2023; 9 Zhou (10.1016/j.ress.2025.111894_bib0042) 2025; 256 Lu (10.1016/j.ress.2025.111894_bib0010) 2016; 58 Brahimi (10.1016/j.ress.2025.111894_bib0013) 2024; 191 Yao (10.1016/j.ress.2025.111894_bib0039) 2024; 214 Wilhelm (10.1016/j.ress.2025.111894_bib0009) 2021; 99 |
| References_xml | – volume: 101 year: 2021 ident: bib0014 article-title: A re-optimized deep auto-encoder for gas turbine unsupervised anomaly detection publication-title: Eng Appl Artif Intell – volume: 135 year: 2024 ident: bib0023 article-title: Graph neural networks for anomaly detection and diagnosis in hydrogen extraction systems publication-title: Eng Appl Artif Intell – volume: 318 year: 2025 ident: bib0035 article-title: Research on anomaly detection of steam power system based on the coupling of thermoeconomics and autoencoder publication-title: Energy – volume: 24 start-page: 1184 year: 2016 end-page: 1200 ident: bib0012 article-title: Sensor fault detection, isolation,and identification using multiple-model-based hybrid Kalman filter for gas turbine engines publication-title: IEEE Trans Control Syst Technol – volume: 255 year: 2025 ident: bib0007 article-title: Diagnostics and prognostics in power plants: a systematic review publication-title: Reliab Eng Syst Saf – volume: 126 year: 2023 ident: bib0008 article-title: Review on prognostics and health management in smart factory: from conventional to deep learning perspectives publication-title: Eng Appl Artif Intell – volume: 9 start-page: 154 year: 2023 end-page: 158 ident: bib0024 article-title: Anomaly detection using K-Means and long-short term memory for predictive maintenance of large-scale solar (LSS) photovoltaic plant publication-title: Energy Rep – volume: 237 year: 2025 ident: bib0040 article-title: A health monitoring and early fault detection method of rotating machines based on latent variables of diffusion model publication-title: Mech Syst Signal Process – volume: 36 start-page: 449 year: 2023 end-page: 470 ident: bib0011 article-title: Digital twin model of gas turbine and its application in warning of performance fault publication-title: Chin J Aeronaut – volume: 238 year: 2025 ident: bib0041 article-title: A statistical time series model-based method for robust detection of incipient faults in rotating machinery under different operating conditions publication-title: Mech Syst Signal Process – volume: 35 start-page: 12208 year: 2023 end-page: 12219 ident: bib0038 article-title: Gan-based anomaly detection for multivariate time series using polluted training set publication-title: IEEE Trans Knowl Data Eng – volume: 263 year: 2025 ident: bib0018 article-title: An innovative data-driven AI approach for detecting and isolating faults in gas turbines at power plants publication-title: Expert Syst Appl – volume: 296 year: 2026 ident: bib0027 article-title: Generative adversarial networks-enabled anomaly detection systems: A survey publication-title: Expert Syst Appl – volume: 214 year: 2024 ident: bib0039 article-title: A novel stochastic process diffusion model for wind turbines condition monitoring and fault identification with multi-parameter information fusion publication-title: Mech Syst Signal Process – volume: 58 year: 2023 ident: bib0036 article-title: A methodology to determine the optimal train-set size for autoencoders applied to energy systems publication-title: Adv Eng Inform – volume: 256 year: 2025 ident: bib0043 article-title: Residual feature-based semi-supervised anomaly detection for Gearbox under varying rotational speeds publication-title: Measurement – volume: 14 start-page: 4551 year: 2024 ident: bib0034 article-title: Advancements in gas turbine fault detection: A machine learning approach based on the temporal convolutional network–autoencoder model publication-title: Appl Sci – volume: 99 start-page: 278 year: 2021 end-page: 283 ident: bib0009 article-title: Overview on hybrid approaches to fault detection and diagnosis: Combining data-driven, physics-based and knowledge-based models publication-title: Procedia CIRP – volume: 134 year: 2023 ident: bib0046 article-title: Unsupervised learning of global factors in deep generative models publication-title: Pattern Recognit – volume: 37 start-page: 1691 year: 2024 end-page: 1699 ident: bib0020 article-title: Enhanced autoregressive integrated moving average model for anomaly detection in power plant operations publication-title: IJE Trans B: Appl – volume: 224 year: 2025 ident: bib0005 article-title: An anomaly detection method for gas turbines