Chiller fault diagnosis based on improved variational autoencoder and co-training framework: A case study of insufficient samples

Implementing efficient automatic fault diagnosis is critical for saving energy and minimizing financial losses in the heating ventilation air-conditioning (HVAC) systems of commercial buildings. However, the limited quantity and weak features of fault samples acquired during HVAC operations hinder t...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of Building Engineering Ročník 88; s. 109137
Hlavní autori: Lu, Cheng, Ma, Xiang, Yan, Ke
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.07.2024
Predmet:
ISSN:2352-7102, 2352-7102
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Implementing efficient automatic fault diagnosis is critical for saving energy and minimizing financial losses in the heating ventilation air-conditioning (HVAC) systems of commercial buildings. However, the limited quantity and weak features of fault samples acquired during HVAC operations hinder the effectiveness of conventional machine learning-based fault diagnosis methodologies. This paper proposes a method based on an improved conditional variational autoencoder (MCVAE) and co-training (CT) ideology to address the issue of insufficient training samples. Initially, we employ MCVAE to synthesize an extensive dataset of chiller fault samples from the original training dataset. Subsequently, the beneficial samples for training our fault diagnostic classifier, namely high-quality samples, are selected from the generated dataset using the CT-based framework. Finally, the selected high-quality samples are merged into the original training dataset to train the ultimate fault classifiers. Experimental results demonstrate that our proposed method outperforms in effectiveness and efficiency compared to recently published methods. For instance, in the case of fault level 1 compared to the suboptimal model, our approach exhibits improvements of 2.41% when each type has 5 fault samples. •The combination of MIXUP algorithm and conditional variational autoencoder are used to synthesize fault samples.•A high-quality sample selection framework is proposed based on Co-Training.•The proposed method improves both the effectiveness and efficiency of the original data augmentation framework for chiller FDD.
AbstractList Implementing efficient automatic fault diagnosis is critical for saving energy and minimizing financial losses in the heating ventilation air-conditioning (HVAC) systems of commercial buildings. However, the limited quantity and weak features of fault samples acquired during HVAC operations hinder the effectiveness of conventional machine learning-based fault diagnosis methodologies. This paper proposes a method based on an improved conditional variational autoencoder (MCVAE) and co-training (CT) ideology to address the issue of insufficient training samples. Initially, we employ MCVAE to synthesize an extensive dataset of chiller fault samples from the original training dataset. Subsequently, the beneficial samples for training our fault diagnostic classifier, namely high-quality samples, are selected from the generated dataset using the CT-based framework. Finally, the selected high-quality samples are merged into the original training dataset to train the ultimate fault classifiers. Experimental results demonstrate that our proposed method outperforms in effectiveness and efficiency compared to recently published methods. For instance, in the case of fault level 1 compared to the suboptimal model, our approach exhibits improvements of 2.41% when each type has 5 fault samples. •The combination of MIXUP algorithm and conditional variational autoencoder are used to synthesize fault samples.•A high-quality sample selection framework is proposed based on Co-Training.•The proposed method improves both the effectiveness and efficiency of the original data augmentation framework for chiller FDD.
