{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T05:01:14Z","timestamp":1767157274655,"version":"build-2238731810"},"reference-count":19,"publisher":"AIP Publishing","issue":"5","funder":[{"name":"Fundamental Research Funds for Universities of Henan Province","award":["NSFRF210305"],"award-info":[{"award-number":["NSFRF210305"]}]},{"name":"Scientific and Technological Research Projects in Henan Province","award":["222102210274"],"award-info":[{"award-number":["222102210274"]}]},{"name":"Scientific and Technological Research Projects in Henan Province","award":["232102210092"],"award-info":[{"award-number":["232102210092"]}]}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,1]]},"abstract":"<jats:p>Deep network fault diagnosis methods heavily rely on abundant labeled data for effective model training. However, small-sized samples and imbalanced samples often lead to insufficient features, resulting in accuracy degradation and even instability in the diagnosis model. To address this challenge, this paper introduces a coupled adversarial autoencoder (CoAAE) based on the Bayesian method. This model aims to solve the issue of insufficient samples by generating fake samples and integrating them with the original ones. Within the CoAAE framework, the probability density distribution of the original data is captured using an encoder and fake samples are generated by random sampling from this distribution and decoding them. This process is the adversarial interaction between the encoder and a classifier to obtain the prior distribution of the encoder\u2019s parameters. The encoder\u2019s parameters are updated through the decoder\u2019s reconstruction process, leading to the posterior distribution. Concurrently, the decoder is trained to enhance its ability to reconstruct samples accurately. To address the imbalance in the original samples, a parallel coupled network is employed. This network shares the weights of the extraction layer in the encoder, enabling it to learn the joint distribution between fault-related and normal samples. To evaluate the effectiveness of the proposed data augmentation method, experiments were conducted on a bearing database from Case Western Reserve University using ResNet18 as the deep learning diagnosis model representative. The results demonstrate that CoAAE can effectively augment imbalanced datasets and outperform other advanced methods.<\/jats:p>","DOI":"10.1063\/5.0193162","type":"journal-article","created":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T18:09:08Z","timestamp":1715105348000},"update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":1,"title":["Deep network fault diagnosis for imbalanced small-sized samples via a coupled adversarial autoencoder based on the Bayesian method"],"prefix":"10.1063","volume":"95","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0467-8946","authenticated-orcid":false,"given":"Xinliang","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Automation, Henan International Joint Laboratory of Direct Drive and Control of Intelligent Equipment, Henan Polytechnic University 1 , Jiaozuo 454003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7922-4774","authenticated-orcid":false,"given":"Yanqi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Automation, Henan International Joint Laboratory of Direct Drive and Control of Intelligent Equipment, Henan Polytechnic University 1 , Jiaozuo 454003, China"},{"name":"Anhui Institute of Information Technology 2 , Wuhu, Anhui 241000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9343-6262","authenticated-orcid":false,"given":"Yitian","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhoushan Yangwangnaxin Technology Co., Ltd. 3 , Zhoushan, Zhejiang 3161041, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4649-8671","authenticated-orcid":false,"given":"Lijie","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Automation, Henan International Joint Laboratory of Direct Drive and Control of Intelligent Equipment, Henan Polytechnic University 1 , Jiaozuo 454003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"317","published-online":{"date-parts":[[2024,5,2]]},"reference":[{"key":"2024050812455324300_c1","doi-asserted-by":"publisher","first-page":"111353","DOI":"10.1016\/j.measurement.2022.111353","article-title":"Diagnosis of unbalanced rolling bearing fault sample based on adaptive sparse contractive auto-encoder and IGWO-USELM","volume":"198","year":"2022","journal-title":"Measurement"},{"key":"2024050812455324300_c2","doi-asserted-by":"publisher","first-page":"107175","DOI":"10.1016\/j.ymssp.2020.107175","article-title":"Oversampling adversarial network for class-imbalanced fault diagnosis","volume":"149","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"2024050812455324300_c3","doi-asserted-by":"publisher","first-page":"101552","DOI":"10.1016\/j.aei.2022.101552","article-title":"Multi-mode data augmentation and fault diagnosis of rotating machinery using modified ACGAN designed with new framework","volume":"52","year":"2022","journal-title":"Adv. Eng. Inform."},{"key":"2024050812455324300_c4","doi-asserted-by":"publisher","first-page":"3909","DOI":"10.1109\/tnnls.2020.3016120","article-title":"H\u221e state estimation for neural networks with general activation function and mixed time-varying delays","volume":"32","year":"2021","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"2024050812455324300_c5","doi-asserted-by":"publisher","first-page":"2360","DOI":"10.1080\/00207721.2020.1794080","article-title":"L2-L\u221e filtering for stochastic delayed systems with randomly occurring nonlinearities and sensor saturation","volume":"51","year":"2020","journal-title":"Int. J. Syst. Sci."