based on single-condition training with zero-fault sample publication-title: Mech Syst Signal Process – volume: 259 year: 2025 ident: bib0031 article-title: An adaptive mixture prior in Bayesian convolutional autoencoder for early detecting anomalous degradation behaviors in lithium-ion batteries publication-title: Reliab Eng Syst Saf – volume: 252 year: 2024 ident: bib0004 article-title: Implementing data mining techniques for gas-turbine (GT) health tracking and life management: The bibliographic perspective publication-title: Expert Syst Appl – volume: 412 year: 2023 ident: bib0015 article-title: Research on anomaly detection and positioning of marine nuclear power steam turbine unit based on isolated forest publication-title: Nucl Eng Des – volume: 152 year: 2023 ident: bib0053 article-title: OpenTwins: An open-source framework for the development of next-gen compositional digital twins publication-title: Comput Ind – volume: 656 year: 2024 ident: bib0050 article-title: Refining one-class representation: a unified transformer for unsupervised time-series anomaly detection publication-title: Inf Sci (Ny) – volume: 228 year: 2025 ident: bib0049 article-title: Fault detection and monitoring using a data-driven information-based strategy: Method, theory, and application publication-title: Mech Syst Signal Process – volume: 231 year: 2022 ident: bib0026 article-title: A review on autoencoder based representation learning for fault detection and diagnosis in industrial processes publication-title: Chemom Intell Lab Syst – volume: 67 year: 2025 ident: bib0045 article-title: Speed-Normalized Expansion-and-Shrinkage network for health indicator generating under time-varying conditions publication-title: Adv Eng Inform – volume: 261 year: 2025 ident: bib0028 article-title: A deep autoencoder with structured latent space for process monitoring and anomaly detection in coal-fired power units publication-title: Reliab Eng Syst Saf – volume: 327 year: 2025 ident: bib0001 article-title: Efficient polynomial PID controller and nonlinear autoregressive with exogenous for increasing the efficiency of combined gas turbine (CGT) plant publication-title: Energy – volume: 245 year: 2024 ident: bib0052 article-title: A lightweight residual network based on improved knowledge transfer and quantized distillation for cross-domain fault diagnosis of rolling bearings publication-title: Expert Syst Appl – volume: 58 start-page: 36 year: 2016 end-page: 47 ident: bib0010 article-title: An improved extended Kalman filter with inequality constraints for gas turbine engine health monitoring publication-title: Aerosp Sci Technol – volume: 265 year: 2026 ident: bib0029 article-title: Partial sensing information-driven threshold cyclic update graph autoencoder for mechanical anomaly detection publication-title: Reliab Eng Syst Saf – volume: 211 year: 2025 ident: bib0016 article-title: KPCA-based fault detection and diagnosis model for the chemical and volume control system in nuclear power plants publication-title: Ann Nucl Energy – volume: 160 year: 2024 ident: bib0033 article-title: Fault detection in the gas turbine of the Kirkuk power plant: an anomaly detection approach using DLSTM-Autoencoder publication-title: Eng Fail Anal – volume: 182 year: 2024 ident: bib0021 article-title: Time series forecasting and anomaly detection using deep learning publication-title: Comput Chem Eng – volume: 261 year: 2025 ident: bib0025 article-title: APT: alarm prediction transformer publication-title: Expert Syst Appl – volume: 256 year: 2025 ident: bib0042 article-title: Unsupervised anomaly detection of machines operating under time-varying conditions: DCD-VAE enabled feature disentanglement of operating conditions and states publication-title: Reliab Eng Syst Saf – volume: 215 year: 2023 ident: bib0032 article-title: Opt-TCAE: Optimal temporal convolutional auto-encoder for boiler tube leakage detection in a thermal power plant using multi-sensor data publication-title: Expert Syst Appl – volume: 189 year: 2022 ident: bib0030 article-title: A new auto-encoder-based dynamic threshold to reduce false alarm rate for anomaly detection of steam turbines publication-title: Expert Syst Appl – volume: 166 year: 2020 ident: bib0017 article-title: Anomaly detection of gas turbines based on normal pattern extraction publication-title: Appl Therm Eng – volume: 134 year: 2022 ident: bib0002 article-title: A comprehensive review on mechanical failures cause vibration in the gas turbine of combined cycle power plants