{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T12:54:05Z","timestamp":1779886445702,"version":"3.53.1"},"reference-count":28,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>As the core refrigeration equipment in cooling systems, the operational state of chiller units is crucial for ship support, equipment cooling, and mission stability. However, because of their sensitivity and the complexity of operating environments, obtaining large volumes of complete, fault-labeled data is difficult in practical engineering appli-cations. This limitation makes it challenging for traditional data-driven approaches to deliver accurate fault diagnoses. Furthermore, data collected from different devices or under varying operating conditions often differ significantly in both feature dimensions and distributions, i.e., data heterogeneity, which further complicates model transfer. To address these challenges, this study proposes a deep transfer learning\u2013based fault di-agnosis method designed to leverage abundant knowledge from the source domain while adaptively learning features of the target domain. Given the persistent difficulties in collecting sufficient high-quality labeled fault data, traditional data-driven models continue to face restricted diagnostic performance on target equipment. At the same time, data heterogeneity across devices or operating conditions intensifies the challenge of cross-domain knowledge transfer. To overcome these issues, this study develops a heterogeneous transfer learning method that integrates a dual-channel autoencoder, domain adversarial training, and pseudo-label self-training. This combination enables precise small-sample knowledge transfer from the source to the target domain. Specifi-cally, the dual-channel autoencoder is first applied to align heterogeneous feature di-mensions. Then, a Gradient Reversal Layer (GRL) and a domain discriminator are in-troduced to extract domain-invariant features. In parallel, high-confidence pseu-do-labeled samples from the target domain are incorporated into joint training to im-prove generalization and robustness. Experimental results confirm that the method achieves high fault diagnosis accuracy in typical industrial application scenarios, ena-bling effective identification of common faults in various types of chiller units under conventional operating conditions, the proposed method achieves higher accuracy and F1-scores in multi-class fault diagnosis tasks compared with both traditional approaches and existing transfer learning methods. These findings provide a novel perspective for advancing the intelligent operation and maintenance of chiller units.<\/jats:p>","DOI":"10.3390\/e27101049","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:54:31Z","timestamp":1760028871000},"page":"1049","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Study on a Fault Diagnosis Method for Heterogeneous Chiller Units Based on Transfer Learning"],"prefix":"10.3390","volume":"27","author":[{"given":"Qiaolian","family":"Feng","sequence":"first","affiliation":[{"name":"College of Power Engineering, Naval University of Engineering, Wuhan 430030, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongbao","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Power Engineering, Naval University of Engineering, Wuhan 430030, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfei","family":"Li","sequence":"additional","affiliation":[{"name":"College of Power Engineering, Naval University of Engineering, Wuhan 430030, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanghui","family":"Chang","sequence":"additional","affiliation":[{"name":"College of Power Engineering, Naval University of Engineering, Wuhan 430030, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Liang","sequence":"additional","affiliation":[{"name":"College of Power Engineering, Naval University of Engineering, Wuhan 430030, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongsheng","family":"Su","sequence":"additional","affiliation":[{"name":"College of Power Engineering, Naval University of Engineering, Wuhan 430030, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gelin","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Mechatronics Engineering, Wuhan University of Technology, Wuhan 430070, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"115632","DOI":"10.1016\/j.enbuild.2025.115632","article-title":"Transfer learning on transformers for building energy consumption forecasting, A comparative study","volume":"336","author":"Spencer","year":"2025","journal-title":"Energy Build."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"128019","DOI":"10.1016\/j.energy.2023.128019","article-title":"Novel data-pulling-based strategy for chiller fault diagnosis in data-scarce scenarios","volume":"279","author":"Ren","year":"2023","journal-title":"Energy"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"110885","DOI":"10.1016\/j.buildenv.2023.110885","article-title":"Automated fault detection and diagnosis of chiller water plants based on convolutional neural network and knowledge distillation","volume":"245","author":"Gao","year":"2023","journal-title":"Build. Environ."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"136832","DOI":"10.1016\/j.energy.2025.136832","article-title":"Variable-condition fault diagnosis for building chiller based on deep feature extraction and discrepancy minimization","volume":"330","author":"Han","year":"2025","journal-title":"Energy"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"114548","DOI":"10.1016\/j.enbuild.2024.114548","article-title":"Ensemble learning based multi-fault diagnosis of air conditioning system","volume":"319","author":"You","year":"2024","journal-title":"Energy Build."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3963","DOI":"10.1016\/j.applthermaleng.2011.07.047","article-title":"A fault detection and diagnosis strategy with enhanced sensitivity for centrifugal chillers","volume":"31","author":"Xiao","year":"2011","journal-title":"Appl. Therm. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.enbuild.2012.05.018","article-title":"A virtual condenser fouling sensor for chillers","volume":"52","author":"Zhao","year":"2012","journal-title":"Energy Build."