ArticleNumber 109137
Author Lu, Cheng
Ma, Xiang
Yan, Ke
Author_xml – sequence: 1
  givenname: Cheng
  surname: Lu
  fullname: Lu, Cheng
  organization: College of Information Engineering, China Jiliang University, Hangzhou, 310018, China
– sequence: 2
  givenname: Xiang
  orcidid: 0000-0003-4269-7603
  surname: Ma
  fullname: Ma, Xiang
  email: maxiang@cjlu.edu.cn
  organization: College of Information Engineering, China Jiliang University, Hangzhou, 310018, China
– sequence: 3
  givenname: Ke
  surname: Yan
  fullname: Yan, Ke
  email: keddiyan@gmail.com
  organization: Mechanical and Electrical Engineering, Hunan University, Changsha, 410006, China
BookMark eNp9kM1KAzEUhYNUsNa-gKu8wNQ7ybQzI25K8Q8KbnQd8lszziQlSStd-ubOWBfioqt7uPAdON8lGjnvNELXOcxyyBc3zazxQs8IkKJ_1Dktz9CY0DnJyhzI6E--QNMYGwAg9ZxWi2KMvlbvtm11wIbv2oSV5Rvno41Y8KgV9g7bbhv8vs97HixP1jveYr5LXjvpVU9yp7D0WQrcOus22ATe6U8fPm7xEsu-Bse0UwfsDbYu7oyx0mqXcOTdttXxCp0b3kY9_b0T9PZw_7p6ytYvj8-r5TqTFCBluTaCypIoQbmaCyjLhalq0ItaQFUWBqiRVEowSkJZCzInAKIACbISlcoVnSBy7JXBxxi0YdtgOx4OLAc2eGQNGzyywSM7euyh6h8kbfqRMMxtT6N3R1T3o_ZWBxaH3VIrG7RMTHl7Cv8GVVeTTg
CitedBy_id crossref_primary_10_3390_buildings15040648
Cites_doi 10.1016/j.enbuild.2022.112207
10.1016/j.enbenv.2019.11.003
10.1016/j.ijrefrig.2006.12.012
10.1016/j.apenergy.2023.121030
10.1016/j.dcan.2022.03.023
10.1016/j.engappai.2023.106316
10.3390/su13126828
10.1016/j.buildenv.2018.01.029
10.1016/j.asoc.2020.106333
10.1007/s10462-023-10579-0
10.1016/j.enbuild.2022.112241
10.1016/j.autcon.2019.04.002
10.1016/j.buildenv.2022.108821
10.1016/j.ijrefrig.2019.03.008
10.1007/s10845-019-01522-8
10.1016/j.rser.2022.112395
10.1016/j.buildenv.2021.107982
10.1016/j.enbuild.2013.12.038
10.1016/j.enbuild.2021.111467
10.1109/TASE.2020.3035620
10.1109/TASE.2006.888053
10.1080/10789669.2005.10391123
10.1016/j.arcontrol.2004.12.002
10.3390/en12030527
10.1016/j.measurement.2022.111045
10.1002/er.1530
ContentType Journal Article
Copyright 2024
Copyright_xml – notice: 2024
DBID AAYXX
CITATION
DOI 10.1016/j.jobe.2024.109137
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
EISSN 2352-7102
ExternalDocumentID 10_1016_j_jobe_2024_109137
S2352710224007058
GroupedDBID --M
0R~
457
7-5
8P~
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXUO
ABMAC
ABYKQ
ACDAQ
ACGFS
ACHRH
ACNTT
ACRLP
ADBBV
ADEZE
AEBSH
AEKER
AFKWA
AFTJW
AGHFR
AGJBL
AGUBO
AGUMN
AHJVU
AIEXJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AXJTR
BJAXD
BKOJK
BLXMC
EBS
EFJIC
FDB
FEDTE
FIRID
FYGXN
GBLVA
HVGLF
KOM
M41
O9-
OAUVE
ROL
SPC
SPCBC
SSB
SSL
SST
SSZ
T5K
~G-
4.4
AATTM
AAXKI
AAYWO
AAYXX
ABJNI
ABXDB
ACLOT
ACVFH
ADCNI
AEIPS
AEUPX
AFJKZ
AFPUW
AIGII
AIIUN
AKBMS
AKYEP
ANKPU
APXCP
CITATION
EFKBS
EFLBG
EJD
ID FETCH-LOGICAL-c300t-1efb3c72db3ad5b0776f890e69b0874f03fc3cc0fdc079b25200b40c0c8b8d1d3
ISICitedReferencesCount 13
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001216950400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2352-7102
IngestDate Tue Nov 18 22:33:33 EST 2025
Sat Nov 29 06:12:27 EST 2025
Sat May 04 15:44:58 EDT 2024
IsPeerReviewed true
IsScholarly true
Keywords Fault diagnosis
Variational autoencoder
Data augmentation
Chiller
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c300t-1efb3c72db3ad5b0776f890e69b0874f03fc3cc0fdc079b25200b40c0c8b8d1d3
ORCID 0000-0003-4269-7603
ParticipantIDs crossref_primary_10_1016_j_jobe_2024_109137
crossref_citationtrail_10_1016_j_jobe_2024_109137
elsevier_sciencedirect_doi_10_1016_j_jobe_2024_109137
PublicationCentury 2000
PublicationDate 2024-07-01
2024-07-00
PublicationDateYYYYMMDD 2024-07-01
PublicationDate_xml – month: 07
  year: 2024
  text: 2024-07-01
  day: 01
PublicationDecade 2020
PublicationTitle Journal of Building Engineering
PublicationYear 2024
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Chen, Zhang, Li, Shi, Gao, Hu (b15) 2022; 161