publication-title: Eng Fail Anal – volume: 224 year: 2022 ident: bib0037 article-title: Health indicator for machine condition monitoring built in the latent space of a deep autoencoder publication-title: Reliab Eng Syst Saf – year: 2020 ident: bib0047 article-title: The aramis data challenge: prognostics and health management in evolving environments publication-title: Proceedings of the 30th European Safety and Reliability Conference – volume: 191 year: 2024 ident: bib0013 article-title: Advancing predictive maintenance for gas turbines: An intelligent monitoring approach with ANFIS, LSTM, and reliability analysis publication-title: Comput Ind Eng – volume: 66 year: 2025 ident: bib0044 article-title: A polynomial speed normalized health indicator for both incipient fault detection and prognosis of variable-speed wind turbine bearings publication-title: Adv Eng Inform – volume: 186 year: 2021 ident: bib0051 article-title: Explaining anomalies detected by autoencoders using shapley additive explanations publication-title: Expert Syst Appl – volume: 340 year: 2025 ident: bib0019 article-title: Scour identification around offshore wind turbine monopile foundations using an unsupervised anomaly detection approach publication-title: Ocean Eng – volume: 27 start-page: 3339 year: 2022 end-page: 3349 ident: bib0003 article-title: A new fault diagnosis approach for heavy-duty gas turbines publication-title: IEEE/ASME Trans Mechatron – volume: 34 year: 2022 ident: bib0006 article-title: Thermodynamic analysis of gas turbine performance using the enthalpy–entropy approach publication-title: Case Stud Therm Eng – volume: 76 start-page: 2960 year: 2025 end-page: 2976 ident: bib0022 article-title: Convolutional neural network design and evaluation for real-time multivariate time series fault detection in spacecraft attitude sensors publication-title: Adv Space Res – volume: 6 start-page: 5 year: 2021 ident: bib0048 article-title: Aircraft engine run-to-failure dataset under real flight conditions for prognostics and diagnostics publication-title: Data – volume: 134 year: 2022 ident: 10.1016/j.ress.2025.111894_bib0002 article-title: A comprehensive review on mechanical failures cause vibration in the gas turbine of combined cycle power plants publication-title: Eng Fail Anal doi: 10.1016/j.engfailanal.2022.106094 – volume: 191 year: 2024 ident: 10.1016/j.ress.2025.111894_bib0013 article-title: Advancing predictive maintenance for gas turbines: An intelligent monitoring approach with ANFIS, LSTM, and reliability analysis publication-title: Comput Ind Eng doi: 10.1016/j.cie.2024.110094 – volume: 67 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0045 article-title: Speed-Normalized Expansion-and-Shrinkage network for health indicator generating under time-varying conditions publication-title: Adv Eng Inform doi: 10.1016/j.aei.2025.103571 – volume: 238 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0041 article-title: A statistical time series model-based method for robust detection of incipient faults in rotating machinery under different operating conditions publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2025.113204 – volume: 296 year: 2026 ident: 10.1016/j.ress.2025.111894_bib0027 article-title: Generative adversarial networks-enabled anomaly detection systems: A survey publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2025.128978 – volume: 252 year: 2024 ident: 10.1016/j.ress.2025.111894_bib0004 article-title: Implementing data mining techniques for gas-turbine (GT) health tracking and life management: The bibliographic perspective publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2024.124077 – volume: 36 start-page: 449 issue: 03 year: 2023 ident: 10.1016/j.ress.2025.111894_bib0011 article-title: Digital twin model of gas turbine and its application in warning of performance fault publication-title: Chin J Aeronaut doi: 10.1016/j.cja.2022.07.021 – volume: 76 start-page: 2960 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0022 article-title: Convolutional neural network design and evaluation for real-time multivariate time series fault detection in spacecraft attitude sensors publication-title: Adv Space Res doi: 10.1016/j.asr.2025.06.068 – volume: 182 year: 2024 ident: 10.1016/j.ress.2025.111894_bib0021 article-title: Time series forecasting and anomaly detection using deep learning publication-title: Comput Chem Eng – volume: 224 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0005 article-title: An anomaly detection