{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:10:01Z","timestamp":1772831401424,"version":"3.50.1"},"reference-count":36,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2022,4,23]],"date-time":"2022-04-23T00:00:00Z","timestamp":1650672000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1733201"],"award-info":[{"award-number":["U1733201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1933202"],"award-info":[{"award-number":["U1933202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Quality &amp; Reliability Eng"],"published-print":{"date-parts":[[2022,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Anomaly detection of gas turbines is a typical binary classification problem under small sample size. In essence, the goal of classification is to discover the mapping that can map samples in different categories to disjoint codomains. The neural network has strong nonlinear mapping ability thus it has great potentialities in classification tasks. However, how to design the architecture of the neural network is still a challenging problem. The inappropriate network architecture might cause either overfitting or underfitting problems. To alleviate the problem, this paper presents an effective anomaly detection model for gas turbines by combining the convolutional auto\u2010encoder (CAE) and weight agnostic neural network (WANN) search. More specifically, the CAE is used for the search space extension by obtaining high\u2010dimensional latent representations of the raw data. Then, the WANN search finds a suitable neural network architecture for anomaly detection in the extended search space. Moreover, a novel method based on maximum likelihood estimation is proposed for threshold selection, which is also effective in the case of unbalanced datasets. In the end, the real\u2010life monitoring data of gas turbines validate the effectiveness of the presented anomaly detection\u00a0model.<\/jats:p>","DOI":"10.1002\/qre.3113","type":"journal-article","created":{"date-parts":[[2022,4,23]],"date-time":"2022-04-23T16:38:20Z","timestamp":1650731900000},"page":"3116-3134","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["CAE\u2010WANN: A novel anomaly detection method for gas turbines via search space extension"],"prefix":"10.1002","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5622-9953","authenticated-orcid":false,"given":"Shisheng","family":"Zhong","sequence":"first","affiliation":[{"name":"School of Mechatronics Engineering Harbin Institute of Technology Harbin China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5095-5217","authenticated-orcid":false,"given":"Dan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mechatronics Engineering Harbin Institute of Technology Harbin China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9525-1168","authenticated-orcid":false,"given":"Lin","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Mechatronics Engineering Harbin Institute of Technology Harbin China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3342-1840","authenticated-orcid":false,"given":"Minghang","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Ocean Engineering Harbin Institute of Technology at Weihai Weihai China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2827-3927","authenticated-orcid":false,"given":"Xuyun","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Ocean Engineering Harbin Institute of Technology at Weihai Weihai China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8794-5709","authenticated-orcid":false,"given":"Feng","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Mechatronics Engineering Harbin Institute of Technology Harbin China"}]}],"member":"311","published-online":{"date-parts":[[2022,4,23]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"crossref","unstructured":"LiuD ZhongS LinL et\u00a0al.A novel performance prediction method for gas turbines using the prophet model. In:IEEE.Proceedings of the 2021 IEEE International Conference on Sensing Diagnostics Prognostics and Control (SDPC).IEEE;2021:203\u2013208.","DOI":"10.1109\/SDPC52933.2021.9563516"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.06.050"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2019.106547"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/qre.2068"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1504\/IJMIC.2013.057137"},{"key":"e_1_2_8_7_1","unstructured":"YuL ClearyDJ CuddihyPE.A novel approach to aircraft engine anomaly detection and diagnostics. In:Proceedings of the 2004 IEEE Aerospace Conference Proceedings.IEEE;2004:3468\u20133475."},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2010.10.028"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.4642"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/qre.2538"},{"key":"e_1_2_8_11_1","doi-asserted-by":"crossref","unstructured":"ZhongS LiuD LinL ZhaoM FuX GuoF.A novel anomaly detection method for gas turbines using weight agnostic neural network search. In:Proceedings of the 2020 Asia\u2010Pacific International Symposium on Advanced Reliability and Maintenance Modeling (APARM).IEEE;2020:1\u20136.","DOI":"10.1109\/APARM49247.2020.9209368"},{"key":"e_1_2_8_12_1","doi-asserted-by":"crossref","unstructured":"FuX ChenH ZhangG TaoT.A new point anomaly detection method about aeroengine based on deep learning. In:Proceedings of the 2018 International Conference on Sensing Diagnostics Prognostics and Control (SDPC).IEEE;2018:176\u2013181.","DOI":"10.1109\/SDPC.2018.8664977"},{"key":"e_1_2_8_13_1","doi-asserted-by":"crossref","unstructured":"BrothertonT