Zhao, Zhang, Zhang, Wang, Li (b4) 2020; 1
Wang, Sun, Jin (b28) 2020; 92
Zhang, Li, Wei, Zhang (b19) 2022; 269
Gupta, Agarwal, Singh, Rai (b30) 2018; 32
A. Blum, T. Mitchell, Combining Labeled and Unlabeled Data with Co-Training y.
De Oliveira, Berton (b20) 2023
A. Razavi, Generating Diverse High-Fidelity Images with VQ-VAE-2.
Zhang, Li, Li, Zhang, Peng (b18) 2021; 253
Lapisa, Bozonnet, Salagnac, Abadie (b1) 2018; 132
Tudoroiu, Zaheeruddin, Tudoroiu, Jeflea (b16) 2008
Isermann (b8) 2005
Namburu, Azam, Luo, Choi, Pattipati (b9) 2007; 4
Zhong, Yan, Dai, Jin, Lou (b33) 2019; 12
Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, Bengio (b25) 2014
Du, Fan, Chi, Jin (b10) 2014; 72
Zhang, Cisse, Dauphin, Lopez-Paz (b11) 2018
Zhang, Li, Chen, Cheng, Xing, Wang, Zhang (b35) 2022; 268
Wang, Wang, He, Wang (b2) 2019; 102
Gálvez, Diez-Olivan, Seneviratne, Galar (b13) 2021; 13
Shi, O’Brien (b5) 2019; 104
Salimans, Goodfellow, Zaremba, Cheung, Radford, Chen (b31) 2016
Zhou, Wang, Ma (b7) 2009; 33
Zhang, Yang, Yi, Lim, An, Li (b23) 2023; 70
Yan (b26) 2021; 201
Katipamula, Brambley (b6) 2005; 11
Yan, Su, Huang, Mo (b34) 2022; 19
Chen, O’Neill, Wen, Pradhan, Yang, Lu, Lin, Miyata, Lee, Shen, Chiosa, Piscitelli, Capozzoli, Hengel, Kührer, Pritoni, Liu, Clauß, Chen, Herr (b3) 2023; 339
Liang, Du (b14) 2007; 30
Li, Zou, Luo, Zhou, Cao, Liu (b24) 2022; 194
Kingma, Welling (b37) 2022
Yan, Zhou (b17) 2022; 8
Goodfellow (b32) 2017
K. Sohn, H. Lee, X. Yan, Learning Structured Output Representation Using Deep Conditional Generative Models.
Zhang, Xu, Chen, Xing (b27) 2023; 123
Han, Shao, Huo, Yang, Cheng (b22) 2022; 212
Li, Wen (b39) 2003
Han, Wang, Mao (b36) 2005; Vol. 3644
Xu, Lu, Jia, Jiang (b21) 2020; 31
Liang (10.1016/j.jobe.2024.109137_b14) 2007; 30
Xu (10.1016/j.jobe.2024.109137_b21) 2020; 31
Wang (10.1016/j.jobe.2024.109137_b28) 2020; 92
Tudoroiu (10.1016/j.jobe.2024.109137_b16) 2008
Shi (10.1016/j.jobe.2024.109137_b5) 2019; 104
Yan (10.1016/j.jobe.2024.109137_b26) 2021; 201
Goodfellow (10.1016/j.jobe.2024.109137_b32) 2017
Chen (10.1016/j.jobe.2024.109137_b3) 2023; 339
Zhang (10.1016/j.jobe.2024.109137_b23) 2023; 70
Gálvez (10.1016/j.jobe.2024.109137_b13) 2021; 13
10.1016/j.jobe.2024.109137_b29
Li (10.1016/j.jobe.2024.109137_b39) 2003
Han (10.1016/j.jobe.2024.109137_b36) 2005; Vol. 3644
Zhou (10.1016/j.jobe.2024.109137_b7) 2009; 33
Wang (10.1016/j.jobe.2024.109137_b2) 2019; 102
Chen (10.1016/j.jobe.2024.109137_b15) 2022; 161
De Oliveira (10.1016/j.jobe.2024.109137_b20) 2023
Kingma (10.1016/j.jobe.2024.109137_b37) 2022
Gupta (10.1016/j.jobe.2024.109137_b30) 2018; 32
Katipamula (10.1016/j.jobe.2024.109137_b6) 2005; 11
Zhao (10.1016/j.jobe.2024.109137_b4) 2020; 1
Zhang (10.1016/j.jobe.2024.109137_b18) 2021; 253
Zhang (10.1016/j.jobe.2024.109137_b35) 2022; 268
10.1016/j.jobe.2024.109137_b12
Zhang (10.1016/j.jobe.2024.109137_b19) 2022; 269
10.1016/j.jobe.2024.109137_b38
Zhang (10.1016/j.jobe.2024.109137_b27) 2023; 123
Du (10.1016/j.jobe.2024.109137_b10) 2014; 72
