{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T00:02:59Z","timestamp":1768694579024,"version":"3.49.0"},"reference-count":34,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Research Foundation of Korea (NRF)","award":["RS-2022-00144000"],"award-info":[{"award-number":["RS-2022-00144000"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["RS-2022-00165225"],"award-info":[{"award-number":["RS-2022-00165225"]}]},{"DOI":"10.13039\/501100003725","name":"Korean government (Ministry of Science and ICT, MIST)","doi-asserted-by":"publisher","award":["RS-2022-00144000"],"award-info":[{"award-number":["RS-2022-00144000"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"Korean government (Ministry of Science and ICT, MIST)","doi-asserted-by":"publisher","award":["RS-2022-00165225"],"award-info":[{"award-number":["RS-2022-00165225"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Anomaly detection systems based on artificial intelligence (AI) have demonstrated high performance and efficiency in a wide range of applications such as power plants and smart factories. However, due to the inherent reliance of AI systems on the quality of training data, they still demonstrate poor performance in certain environments. Especially in hazardous facilities with constrained data collection, deploying these systems remains a challenge. In this paper, we propose Generative Anomaly Detection using Prototypical Networks (GAD-PN) designed to detect anomalies using only a limited number of normal samples. GAD-PN is a structure that integrates CycleGAN with Prototypical Networks (PNs), learning from metadata similar to the target environment. This approach enables the collection of data that are difficult to gather in real-world environments by using simulation or demonstration models, thus providing opportunities to learn a variety of environmental parameters under ideal and normal conditions. During the inference phase, PNs can classify normal and leak samples using only a small number of normal data from the target environment by prototypes that represent normal and abnormal features. We also complement the challenge of collecting anomaly data by generating anomaly data from normal data using CycleGAN trained on anomaly features. It can also be adapted to various environments that have similar anomalous scenarios, regardless of differences in environmental parameters. To validate the proposed structure, data were collected specifically targeting pipe leakage scenarios, which are significant problems in environments such as power plants. In addition, acoustic ultrasound signals were collected from the pipe nozzles in three different environments. As a result, the proposed model achieved a leak detection accuracy of over 90% in all environments, even with only a small number of normal data. This performance shows an average improvement of approximately 30% compared with traditional unsupervised learning models trained with a limited dataset.<\/jats:p>","DOI":"10.3390\/s24154991","type":"journal-article","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T18:04:59Z","timestamp":1722535499000},"page":"4991","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Leak Event Diagnosis for Power Plants: Generative Anomaly Detection Using Prototypical Networks"],"prefix":"10.3390","volume":"24","author":[{"given":"Jaehyeok","family":"Jeong","sequence":"first","affiliation":[{"name":"Department of Electronic Information System Engineering, Sangmyung University, Cheonan 31066, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6510-8763","authenticated-orcid":false,"given":"Doyeob","family":"Yeo","sequence":"additional","affiliation":[{"name":"Nuclear System Integrity Sensing and Diagnosis Division, Korea Atomic Energy Research Institute, Daejeon 34057, Republic of Korea"}]},{"given":"Seungseo","family":"Roh","sequence":"additional","affiliation":[{"name":"Department of Human Intelligence and Robot Engineering, Sangmyung University, Cheonan 31066, Republic of Korea"}]},{"given":"Yujin","family":"Jo","sequence":"additional","affiliation":[{"name":"Department of Human Intelligence and Robot Engineering, Sangmyung University, Cheonan 31066, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4519-1683","authenticated-orcid":false,"given":"Minsuk","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Human Intelligence and Robot Engineering, Sangmyung University, Cheonan 31066, Republic of Korea"}]}],"member":"1968","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3439950","article-title":"Deep learning for anomaly detection: A review","volume":"54","author":"Pang","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"040801","DOI":"10.1115\/1.4049535","article-title":"Image-based surface defect detection using deep learning: A review","volume":"21","author":"Bhatt","year":"2021","journal-title":"J. Comput. Inf. Sci. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"78658","DOI":"10.1109\/ACCESS.2021.3083060","article-title":"Machine learning for anomaly detection: A systematic review","volume":"21","author":"Nassif","year":"2021","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e3070","DOI":"10.1002\/stc.3070","article-title":"Towards probabilistic data-driven damage detection in SHM using sparse Bayesian learning scheme","volume":"29","author":"Wang","year":"2022","journal-title":"Struct. Control Health Monit."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"114509","DOI":"10.1016\/j.measurement.2024.114509","article-title":"Data interpretation and forecasting of SHM heteroscedastic measurements under typhoon conditions enabled by an enhanced Hierarchical sparse Bayesian Learning model with high robustness","volume":"230","author":"Wang","year":"2024","journal-title":"Measurement"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"108785","DOI":"10.1016\/j.anucene.2021.108785","article-title":"Research on anomaly detection method of nuclear power plant operation state based on unsupervised deep generative model","volume":"167","author":"Li","year":"2022","journal-title":"Ann. Nucl. Energy"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1016\/j.psep.2022.05.039","article-title":"Robust deep auto-encoding network for real-time anomaly detection at nuclear power plants","volume":"163","author":"Yong","year":"2022","journal-title":"Process Saf. Environ. Prot."