JohnsonT.Anomaly detection for advanced military aircraft using neural networks. In:Proceedings of the 2001 IEEE Aerospace Conference Proceedings.IEEE;2001:3113\u20133123.","DOI":"10.1109\/AERO.2001.931329"},{"key":"e_1_2_8_14_1","doi-asserted-by":"crossref","unstructured":"LeeH LiG RaiA ChattopadhyayA.Health monitoring framework for aircraft engine system using deep neural network. In:No. 1. Proceedings of the Annual Conference of the PHM Society.2019.","DOI":"10.36001\/phmconf.2019.v11i1.869"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.2514\/1.B36267"},{"key":"e_1_2_8_16_1","doi-asserted-by":"crossref","unstructured":"YuanM WuY LinL.Fault diagnosis and remaining useful life estimation of aero engine using LSTM neural network. In:Proceedings of the 2016 IEEE International Conference on Aircraft Utility Systems (AUS).2016:135\u2013140.","DOI":"10.1109\/AUS.2016.7748035"},{"key":"e_1_2_8_17_1","doi-asserted-by":"crossref","unstructured":"XieL WangJ WeiZ WangM TianQ.DisturbLabel: regularizing CNN on the loss layer. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:4753\u20134762.","DOI":"10.1109\/CVPR.2016.514"},{"key":"e_1_2_8_18_1","unstructured":"MerityS KeskarNS SocherR.Regularizing and optimizing LSTM language models. In: International Conference on Learning Representations.2018."},{"key":"e_1_2_8_19_1","unstructured":"CogswellM AhmedF GirshickR ZitnickL BatraD.Reducing overfitting in deep networks by decorrelating representations. In: International Conference on Learning Representations 2016."},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2019.01.022"},{"key":"e_1_2_8_21_1","unstructured":"SoD LeQ LiangC.The evolved transformer. In: International Conference on Machine Learning.2019:5877\u20135886."},{"key":"e_1_2_8_22_1","unstructured":"ZophB LeQV.Neural architecture search with reinforcement learning. In: International Conference on Learning Representations.2017."},{"key":"e_1_2_8_23_1","unstructured":"GaierA HaD.Weight agnostic neural networks. In:Proceedings of the Advances in Neural Information Processing Systems.2019:5364\u20135378."},{"key":"e_1_2_8_24_1","unstructured":"ElskenT MetzenJH HutterF.Neural architecture search: a survey.The Journal of Machine Learning Research2019:1997\u20132017."},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"RanzatoM HuangFJ BoureauYL LeCunY.Unsupervised learning of invariant feature hierarchies with applications to object recognition. In:Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition.IEEE;2007:1\u20138.","DOI":"10.1109\/CVPR.2007.383157"},{"key":"e_1_2_8_26_1","doi-asserted-by":"crossref","unstructured":"MasciJ MeierU CireanD SchmidhuberJ.Stacked convolutional auto\u2010encoders for hierarchical feature extraction. In:Proceedings of the International Conference on Artificial Neural Networks.Springer;2011:52\u201359.","DOI":"10.1007\/978-3-642-21735-7_7"},{"key":"e_1_2_8_27_1","doi-asserted-by":"crossref","unstructured":"TurchenkoV LuczakA.Creation of a deep convolutional auto\u2010encoder in caffe. In:Proceedings of the 2017 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS).IEEE;2017:651\u2013659.","DOI":"10.1109\/IDAACS.2017.8095172"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0069178"},{"key":"e_1_2_8_29_1","unstructured":"RadfordA MetzL ChintalaS.Unsupervised representation learning with deep convolutional generative adversarial networks.2015. arXiv:1511.06434."},{"key":"e_1_2_8_30_1","doi-asserted-by":"crossref","unstructured":"IsolaP ZhuJY ZhouT EfrosAA.Image\u2010to\u2010image translation with conditional adversarial networks. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1125\u20131134.","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"e_1_2_8_32_1","unstructured":"ProvostF.Machine learning from imbalanced data sets 101. In:Proceedings of the AAAI 2000 Workshop on Imbalanced Data Sets.AAAI Press;2000:1\u20133."},{"key":"e_1_2_8_33_1","doi-asserted-by":"crossref","unstructured":"WuK ZhongS FuX WeiC.An aeroengine gas path anomaly detection method in the case of sample imbalance. In:Proceedings of the 2019 Prognostics and System Health Management Conference (PHM\u2010Qingdao).2019:1\u20136.","DOI":"10.1109\/PHM-Qingdao46334.2019.8943051"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2006.17"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.08.035"},{"key":"e_1_2_8_36_1","unstructured":"LingCX HuangJ ZhangH.AUC: a statistically consistent and more discriminating measure than accuracy. In:Proceedings of the IJCAI.2003:519\u2013524."},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1951.10500769"}],"container-title":["Quality and Reliability Engineering International"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/qre.3113","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/qre.3113","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/qre.3113","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T20:55:48Z","timestamp":1727038548000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/qre.3113"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,23]]},"references-count":36,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["10.1002\/qre.3113"],"URL":"https:\/\/doi.org\/10.1002\/qre.3113","archive":["Portico"],"relation":{},"ISSN":["0748-8017","1099-1638"],"issn-type":[{"value":"0748-8017","type":"print"},{"value":"1099-1638","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,23]]},"assertion":[{"value":"2020-11-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-03","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}