method for gas turbines based on single-condition training with zero-fault sample publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2024.112209 – volume: 231 year: 2022 ident: 10.1016/j.ress.2025.111894_bib0026 article-title: A review on autoencoder based representation learning for fault detection and diagnosis in industrial processes publication-title: Chemom Intell Lab Syst doi: 10.1016/j.chemolab.2022.104711 – volume: 66 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0044 article-title: A polynomial speed normalized health indicator for both incipient fault detection and prognosis of variable-speed wind turbine bearings publication-title: Adv Eng Inform doi: 10.1016/j.aei.2025.103455 – volume: 656 year: 2024 ident: 10.1016/j.ress.2025.111894_bib0050 article-title: Refining one-class representation: a unified transformer for unsupervised time-series anomaly detection publication-title: Inf Sci (Ny) doi: 10.1016/j.ins.2023.119914 – volume: 211 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0016 article-title: KPCA-based fault detection and diagnosis model for the chemical and volume control system in nuclear power plants publication-title: Ann Nucl Energy doi: 10.1016/j.anucene.2024.110973 – volume: 412 year: 2023 ident: 10.1016/j.ress.2025.111894_bib0015 article-title: Research on anomaly detection and positioning of marine nuclear power steam turbine unit based on isolated forest publication-title: Nucl Eng Des doi: 10.1016/j.nucengdes.2023.112466 – volume: 58 year: 2023 ident: 10.1016/j.ress.2025.111894_bib0036 article-title: A methodology to determine the optimal train-set size for autoencoders applied to energy systems publication-title: Adv Eng Inform doi: 10.1016/j.aei.2023.102139 – volume: 24 start-page: 1184 issue: 4 year: 2016 ident: 10.1016/j.ress.2025.111894_bib0012 article-title: Sensor fault detection, isolation,and identification using multiple-model-based hybrid Kalman filter for gas turbine engines publication-title: IEEE Trans Control Syst Technol doi: 10.1109/TCST.2015.2480003 – volume: 101 year: 2021 ident: 10.1016/j.ress.2025.111894_bib0014 article-title: A re-optimized deep auto-encoder for gas turbine unsupervised anomaly detection publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2021.104199 – volume: 6 start-page: 5 issue: 1 year: 2021 ident: 10.1016/j.ress.2025.111894_bib0048 article-title: Aircraft engine run-to-failure dataset under real flight conditions for prognostics and diagnostics publication-title: Data doi: 10.3390/data6010005 – volume: 340 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0019 article-title: Scour identification around offshore wind turbine monopile foundations using an unsupervised anomaly detection approach publication-title: Ocean Eng doi: 10.1016/j.oceaneng.2025.122365 – volume: 259 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0031 article-title: An adaptive mixture prior in Bayesian convolutional autoencoder for early detecting anomalous degradation behaviors in lithium-ion batteries publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2025.110926 – volume: 228 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0049 article-title: Fault detection and monitoring using a data-driven information-based strategy: Method, theory, and application publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2025.112403 – volume: 265 year: 2026 ident: 10.1016/j.ress.2025.111894_bib0029 article-title: Partial sensing information-driven threshold cyclic update graph autoencoder for mechanical anomaly detection publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2025.111558 – volume: 318 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0035 article-title: Research on anomaly detection of steam power system based on the coupling of thermoeconomics and autoencoder publication-title: Energy doi: 10.1016/j.energy.2025.134819 – volume: 261 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0025 article-title: APT: alarm prediction transformer publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2024.125521 – volume: 189 year: 2022 ident: 10.1016/j.ress.2025.111894_bib0030 article-title: A new auto-encoder-based dynamic threshold to reduce false alarm rate for anomaly detection of steam turbines publication-title: Expert Syst Appl – volume: 14 start-page: 4551 issue: 11 year: 2024 ident: 10.1016/j.ress.2025.111894_bib0034 article-title: Advancements in gas turbine fault detection: A machine learning approach based on the temporal convolutional network–autoencoder