Lapisa (10.1016/j.jobe.2024.109137_b1) 2018; 132
Namburu (10.1016/j.jobe.2024.109137_b9) 2007; 4
Yan (10.1016/j.jobe.2024.109137_b17) 2022; 8
Zhong (10.1016/j.jobe.2024.109137_b33) 2019; 12
Salimans (10.1016/j.jobe.2024.109137_b31) 2016
Isermann (10.1016/j.jobe.2024.109137_b8) 2005
Li (10.1016/j.jobe.2024.109137_b24) 2022; 194
Goodfellow (10.1016/j.jobe.2024.109137_b25) 2014
Zhang (10.1016/j.jobe.2024.109137_b11) 2018
Yan (10.1016/j.jobe.2024.109137_b34) 2022; 19
Han (10.1016/j.jobe.2024.109137_b22) 2022; 212
References_xml – volume: 8
  start-page: 531
  year: 2022
  end-page: 539
  ident: b17
  article-title: Chiller faults detection and diagnosis with sensor network and adaptive 1D CNN
  publication-title: Digit. Commun. Netw.
– year: 2014
  ident: b25
  article-title: Generative Adversarial Networks
– reference: A. Razavi, Generating Diverse High-Fidelity Images with VQ-VAE-2.
– volume: 12
  start-page: 527
  year: 2019
  ident: b33
  article-title: Energy efficiency solutions for buildings: automated fault diagnosis of air handling units using generative adversarial networks
  publication-title: Energies
– year: 2023
  ident: b20
  article-title: A systematic review for class-imbalance in semi-supervised learning
  publication-title: Artif. Intell. Rev.
– volume: Vol. 3644
  start-page: 878
  year: 2005
  end-page: 887
  ident: b36
  article-title: Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning
  publication-title: Advances in Intelligent Computing
– volume: 19
  start-page: 387
  year: 2022
  end-page: 395
  ident: b34
  article-title: Chiller fault diagnosis based on VAE-enabled generative adversarial networks
  publication-title: IEEE Trans. Autom. Sci. Eng.
– year: 2003
  ident: b39
  article-title: Development and validation of a dynamic air handling unit model, part I
– year: 2022
  ident: b37
  article-title: Auto-encoding variational Bayes
– volume: 212
  year: 2022
  ident: b22
  article-title: End-to-end chiller fault diagnosis using fused attention mechanism and dynamic cross-entropy under imbalanced datasets
  publication-title: Build. Environ.
– year: 2016
  ident: b31
  article-title: Improved techniques for training GANs
– volume: 70
  year: 2023
  ident: b23
  article-title: Imbalanced data based fault diagnosis of the chiller via integrating a new resampling technique with an improved ensemble extreme learning machine
  publication-title: J. Build. Eng.
– volume: 339
  year: 2023
  ident: b3
  article-title: A review of data-driven fault detection and diagnostics for building HVAC systems
  publication-title: Appl. Energy
– year: 2005
  ident: b8
  article-title: Model-based fault-detection and diagnosis – status and applications
  publication-title: Annu. Rev. Control
– volume: 253
  year: 2021
  ident: b18
  article-title: Fault detection and diagnosis of the air handling unit via an enhanced kernel slow feature analysis approach considering the time-wise and batch-wise dynamics
  publication-title: Energy Build.