},{"key":"2024050812455324300_c6","doi-asserted-by":"publisher","first-page":"(published online)","DOI":"10.1109\/tnnls.2022.3230978","article-title":"Distributed state estimation for mixed delays system over sensor networks with multichannel random attacks and Markov switching topology","year":"2022","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"2024050812455324300_c7","doi-asserted-by":"publisher","first-page":"108385","DOI":"10.1016\/j.asoc.2021.108385","article-title":"Method to enhance deep learning fault diagnosis by generating adversarial samples","volume":"116","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"2024050812455324300_c8","doi-asserted-by":"publisher","first-page":"110826","DOI":"10.1016\/j.measurement.2022.110826","article-title":"Fault diagnosis of rotating machinery based on combination of Wasserstein generative adversarial networks and long short term memory fully convolutional network","volume":"191","year":"2022","journal-title":"Measurement"},{"key":"2024050812455324300_c9","doi-asserted-by":"publisher","first-page":"106756","DOI":"10.1016\/j.knosys.2021.106756","article-title":"A conditional variational autoencoder based self-transferred algorithm for imbalanced classification","volume":"218","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"2024050812455324300_c10","doi-asserted-by":"publisher","first-page":"192","DOI":"10.33103\/uot.ijccce.23.2.15","article-title":"A systematic review of deep dream","volume":"23","year":"2023","journal-title":"Iraqi J. Comput. Commun. Control Syst. Eng."},{"key":"2024050812455324300_c11","doi-asserted-by":"publisher","first-page":"101443","DOI":"10.1109\/access.2023.3309419","article-title":"A hybrid artistic model using deepy-dream model and multiple convolutional neural networks architectures","volume":"11","year":"2023","journal-title":"IEEE Access"},{"key":"2024050812455324300_c12","doi-asserted-by":"publisher","first-page":"030022","DOI":"10.1063\/5.0119604","article-title":"An extensive study of sentiment analysis techniques: A survey","volume":"2591","year":"2023","journal-title":"AIP Conf. Proc."},{"key":"2024050812455324300_c13","doi-asserted-by":"publisher","first-page":"34","DOI":"10.3991\/ijoe.v19i03.37235","article-title":"The effect of changing targeted layers of the deep dream technique using VGG-16 model","volume":"19","year":"2021","journal-title":"Int. J. Online Biomed. Eng."},{"key":"2024050812455324300_c14","doi-asserted-by":"publisher","first-page":"116396","DOI":"10.1016\/j.image.2021.116396","article-title":"Coupled adversarial variational autoencoder","volume":"98","year":"2021","journal-title":"Signal Process. Image Commun."},{"key":"2024050812455324300_c15","doi-asserted-by":"publisher","first-page":"103511","DOI":"10.1016\/j.probengmech.2023.103511","article-title":"Assessment of multi-dimensional joint probability distribution for uncertain mechanical strength parameters under small sample test data","volume":"74","year":"2023","journal-title":"Probabilistic Eng. Mech."},{"key":"2024050812455324300_c16","doi-asserted-by":"publisher","first-page":"106102","DOI":"10.1016\/j.jspi.2023.106102","article-title":"Testing higher and infinite degrees of stochastic dominance for small samples: A Bayesian approach","volume":"230","year":"2023","journal-title":"J.\u00a0Stat. Plan. Inference"},{"key":"2024050812455324300_c17","doi-asserted-by":"publisher","first-page":"111008","DOI":"10.1016\/j.jcp.2022.111008","article-title":"Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems","volume":"455","year":"2022","journal-title":"J.\u00a0Comput. Phys."},{"key":"2024050812455324300_c18","doi-asserted-by":"publisher","first-page":"108371","DOI":"10.1016\/j.measurement.2020.108371","article-title":"Rolling bearing fault diagnosis using variational autoencoding generative adversarial networks with deep regret analysis","volume":"168","year":"2021","journal-title":"Measurement"},{"key":"2024050812455324300_c19","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1016\/j.egyr.2022.01.226","article-title":"Fault diagnosis of permanent magnet motor based on DCGAN-RCCNN","volume":"8","year":"2022","journal-title":"Energy Rep."}],"updated-by":[{"DOI":"10.1063\/5.0218473","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T00:00:00Z","timestamp":1716422400000}}],"container-title":["Review of Scientific Instruments"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/aip\/rsi\/article-pdf\/doi\/10.1063\/5.0193162\/19935301\/055104_1_5.0193162.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/aip\/rsi\/article-pdf\/doi\/10.1063\/5.0193162\/19935301\/055104_1_5.0193162.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T08:46:06Z","timestamp":1715157966000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/rsi\/article\/95\/5\/055104\/3287839\/Deep-network-fault-diagnosis-for-imbalanced-small"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,1]]},"references-count":19,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5,1]]}},"URL":"https:\/\/doi.org\/10.1063\/5.0193162","relation":{},"ISSN":["0034-6748","1089-7623"],"issn-type":[{"value":"0034-6748","type":"print"},{"value":"1089-7623","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,5,1]]},"published":{"date-parts":[[2024,5,1]]},"article-number":"055104"}}