model publication-title: Appl Sci doi: 10.3390/app14114551 – volume: 37 start-page: 1691 issue: 08 year: 2024 ident: 10.1016/j.ress.2025.111894_bib0020 article-title: Enhanced autoregressive integrated moving average model for anomaly detection in power plant operations publication-title: IJE Trans B: Appl – volume: 34 year: 2022 ident: 10.1016/j.ress.2025.111894_bib0006 article-title: Thermodynamic analysis of gas turbine performance using the enthalpy–entropy approach publication-title: Case Stud Therm Eng doi: 10.1016/j.csite.2022.102036 – volume: 261 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0028 article-title: A deep autoencoder with structured latent space for process monitoring and anomaly detection in coal-fired power units publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2025.111060 – volume: 256 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0042 article-title: Unsupervised anomaly detection of machines operating under time-varying conditions: DCD-VAE enabled feature disentanglement of operating conditions and states publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2024.110653 – volume: 160 year: 2024 ident: 10.1016/j.ress.2025.111894_bib0033 article-title: Fault detection in the gas turbine of the Kirkuk power plant: an anomaly detection approach using DLSTM-Autoencoder publication-title: Eng Fail Anal – year: 2020 ident: 10.1016/j.ress.2025.111894_bib0047 article-title: The aramis data challenge: prognostics and health management in evolving environments – volume: 27 start-page: 3339 issue: 5 year: 2022 ident: 10.1016/j.ress.2025.111894_bib0003 article-title: A new fault diagnosis approach for heavy-duty gas turbines publication-title: IEEE/ASME Trans Mechatron doi: 10.1109/TMECH.2021.3138834 – volume: 99 start-page: 278 year: 2021 ident: 10.1016/j.ress.2025.111894_bib0009 article-title: Overview on hybrid approaches to fault detection and diagnosis: Combining data-driven, physics-based and knowledge-based models publication-title: Procedia CIRP doi: 10.1016/j.procir.2021.03.041 – volume: 245 year: 2024 ident: 10.1016/j.ress.2025.111894_bib0052 article-title: A lightweight residual network based on improved knowledge transfer and quantized distillation for cross-domain fault diagnosis of rolling bearings publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2023.123083 – volume: 256 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0043 article-title: Residual feature-based semi-supervised anomaly detection for Gearbox under varying rotational speeds publication-title: Measurement doi: 10.1016/j.measurement.2025.118236 – volume: 237 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0040 article-title: A health monitoring and early fault detection method of rotating machines based on latent variables of diffusion model publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2025.113122 – volume: 126 year: 2023 ident: 10.1016/j.ress.2025.111894_bib0008 article-title: Review on prognostics and health management in smart factory: from conventional to deep learning perspectives publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2023.107126 – volume: 152 year: 2023 ident: 10.1016/j.ress.2025.111894_bib0053 article-title: OpenTwins: An open-source framework for the development of next-gen compositional digital twins publication-title: Comput Ind doi: 10.1016/j.compind.2023.104007 – volume: 255 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0007 article-title: Diagnostics and prognostics in power plants: a systematic review publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2024.110663 – volume: 58 start-page: 36 year: 2016 ident: 10.1016/j.ress.2025.111894_bib0010 article-title: An improved extended Kalman filter with inequality constraints for gas turbine engine health monitoring publication-title: Aerosp Sci Technol doi: 10.1016/j.ast.2016.08.008 – volume: 186 year: 2021 ident: 10.1016/j.ress.2025.111894_bib0051 article-title: Explaining anomalies detected by autoencoders using shapley additive explanations publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2021.115736 – volume: 263 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0018 article-title: An innovative data-driven AI approach for detecting and isolating faults in gas turbines at power plants publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2024.125497 – volume: 9 start-page: 154 year: 2023 ident: 10.1016/j.ress.2025.111894_bib0024 article-title: Anomaly detection using K-Means and long-short term memory for predictive