– volume: 72
  start-page: 157
  year: 2014
  end-page: 166
  ident: b10
  article-title: Sensor fault detection and its efficiency analysis in air handling unit using the combined neural networks
  publication-title: Energy Build.
– volume: 123
  year: 2023
  ident: b27
  article-title: A novel building heat pump system semi-supervised fault detection and diagnosis method under small and imbalanced data
  publication-title: Eng. Appl. Artif. Intell.
– volume: 102
  start-page: 159
  year: 2019
  end-page: 167
  ident: b2
  article-title: A practical chiller fault diagnosis method based on discrete Bayesian network
  publication-title: Int. J. Refrig.
– volume: 268
  year: 2022
  ident: b35
  article-title: Integrated generative networks embedded with ensemble classifiers for fault detection and diagnosis under small and imbalanced data of building air condition system
  publication-title: Energy Build.
– reference: A. Blum, T. Mitchell, Combining Labeled and Unlabeled Data with Co-Training y.
– volume: 92
  year: 2020
  ident: b28
  article-title: Imbalanced sample fault diagnosis of rotating machinery using conditional variational auto-encoder generative adversarial network
  publication-title: Appl. Soft Comput.
– volume: 132
  start-page: 83
  year: 2018
  end-page: 95
  ident: b1
  article-title: Optimized design of low-rise commercial buildings under various climates – Energy performance and passive cooling strategies
  publication-title: Build. Environ.
– volume: 269
  year: 2022
  ident: b19
  article-title: Fault detection and diagnosis of the air handling unit via combining the feature sparse representation based dynamic SFA and the LSTM network
  publication-title: Energy Build.
– volume: 32
  year: 2018
  ident: b30
  article-title: A deep generative framework for paraphrase generation
  publication-title: Proc. AAAI Conf. Artif. Intell.
– start-page: 334
  year: 2008
  end-page: 339
  ident: b16
  article-title: Fault detection and diagnosis (FDD) in heating ventilation air conditioning systems (HVAC) using an interactive multiple model augmented unscented Kalman filter (IMMAUKF)
  publication-title: 2008 Conference on Human System Interactions
– year: 2017
  ident: b32
  article-title: NIPS 2016 tutorial: generative adversarial networks
– volume: 161
  year: 2022
  ident: b15
  article-title: A review of computing-based automated fault detection and diagnosis of heating, ventilation and air conditioning systems
  publication-title: Renew. Sustain. Energy Rev.
– volume: 30
  start-page: 1104
  year: 2007
  end-page: 1114
  ident: b14
  article-title: Model-based fault detection and diagnosis of HVAC systems using support vector machine method
  publication-title: Int. J. Refrig.
– volume: 201
  year: 2021
  ident: b26
  article-title: Chiller fault detection and diagnosis with anomaly detective generative adversarial network
  publication-title: Build. Environ.
– reference: K. Sohn, H. Lee, X. Yan, Learning Structured Output Representation Using Deep Conditional Generative Models.
– volume: 1
  start-page: 149
  year: 2020
  end-page: 164
  ident: b4
  article-title: A review of data mining technologies in building energy systems: load prediction, pattern identification, fault detection and diagnosis
  publication-title: Energy Built Environ.
– year: 2018
  ident: b11
  article-title: Mixup: beyond empirical risk minimization
– volume: 13
  start-page: 6828
  year: 2021
  ident: b13
  article-title: Fault detection and RUL estimation for railway HVAC systems using a hybrid model-based approach
  publication-title: Sustainability
– volume: 33
  start-page: 903
  year: 2009
  end-page: 918
  ident: b7
  article-title: A model-based fault detection and diagnosis strategy for HVAC systems
  publication-title: Int. J. Energy Res.
– volume: 11
  start-page: 3
  year: 2005
  end-page: 25
  ident: b6
  article-title: Review article: methods for fault detection, diagnostics, and prognostics for building systems—A review, part I
  publication-title: HVAC&R Res.
– volume: 194
  year: 2022
  ident: b24
  article-title: A new generative adversarial network based imbalanced fault diagnosis method
  publication-title: Measurement
– volume: 104
  start-page: 215
  year: 2019
  end-page: 229
  ident: b5
  article-title: Development and implementation of automated fault detection and diagnostics for building systems: A review
  publication-title: Autom. Constr.