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"103928","DOI":"10.1016\/j.pnucene.2021.103928","article-title":"Abnormal event detection, identification and isolation in nuclear power plants using LSTM networks","volume":"140","author":"Wang","year":"2021","journal-title":"Prog. Nucl. Energy"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhang, S., Ye, F., Wang, B., and Habetler, T. (2020, January 24\u201327). Few-Shot Bearing Anomaly detection via model-agnostic meta-learning. Proceedings of the International Conference on Electrical Machines and Systems (ICEMS), Hamamatsu, Japan.","DOI":"10.23919\/ICEMS50442.2020.9291099"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Feng, T., Qi, Q., Wang, J., and Liao, J. (2021, January 21\u201324). Few-shot class-adaptive anomaly detection with model-agnostic meta-learning. Proceedings of the IFIP Networking Conference, Espoo and Helsinki, Finland.","DOI":"10.23919\/IFIPNetworking52078.2021.9472814"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"4483","DOI":"10.1007\/s10462-021-10004-4","article-title":"A survey of deep meta-learning","volume":"54","author":"Huisman","year":"2021","journal-title":"Artif. Intell. Rev."},{"key":"ref_12","unstructured":"Finn, C., Abbeel, P., and Levine, S. (2017, January 6\u201311). Model-agnostic meta-learning for fast adaptation of deep networks. Proceedings of the International Conference on Machine Learning (ICML), Sydney, Australia."},{"key":"ref_13","unstructured":"Snell, J., Swersky, K., and Zemel, R. (2017, January 4\u20139). Prototypical networks for few-shot learning. Proceedings of the Advances in Neural Information Processing Systems (NIPS), Long Beach, CA, USA."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22\u201329). Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. Proceedings of the IEEE Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Roth, K., Pemula, L., Zepeda, J., Sch\u00f6lkopf, B., Brox, T., and Gehler, P. (2022). Towards total recall in industrial anomaly detection. arXiv.","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"ref_16","unstructured":"Cohen, N., and Hoshen, Y. (2020). Sub-image anomaly detection with deep pyramid correspondences. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Defard, T., Setkov, A., Loesch, A., and Audigier, R. (2020). Padim: A patch distribution modeling framework for anomaly detection and localization. arXiv.","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"ref_18","unstructured":"Rabino, P., Alliegro, A., Borlino, F.C., and Tommasi, T. (2023). OpenPatch: A 3D patchwork for Out-of-Distribution detection. arXiv."},{"key":"ref_19","unstructured":"Mousakhan, A., Brox, T., and Tayyub, J. (2023). Anomaly detection with conditioned denoising diffusion models. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., and Steger, C. (2019, January 15\u201320). MVTec AD\u2014A comprehensive real-world dataset for unsupervised anomaly detection. Proceedings of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"106099","DOI":"10.1016\/j.jobe.2023.106099","article-title":"Anomaly detection using a model-agnostic meta-learning-based variational auto-encoder for facility management","volume":"68","author":"Moon","year":"2023","journal-title":"J. Build. Eng."},{"key":"ref_22","unstructured":"Kingma, D.P., and Welling, M. (2014, January 14\u201316). Auto-encoding variational bayes. Proceedings of the International Conference on Learning Representations (ICLR), Banff, AB, Canada."},{"key":"ref_23","unstructured":"Sun, H., Huang, Y., Han, L., and Zhou, C. (2023). Few-shot detection of anomalies in industrial cyber-physical system via prototypical network and contrastive learning. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wu, Z., Wang, Z., Chen, Z., and Jiang, Y.G. (2023, January 18\u201322). Prototypical residual networks for anomaly detection and localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01562"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3787","DOI":"10.1109\/JSEN.2022.3230361","article-title":"LSTM-Autoencoder-based anomaly detection for indoor air quality time-series data","volume":"23","author":"Wei","year":"2023","journal-title":"IEEE Sens. J."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Apostol, E.-S., Truic\u0103, C.-O., Pop, F., and Esposito, C. (2021). Change point enhanced anomaly detection for IoT time series data. Water, 13.","DOI":"10.3390\/w13121633"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"giad060","DOI":"10.1093\/gigascience\/giad060","article-title":"Health record hiccups\u20145526 real-world time series with change points labelled by crowdsourced visual inspection","volume":"12","author":"Quan","year":"2021","journal-title":"GigaScience"},{"key":"ref_28","first-page":"171","article-title":"Automated detection of myocardial infarction using a gramian angular field and principal component analysis network","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"016607","DOI":"10.1063\/5.0187614","article-title":"Swin transformer-based fluid classification using gram angle field-converted well logging data: A novel approach","volume":"36","author":"Sun","year":"2024","journal-title":"Phys. Fluids"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3001","DOI":"10.1007\/s10845-022-01981-6","article-title":"Deep generative model with time series-image encoding for manufacturing fault detection in die casting process","volume":"34","author":"Song","year":"2023","journal-title":"J. Intell. Manuf."},{"key":"ref_31","unstructured":"(2018). Standard Practice for Leaks Using Ultrasonics (Standard No. ASTM E1002-11)."},{"key":"ref_32","first-page":"59","article-title":"Pipe leak detection system using wireless acoustic sensor module and deep auto-encoder","volume":"25","author":"Yeo","year":"2020","journal-title":"J. Korea Soc. Comput. Inf."},{"key":"ref_33","first-page":"1","article-title":"Convolutional neural networks are not invariant to translation, but they can learn to be","volume":"22","author":"Biscione","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"333","DOI":"10.21595\/jme.2024.23829","article-title":"Enhancing non-destructive testing in concrete structures: A GADF-CNN approach for defect detection","volume":"12","author":"Feng","year":"2024","journal-title":"J. Meas. Eng."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/15\/4991\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:28:33Z","timestamp":1760110113000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/15\/4991"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,1]]},"references-count":34,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["s24154991"],"URL":"https:\/\/doi.org\/10.3390\/s24154991","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,1]]}}}