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"110492","DOI":"10.1016\/j.enbuild.2020.110492","article-title":"Fault detection and diagnosis of large-scale HVAC systems in buildings using data-driven methods: A comprehensive review","volume":"229","author":"Mirnaghi","year":"2020","journal-title":"Energy Build."},{"key":"ref_9","first-page":"285","article-title":"Fault Diagnosis of Chiller Units Based on Consistency-Loss Generative Adversarial Network","volume":"46","author":"Gao","year":"2025","journal-title":"Chin. J. Sci. Instrum."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"110233","DOI":"10.1016\/j.engappai.2025.110233","article-title":"Non-parametric semi-supervised chiller fault diagnosis via variational compressor under severe few labeled samples","volume":"146","author":"Han","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_11","first-page":"1","article-title":"Fault diagnosis of rolling bearings based on a multi-source domain adaptive residual network","volume":"7","author":"Gao","year":"2024","journal-title":"J. Vib. Shock."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"102043","DOI":"10.1016\/j.jobe.2020.102043","article-title":"Fault diagnosis for building chillers based on data self-production and deep convolutional neural network","volume":"34","author":"Gao","year":"2021","journal-title":"J. Build. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"109137","DOI":"10.1016\/j.jobe.2024.109137","article-title":"Chiller fault diagnosis based on improved variational autoencoder and co-training framework: A case study of insufficient samples","volume":"88","author":"Lu","year":"2024","journal-title":"J. Build. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"107957","DOI":"10.1016\/j.buildenv.2021.107957","article-title":"Transfer learning based methodology for migration and application of fault detection and diagnosis between building chillers for improving energy efficiency","volume":"200","author":"Zhu","year":"2021","journal-title":"Build. Environ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"105522","DOI":"10.1016\/j.engappai.2022.105522","article-title":"Transfer learning based fault diagnosis of automobile dry clutch system","volume":"117","author":"Chakrapani","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"129322","DOI":"10.1016\/j.neucom.2024.129322","article-title":"A comprehensive survey of transfer dictionary learning","volume":"623","author":"Li","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"112324","DOI":"10.1016\/j.asoc.2024.112324","article-title":"Novel imbalanced multi-class fault diagnosis method using transfer learning and oversampling strategies-based multi-layer support vector machines (ML-SVMs)","volume":"167","author":"Wei","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"109740","DOI":"10.1016\/j.engappai.2024.109740","article-title":"A heterogeneous transfer learning method for fault prediction of railway track circuit","volume":"140","author":"Na","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"103472","DOI":"10.1016\/j.aei.2025.103472","article-title":"Hierarchical pseudo-label co-calibration with prototypical decision boundary optimization for mechanical fault diagnosis in label-scarce scenarios","volume":"67","author":"Li","year":"2025","journal-title":"Adv. Eng. Inform."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"103540","DOI":"10.1016\/j.aei.2025.103540","article-title":"Domain knowledge guided pseudo-label generation framework for semi-supervised domain generalization fault diagnosis","volume":"67","author":"Wei","year":"2025","journal-title":"Adv. Eng. Inform."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/j.isatra.2024.08.012","article-title":"Multi-source subdomain negative transfer suppression and multiple pseudo-labels guidance alignment: A method for fault diagnosis under cross-working conditions","volume":"154","author":"Chen","year":"2024","journal-title":"ISA Trans."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1177\/14759217241249656","article-title":"Interpretable domain adaptation transformer: A transfer learning method for fault diagnosis of rotating machinery","volume":"24","author":"Liu","year":"2024","journal-title":"Struct. Health Monit."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/s40430-024-05224-y","article-title":"An unsupervised transfer learning gear fault diagnosis method based on parameter-optimized VMD and residual attention networks","volume":"46","author":"Ma","year":"2024","journal-title":"J. Braz. Soc. Mech. Sci. Eng."},{"key":"ref_24","first-page":"12361","article-title":"A new bearing fault diagnosis method using elastic net transfer learning and LSTM","volume":"40","author":"Song","year":"2021","journal-title":"J. Intell. Fuzzy Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"111057","DOI":"10.1016\/j.ress.2025.111057","article-title":"DG-Softmax: A new domain generalization intelligent fault diagnosis method for planetary gearboxes","volume":"260","author":"Qian","year":"2025","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"101682","DOI":"10.1016\/j.aei.2022.101682","article-title":"Remaining useful life prediction of bearings by a new reinforced memory GRU network","volume":"53","author":"Zhou","year":"2022","journal-title":"Adv. Eng. Inform."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"111837","DOI":"10.1016\/j.ymssp.2024.111837","article-title":"Federated transfer learning for machinery fault diagnosis: A comprehensive review of technique and application","volume":"223","author":"Qian","year":"2025","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_28","first-page":"3556919","article-title":"Remaining useful life prediction methodologies with health indicator dependence for rotating machinery: A comprehensive review","volume":"74","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/10\/1049\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T08:10:36Z","timestamp":1760343036000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/10\/1049"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":28,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["e27101049"],"URL":"https:\/\/doi.org\/10.3390\/e27101049","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,9]]}}}