– volume: 4
  start-page: 469
  year: 2007
  end-page: 473
  ident: b9
  article-title: Data-driven modeling, fault diagnosis and optimal sensor selection for HVAC Chillers
  publication-title: IEEE Trans. Autom. Sci. Eng.
– volume: 31
  start-page: 1467
  year: 2020
  end-page: 1481
  ident: b21
  article-title: Imbalanced fault diagnosis of rotating machinery via multi-domain feature extraction and cost-sensitive learning
  publication-title: J. Intell. Manuf.
– volume: 268
  year: 2022
  ident: 10.1016/j.jobe.2024.109137_b35
  article-title: Integrated generative networks embedded with ensemble classifiers for fault detection and diagnosis under small and imbalanced data of building air condition system
  publication-title: Energy Build.
  doi: 10.1016/j.enbuild.2022.112207
– volume: 1
  start-page: 149
  issue: 2
  year: 2020
  ident: 10.1016/j.jobe.2024.109137_b4
  article-title: A review of data mining technologies in building energy systems: load prediction, pattern identification, fault detection and diagnosis
  publication-title: Energy Built Environ.
  doi: 10.1016/j.enbenv.2019.11.003
– year: 2018
  ident: 10.1016/j.jobe.2024.109137_b11
– volume: 30
  start-page: 1104
  issue: 6
  year: 2007
  ident: 10.1016/j.jobe.2024.109137_b14
  article-title: Model-based fault detection and diagnosis of HVAC systems using support vector machine method
  publication-title: Int. J. Refrig.
  doi: 10.1016/j.ijrefrig.2006.12.012
– volume: 339
  year: 2023
  ident: 10.1016/j.jobe.2024.109137_b3
  article-title: A review of data-driven fault detection and diagnostics for building HVAC systems
  publication-title: Appl. Energy
  doi: 10.1016/j.apenergy.2023.121030
– volume: 8
  start-page: 531
  issue: 4
  year: 2022
  ident: 10.1016/j.jobe.2024.109137_b17
  article-title: Chiller faults detection and diagnosis with sensor network and adaptive 1D CNN
  publication-title: Digit. Commun. Netw.
  doi: 10.1016/j.dcan.2022.03.023
– volume: 123
  year: 2023
  ident: 10.1016/j.jobe.2024.109137_b27
  article-title: A novel building heat pump system semi-supervised fault detection and diagnosis method under small and imbalanced data
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2023.106316
– volume: 13
  start-page: 6828
  issue: 12
  year: 2021
  ident: 10.1016/j.jobe.2024.109137_b13
  article-title: Fault detection and RUL estimation for railway HVAC systems using a hybrid model-based approach
  publication-title: Sustainability
  doi: 10.3390/su13126828
– volume: 132
  start-page: 83
  year: 2018
  ident: 10.1016/j.jobe.2024.109137_b1
  article-title: Optimized design of low-rise commercial buildings under various climates – Energy performance and passive cooling strategies
  publication-title: Build. Environ.
  doi: 10.1016/j.buildenv.2018.01.029
– volume: 92
  year: 2020
  ident: 10.1016/j.jobe.2024.109137_b28
  article-title: Imbalanced sample fault diagnosis of rotating machinery using conditional variational auto-encoder generative adversarial network
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2020.106333
– year: 2023
  ident: 10.1016/j.jobe.2024.109137_b20
  article-title: A systematic review for class-imbalance in semi-supervised learning
  publication-title: Artif. Intell. Rev.
  doi: 10.1007/s10462-023-10579-0
– volume: 70
  year: 2023
  ident: 10.1016/j.jobe.2024.109137_b23
  article-title: Imbalanced data based fault diagnosis of the chiller via integrating a new resampling technique with an improved ensemble extreme learning machine
  publication-title: J. Build. Eng.
– volume: 32
  issue: 1
  year: 2018
  ident: 10.1016/j.jobe.2024.109137_b30
  article-title: A deep generative framework for paraphrase generation
  publication-title: Proc. AAAI Conf. Artif. Intell.