maintenance of large-scale solar (LSS) photovoltaic plant publication-title: Energy Rep doi: 10.1016/j.egyr.2023.09.159 – volume: 134 year: 2023 ident: 10.1016/j.ress.2025.111894_bib0046 article-title: Unsupervised learning of global factors in deep generative models publication-title: Pattern Recognit – volume: 327 year: 2025 ident: 10.1016/j.ress.2025.111894_bib0001 article-title: Efficient polynomial PID controller and nonlinear autoregressive with exogenous for increasing the efficiency of combined gas turbine (CGT) plant publication-title: Energy doi: 10.1016/j.energy.2025.136334 – volume: 214 year: 2024 ident: 10.1016/j.ress.2025.111894_bib0039 article-title: A novel stochastic process diffusion model for wind turbines condition monitoring and fault identification with multi-parameter information fusion publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2024.111397 – volume: 215 year: 2023 ident: 10.1016/j.ress.2025.111894_bib0032 article-title: Opt-TCAE: Optimal temporal convolutional auto-encoder for boiler tube leakage detection in a thermal power plant using multi-sensor data publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2022.119377 – volume: 35 start-page: 12208 issue: 12 year: 2023 ident: 10.1016/j.ress.2025.111894_bib0038 article-title: Gan-based anomaly detection for multivariate time series using polluted training set publication-title: IEEE Trans Knowl Data Eng doi: 10.1109/TKDE.2021.3128667 – volume: 166 year: 2020 ident: 10.1016/j.ress.2025.111894_bib0017 article-title: Anomaly detection of gas turbines based on normal pattern extraction publication-title: Appl Therm Eng doi: 10.1016/j.applthermaleng.2019.114664 – volume: 135 year: 2024 ident: 10.1016/j.ress.2025.111894_bib0023 article-title: Graph neural networks for anomaly detection and diagnosis in hydrogen extraction systems publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2024.108846 – volume: 224 year: 2022 ident: 10.1016/j.ress.2025.111894_bib0037 article-title: Health indicator for machine condition monitoring built in the latent space of a deep autoencoder publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2022.108482 |
| SSID | ssj0004957 |
| Score | 2.4725728 |
| Snippet | An innovative anomaly detection (AD) framework designed for gas turbines (GTs) in power plants working under variable operating conditions (OCs) was proposed... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 111894 |
| SubjectTerms | Anomaly detection Conditional variational autoencoder Gas turbine Self-attention Variable operating conditions |
| Title | An anomaly detection method for gas turbines in power plants using conditional variational autoencoder optimized with self-attention |
| URI | https://dx.doi.org/10.1016/j.ress.2025.111894 |
| Volume | 267 |
| WOSCitedRecordID | wos001613977100001&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0951-8320 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0004957 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELaWlgMcEE9RXvKBW5QqbyfHFSoChCokioi4RLbjtKm2Sekmqy1nfgA_mXHGTkJBCJC4RKtIcVaeb2fGs998Q8jzMq18yfzYBd9fupCBV_CT8oQrGIPw7QOsq2FqyVt2eJjmefZusfhme2E2K9Y06Xabnf9XU8M9MLZunf0Lc4-Lwg34DEaHK5gdrn9k-KWmF7dnfHXplKpTOAocB0UPnMJjvnYgzgjNdx845HpOmp4mrQkxvWnC1X9kY5FwA4dpWzDkfddq4UutP9GCrzmrv1j2-lqtKldrdTajpa3st1rVKAZ-6ahJ_XDAHOpIO2teGTkSZBoYV9g2x_KEtyNnaCAe5HW_rcdYkvcDDGG9z_2E84-mCP7ppDWB2dQ1gmQidmGxzTbcTOwmrFr6Ljghb-7AAxzo8VMwwLrE6b6uW-zDK2IdH1KcqXxFZPu9XlivCxmhDyfe6BrZDVicgZ_cXb4-yN9MvbYZqsfaL2IasZAzePVNv052ZgnM0W1yy5w86BIRc4csVHOX3JzpUd4jX5cNNdihI3YoYocCdihgh1rs0LqhA3YoYocO2KEz7NAZdugMO3TEDtXYoT9i5z758PLg6MUr14zpcGUQh50r4QgvIW-UkDxnvkpEEKQlD8syYoEnM-mJKoaQmqkgkUlWqUSJMEohSyo9LlnihQ_ITtM26iGhrBS-4Ix7QoaR5BXEBBnHvExTEXMeBXvEsftZnKMaS2FpiqeF3v1C736Bu79HYrvlhcknMU8sACG_ee7RPz73mNyYgPyE7HQXvXpKrstNV68vnhkgfQeFU6Mr |
| linkProvider | Elsevier |
| 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=An+anomaly+detection+method+for+gas+turbines+in+power+plants+using+conditional+variational+autoencoder+optimized+with+self-attention&rft.jtitle=Reliability+engineering+%26+system+safety&rft.au=Chen%2C+Dongchao&rft.au=Li%2C+Xiuxia&rft.au=Xu%2C+Jingquan&rft.au=Wang%2C+Zhong&rft.date=2026-03-01&rft.pub=Elsevier+Ltd&rft.issn=0951-8320&rft.volume=267&rft_id=info:doi/10.1016%2Fj.ress.2025.111894&rft.externalDocID=S0951832025010944 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0951-8320&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0951-8320&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0951-8320&client=summon |