{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T04:25:46Z","timestamp":1794543946860,"version":"4.9.1"},"reference-count":33,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2021,12,29]],"date-time":"2021-12-29T00:00:00Z","timestamp":1640736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62103168"],"award-info":[{"award-number":["62103168"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20210452"],"award-info":[{"award-number":["BK20210452"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This work considers industrial process monitoring using a variational autoencoder (VAE). As a powerful deep generative model, the variational autoencoder and its variants have become popular for process monitoring. However, its monitoring ability, especially its fault diagnosis ability, has not been well investigated. In this paper, the process modeling and monitoring capabilities of several VAE variants are comprehensively studied. First, fault detection schemes are defined in three distinct ways, considering latent, residual, and the combined domains. Afterwards, to conduct the fault diagnosis, we first define the deep contribution plot, and then a deep reconstruction-based contribution diagram is proposed for deep domains under the fault propagation mechanism. In a case study, the performance of the process monitoring capability of four deep VAE models, namely, the static VAE model, the dynamic VAE model, and the recurrent VAE models (LSTM-VAE and GRU-VAE), has been comparatively evaluated on the industrial benchmark Tennessee Eastman process. Results show that recurrent VAEs with a deep reconstruction-based diagnosis mechanism are recommended for industrial process monitoring tasks.<\/jats:p>","DOI":"10.3390\/s22010227","type":"journal-article","created":{"date-parts":[[2021,12,29]],"date-time":"2021-12-29T08:12:15Z","timestamp":1640765535000},"page":"227","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Fault Detection and Diagnosis in Industrial Processes with Variational Autoencoder: A Comprehensive Study"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4296-5914","authenticated-orcid":false,"given":"Jinlin","family":"Zhu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Food Science and Technology, Jiangnan University, Wuxi 214122, China"},{"name":"School of Food Science and Technology, Jiangnan University, Wuxi 214122, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muyun","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi 214122, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,12,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.chemolab.2017.09.021","article-title":"Review on data-driven modeling and monitoring for plant-wide industrial processes","volume":"171","author":"Ge","year":"2017","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1016\/j.compchemeng.2019.04.003","article-title":"Advances and opportunities in machine learning for process data analytics","volume":"126","author":"Qin","year":"2019","journal-title":"Comput. Chem. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.arcontrol.2018.09.003","article-title":"Review and big data perspectives on robust data mining approaches for industrial process modeling with outliers and missing data","volume":"46","author":"Zhu","year":"2018","journal-title":"Annu. Rev. Control"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1016\/j.automatica.2009.02.027","article-title":"Reconstruction-based contribution for process monitoring","volume":"45","author":"Alcala","year":"2009","journal-title":"Automatica"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.jprocont.2010.10.005","article-title":"Analysis and generalization of fault diagnosis methods for process monitoring","volume":"21","author":"Alcala","year":"2011","journal-title":"J. Process Control"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.chemolab.2004.05.001","article-title":"Fault detection and identification of nonlinear processes based on kernel PCA","volume":"75","author":"Choi","year":"2005","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1002\/aic.690370209","article-title":"Nonlinear principal component analysis using autoassociative neural networks","volume":"37","author":"Kramer","year":"1991","journal-title":"AIChE J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/0169-7439(95)00076-3","article-title":"Disturbance detection and isolation by dynamic principal component analysis","volume":"30","author":"Ku","year":"1995","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"6438","DOI":"10.1109\/TIE.2014.2301761","article-title":"A new method of dynamic latent variable modeling for process monitoring","volume":"61","author":"Li","year":"2014","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"107837","DOI":"10.1016\/j.ress.2021.107837","article-title":"A framework to automate fault detection and diagnosis based on moving window principal component analysis and Bayesian network","volume":"215","author":"Andrade","year":"2021","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"116099","DOI":"10.1016\/j.ces.2020.116099","article-title":"Fault detection and diagnosis of nonlinear dynamical processes through correlation dimension and fractal analysis based dynamic kernel PCA","volume":"229","author":"Bounoua","year":"2021","journal-title":"Chem. Eng. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"5956","DOI":"10.1021\/acs.iecr.9b06826","article-title":"Two-Step Localized Kernel Principal Component Analysis Based Incipient Fault Diagnosis for Nonlinear Industrial Processes","volume":"59","author":"Deng","year":"2020","journal-title":"Ind. Eng. Chem. Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1109\/MCI.2018.2840738","article-title":"Recent trends in deep learning based natural language processing","volume":"13","author":"Young","year":"2018","journal-title":"IEEE Comput. Intell. Mag."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1109\/TBME.2019.2909027","article-title":"Dynamic-deephit: A deep learning approach for dynamic survival analysis with competing risks based on longitudinal data","volume":"67","author":"Lee","year":"2019","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3085","DOI":"10.1007\/s00521-020-05171-4","article-title":"Multichannel one-dimensional convolutional neural network-based feature learning for fault diagnosis of industrial processes","volume":"33","author":"Yu","year":"2021","journal-title":"Neural Comput. Applic"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.chemolab.2017.06.010","article-title":"Semi-supervised fault classification based on dynamic sparse stacked auto-encoders model","volume":"168","author":"Jiang","year":"2017","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.chemolab.2016.08.007","article-title":"Nonlinear and robust statistical process monitoring based on variant autoencoders","volume":"158","author":"Yan","year":"2016","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.engappai.2019.04.013","article-title":"Process monitoring using variational autoencoder for high-dimensional nonlinear processes","volume":"83","author":"Lee","year":"2019","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.jprocont.2019.01.008","article-title":"Gaussian feature learning based on variational autoencoder for improving nonlinear process monitoring","volume":"75","author":"Zhang","year":"2019","journal-title":"J. Process Control"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"106515","DOI":"10.1016\/j.compchemeng.2019.106515","article-title":"A novel process monitoring approach based on variational recurrent autoencoder","volume":"129","author":"Cheng","year":"2019","journal-title":"Comput. Chem. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1109\/TII.2021.3078414","article-title":"Adversarial Autoencoder Based Feature Learning for Fault Detection in Industrial Processes","volume":"18","author":"Jang","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yu, J., and Liu, X. (2020, January 6\u20138). A Fault Detection Method based on Convolutional Gated Recurrent Unit Auto-encoder for Tennessee Eastman Process. Proceedings of the Chinese Automation Congress, Shanghai, China.","DOI":"10.1109\/CAC51589.2020.9326895"},{"key":"ref_24","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-encoding variational bayes. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"062412","DOI":"10.1103\/PhysRevE.97.062412","article-title":"Variational encoding of complex dynamics","volume":"97","author":"Sultan","year":"2018","journal-title":"Phys. Rev. E"},{"key":"ref_26","unstructured":"Lipton, Z.C., Berkowitz, J., and Elkan, C. (2015). A critical review of recurrent neural networks for sequence learning. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv.","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1111\/j.2517-6161.1991.tb01857.x","article-title":"A reliable data-based bandwidth selection method for kernel density estimation","volume":"53","author":"Sheather","year":"1991","journal-title":"J. R. Stat. Soc. Ser. B"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.1016\/j.jprocont.2012.06.009","article-title":"A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process","volume":"22","author":"Yin","year":"2012","journal-title":"J. Process Control"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.jprocont.2017.06.017","article-title":"Concurrent quality and process monitoring with canonical correlation analysis","volume":"60","author":"Zhu","year":"2017","journal-title":"J. Process Control"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/j.ifacol.2015.08.199","article-title":"Revision of the Tennessee Eastman process model","volume":"48","author":"Bathelt","year":"2015","journal-title":"IFAC-PapersOnLine"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1877","DOI":"10.1109\/TII.2017.2658732","article-title":"Distributed parallel pca for modeling and monitoring of large-scale plant-wide processes with big data","volume":"12","author":"Zhu","year":"2017","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"480","DOI":"10.1002\/cem.800","article-title":"Statistical process monitoring: Basics and beyond","volume":"17","author":"Qin","year":"2003","journal-title":"J. Chemom."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/1\/227\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:55:33Z","timestamp":1760169333000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/1\/227"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,29]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,1]]}},"alternative-id":["s22010227"],"URL":"https:\/\/doi.org\/10.3390\/s22010227","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,29]]}}}