– ident: 10.1016/j.jobe.2024.109137_b29
– year: 2003
  ident: 10.1016/j.jobe.2024.109137_b39
– volume: 269
  year: 2022
  ident: 10.1016/j.jobe.2024.109137_b19
  article-title: Fault detection and diagnosis of the air handling unit via combining the feature sparse representation based dynamic SFA and the LSTM network
  publication-title: Energy Build.
  doi: 10.1016/j.enbuild.2022.112241
– volume: 104
  start-page: 215
  year: 2019
  ident: 10.1016/j.jobe.2024.109137_b5
  article-title: Development and implementation of automated fault detection and diagnostics for building systems: A review
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2019.04.002
– volume: 212
  year: 2022
  ident: 10.1016/j.jobe.2024.109137_b22
  article-title: End-to-end chiller fault diagnosis using fused attention mechanism and dynamic cross-entropy under imbalanced datasets
  publication-title: Build. Environ.
  doi: 10.1016/j.buildenv.2022.108821
– year: 2022
  ident: 10.1016/j.jobe.2024.109137_b37
– volume: 102
  start-page: 159
  year: 2019
  ident: 10.1016/j.jobe.2024.109137_b2
  article-title: A practical chiller fault diagnosis method based on discrete Bayesian network
  publication-title: Int. J. Refrig.
  doi: 10.1016/j.ijrefrig.2019.03.008
– year: 2017
  ident: 10.1016/j.jobe.2024.109137_b32
– ident: 10.1016/j.jobe.2024.109137_b12
– volume: 31
  start-page: 1467
  issue: 6
  year: 2020
  ident: 10.1016/j.jobe.2024.109137_b21
  article-title: Imbalanced fault diagnosis of rotating machinery via multi-domain feature extraction and cost-sensitive learning
  publication-title: J. Intell. Manuf.
  doi: 10.1007/s10845-019-01522-8
– volume: 161
  year: 2022
  ident: 10.1016/j.jobe.2024.109137_b15
  article-title: A review of computing-based automated fault detection and diagnosis of heating, ventilation and air conditioning systems
  publication-title: Renew. Sustain. Energy Rev.
  doi: 10.1016/j.rser.2022.112395
– volume: 201
  year: 2021
  ident: 10.1016/j.jobe.2024.109137_b26
  article-title: Chiller fault detection and diagnosis with anomaly detective generative adversarial network
  publication-title: Build. Environ.
  doi: 10.1016/j.buildenv.2021.107982
– volume: 72
  start-page: 157
  year: 2014
  ident: 10.1016/j.jobe.2024.109137_b10
  article-title: Sensor fault detection and its efficiency analysis in air handling unit using the combined neural networks
  publication-title: Energy Build.
  doi: 10.1016/j.enbuild.2013.12.038
– volume: 253
  year: 2021
  ident: 10.1016/j.jobe.2024.109137_b18
  article-title: Fault detection and diagnosis of the air handling unit via an enhanced kernel slow feature analysis approach considering the time-wise and batch-wise dynamics
  publication-title: Energy Build.
  doi: 10.1016/j.enbuild.2021.111467
– volume: 19
  start-page: 387
  issue: 1
  year: 2022
  ident: 10.1016/j.jobe.2024.109137_b34
  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: 4
  start-page: 469
  issue: 3
  year: 2007
  ident: 10.1016/j.jobe.2024.109137_b9
  article-title: Data-driven modeling, fault diagnosis and optimal sensor selection for HVAC Chillers
  publication-title: IEEE Trans. Autom. Sci. Eng.
  doi: 10.1109/TASE.2006.888053
– year: 2014
  ident: 10.1016/j.jobe.2024.109137_b25
– volume: 11
  start-page: 3
  issue: 1
  year: 2005
  ident: 10.1016/j.jobe.2024.109137_b6
  article-title: Review article: methods for fault detection, diagnostics, and prognostics for building systems—A review, part I
  publication-title: HVAC&R Res.
  doi: 10.1080/10789669.2005.10391123
– year: 2005
  ident: 10.1016/j.jobe.2024.109137_b8
  article-title: Model-based fault-detection and diagnosis – status and applications
  publication-title: Annu. Rev. Control
  doi: 10.1016/j.arcontrol.2004.12.002
– year: 2016
  ident: 10.1016/j.jobe.2024.109137_b31
– volume: 12
  start-page: 527
  issue: 3
  year: 2019
  ident: 10.1016/j.jobe.2024.109137_b33
  article-title: Energy efficiency solutions for buildings: automated fault diagnosis of air handling units using generative adversarial networks
  publication-title: Energies
  doi: 10.3390/en12030527
– volume: 194
  year: 2022
  ident: 10.1016/j.jobe.2024.109137_b24
  article-title: A new generative adversarial network based imbalanced fault diagnosis method
  publication-title: Measurement
  doi: 10.1016/j.measurement.2022.111045
– ident: 10.1016/j.jobe.2024.109137_b38
– start-page: 334
  year: 2008
  ident: 10.1016/j.jobe.2024.109137_b16
  article-title: Fault detection and diagnosis (FDD) in heating ventilation air conditioning systems (HVAC) using an interactive multiple model augmented unscented Kalman filter (IMMAUKF)
– volume: Vol. 3644
  start-page: 878
  year: 2005
  ident: 10.1016/j.jobe.2024.109137_b36
  article-title: Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning
– volume: 33
  start-page: 903
  issue: 10
  year: 2009
  ident: 10.1016/j.jobe.2024.109137_b7
  article-title: A model-based fault detection and diagnosis strategy for HVAC systems
  publication-title: Int. J. Energy Res.
  doi: 10.1002/er.1530
SSID ssj0002953864
Score 2.3560116
Snippet Implementing efficient automatic fault diagnosis is critical for saving energy and minimizing financial losses in the heating ventilation air-conditioning...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 109137
SubjectTerms Chiller
Data augmentation
Fault diagnosis
Variational autoencoder
Title Chiller fault diagnosis based on improved variational autoencoder and co-training framework: A case study of insufficient samples
URI https://dx.doi.org/10.1016/j.jobe.2024.109137
Volume 88
WOSCitedRecordID wos001216950400001&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
  customDbUrl:
  eissn: 2352-7102
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002953864
  issn: 2352-7102
  databaseCode: AIEXJ
  dateStart: 20150301
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6FlAMXRAWI8tIeeotcrV9ZL7eAiiiPikNB4WSt9yElipwqtqNe-Q_8YGa8a8dUaUUPvVjWyB47ni-z4_HMN4QcT42ItdZxkGphgoRHSQCLoAxkypScJmkRtvNTfn7l5-fZfC6-j0Z_ul6Y7YqXZXZ1JS7v1dQgA2Nj6-wdzN0rBQHsg9FhC2aH7X8ZHsmKV2YzsbJZ1ZhbxVK6RTXB9Urjt4FFm0eA_S28J3e5QNnUa-S0RGoJ1-oWdNMjJrYr4HJt7AoUOVpaxzdRNS0NBRYVVBLJhqsbIt73fgT3kASxLwhq3Md_sxN9a-PaOeC3F_1y6dovZpisAMN3ha3ep0UQ72H5p3PAZo_MO2U368971Za8lO91-C73sDxZYu8UXvFkd_C_7NrXVr2-FrErc1vmqCNHHbnT8YAcRDwV2ZgczM5O55_73F0kYJlomcn6e_f9WK508PrN7I95BnHMxRPy2JuDzhxwDsnIlE_Jbw8a2oKG9qChLWjouqQdaOgANHQAGgqgoQPQ0B407-iMImRoCxm6tnQIGeoh84z8-Hh68eFT4IdzBCpmrA5CY4tY8UgXsdRpgaxQNhPMTEXBMp5YFlsVK8WsVoyLIkJ6ryJhiqmsyHSo4-dkXK5L84JQeKsQEBmHRvAsgQVH2kTbUMIjNtOkMPKIhN3jy5Vnrsdfs8pvtt0RmfTnXDrelluPTjur5D7ydBFlDji75byXd7rKK_Jo9594Tcb1pjFvyEO1rRfV5q0H2V8sI6cG
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=Chiller+fault+diagnosis+based+on+improved+variational+autoencoder+and+co-training+framework%3A+A+case+study+of+insufficient+samples&rft.jtitle=Journal+of+Building+Engineering&rft.au=Lu%2C+Cheng&rft.au=Ma%2C+Xiang&rft.au=Yan%2C+Ke&rft.date=2024-07-01&rft.issn=2352-7102&rft.eissn=2352-7102&rft.volume=88&rft.spage=109137&rft_id=info:doi/10.1016%2Fj.jobe.2024.109137&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_jobe_2024_109137
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2352-7102&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2352-7102&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2352-7102&client=summon