{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:10:22Z","timestamp":1774890622094,"version":"3.50.1"},"reference-count":52,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/501100018625","name":"Science and Technology Innovation Plan Of Shanghai Science and Technology Commission","doi-asserted-by":"publisher","award":["23S41900500"],"award-info":[{"award-number":["23S41900500"]}],"id":[{"id":"10.13039\/501100018625","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322309"],"award-info":[{"award-number":["62322309"]}],"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":["62433004"],"award-info":[{"award-number":["62433004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016096","name":"Shanghai Key Basic Research Program","doi-asserted-by":"publisher","award":["22TQ1400100- 16"],"award-info":[{"award-number":["22TQ1400100- 16"]}],"id":[{"id":"10.13039\/100016096","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of the Franklin Institute"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.jfranklin.2026.108525","type":"journal-article","created":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T07:59:33Z","timestamp":1771315173000},"page":"108525","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical fault root cause diagnosis in multimode process using direct causality and causal polarity analysis"],"prefix":"10.1016","volume":"363","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5068-346X","authenticated-orcid":false,"given":"Zhenhua","family":"Yu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2341-3054","authenticated-orcid":false,"given":"Guan","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1527-885X","authenticated-orcid":false,"given":"Lihua","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3402-9018","authenticated-orcid":false,"given":"Qingchao","family":"Jiang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-4739","authenticated-orcid":false,"given":"Weimin","family":"Zhong","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.jfranklin.2026.108525_bib0001","doi-asserted-by":"crossref","first-page":"2573","DOI":"10.1016\/j.jfranklin.2016.11.012","article-title":"Fault diagnosis of non-Gaussian process based on FKICA","volume":"354","author":"Du","year":"2017","journal-title":"J. Frankl. Inst."},{"issue":"7","key":"10.1016\/j.jfranklin.2026.108525_bib0002","doi-asserted-by":"crossref","first-page":"3249","DOI":"10.1016\/j.jfranklin.2018.02.027","article-title":"Fault diagnosis for processes with feedback control loops by shifted output sampling approach","volume":"355","author":"Wang","year":"2018","journal-title":"J. Frankl. Inst."},{"issue":"14","key":"10.1016\/j.jfranklin.2026.108525_bib0003","doi-asserted-by":"crossref","first-page":"10054","DOI":"10.1016\/j.jfranklin.2020.07.046","article-title":"Observer-based fault detection and diagnosis strategy for industrial processes","volume":"357","author":"Bernardi","year":"2020","journal-title":"J. Frankl. Inst."},{"issue":"13","key":"10.1016\/j.jfranklin.2026.108525_bib0004","doi-asserted-by":"crossref","first-page":"7115","DOI":"10.1016\/j.jfranklin.2022.06.022","article-title":"Fault detection and diagnosis strategy based on k-nearest neighbors and fuzzy C-means clustering algorithm for industrial processes","volume":"359","author":"Elshenawy","year":"2022","journal-title":"J. Frankl. Inst."},{"issue":"1","key":"10.1016\/j.jfranklin.2026.108525_bib0005","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.jfranklin.2023.10.004","article-title":"An industrial process fault diagnosis method based on independent slow feature analysis and stacked sparse autoencoder network","volume":"361","author":"Li","year":"2024","journal-title":"J. Frankl. Inst."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0006","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.jprocont.2021.11.013","article-title":"Data-knowledge-driven distributed monitoring for large-scale processes based on digraph","volume":"109","author":"Wu","year":"2022","journal-title":"J. Process Control"},{"issue":"11","key":"10.1016\/j.jfranklin.2026.108525_bib0007","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.ifacol.2019.09.115","article-title":"Generation of signed directed graphs using functional models","volume":"52","author":"Reinartz","year":"2019","journal-title":"IFAC Pap. OnLine"},{"key":"10.1016\/j.jfranklin.2026.108525_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2021.101312","article-title":"High-speed train fault detection with unsupervised causality-based feature extraction methods","volume":"49","author":"Xu","year":"2021","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2020.106944","article-title":"Causality validation of multilevel flow modelling","volume":"140","author":"Nielsen","year":"2020","journal-title":"Comput. Chem. Eng."},{"issue":"1","key":"10.1016\/j.jfranklin.2026.108525_bib0010","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1021\/acs.iecr.7b03338","article-title":"Robust principal component pursuit for fault detection in a blast furnace process","volume":"57","author":"Pan","year":"2018","journal-title":"Ind. Eng. Chem. Res."},{"issue":"3","key":"10.1016\/j.jfranklin.2026.108525_bib0011","doi-asserted-by":"crossref","first-page":"2626","DOI":"10.1109\/TIE.2020.2972472","article-title":"Key-performance-indicator-related process monitoring based on improved kernel partial least squares","volume":"68","author":"Si","year":"2020","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"1","key":"10.1016\/j.jfranklin.2026.108525_bib0012","doi-asserted-by":"crossref","first-page":"622","DOI":"10.1109\/TIE.2020.2967708","article-title":"Data-driven monitoring and diagnosing of abnormal furnace conditions in blast furnace ironmaking: an integrated PCA-ICA method","volume":"68","author":"Zhou","year":"2020","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"2","key":"10.1016\/j.jfranklin.2026.108525_bib0013","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1016\/j.jprocont.2013.11.009","article-title":"Root cause diagnosis of plant-wide oscillations using Granger causality","volume":"24","author":"Yuan","year":"2014","journal-title":"J. Process Control"},{"issue":"29","key":"10.1016\/j.jfranklin.2026.108525_bib0014","doi-asserted-by":"crossref","first-page":"9500","DOI":"10.1021\/acs.iecr.8b00697","article-title":"Systematic procedure for Granger-causality-based root cause diagnosis of chemical process faults","volume":"57","author":"Chen","year":"2018","journal-title":"Ind. Eng. Chem. Res."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2024.108589","article-title":"A hierarchical granger causality analysis framework based on information of redundancy for root cause diagnosis of process disturbances","volume":"182","author":"Wang","year":"2024","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0016","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.conengprac.2017.07.005","article-title":"A novel data-based quality-related fault diagnosis scheme for fault detection and root cause diagnosis with application to hot strip mill process","volume":"67","author":"Ma","year":"2017","journal-title":"Control Eng. Pract."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0017","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.neucom.2020.03.007","article-title":"Autonomous root-cause fault diagnosis using symbolic dynamic based causality analysis","volume":"401","author":"Rashidi","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.jfranklin.2026.108525_bib0018","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/j.compchemeng.2013.05.011","article-title":"Data-driven causal inference based on a modified transfer entropy","volume":"57","author":"Shu","year":"2013","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0019","doi-asserted-by":"crossref","first-page":"1693","DOI":"10.1016\/B978-0-444-63965-3.50284-1","article-title":"Root cause diagnosis of disturbances propagation paths by using improved convergent cross mapping","volume":"40","author":"Cheng","year":"2017","journal-title":"Comput. Aided Chem. Eng."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0020","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.conengprac.2018.10.005","article-title":"Improved CCM for variable causality detection in complex systems","volume":"83","author":"Wang","year":"2019","journal-title":"Control Eng. Pract."},{"issue":"2","key":"10.1016\/j.jfranklin.2026.108525_bib0021","first-page":"13619","article-title":"Causal network construction based on convergent cross mapping (CCM) for alarm system root cause tracing of nonlinear industrial process, IFAC-Pap","volume":"53","author":"Tian","year":"2020","journal-title":"OnLine"},{"issue":"9","key":"10.1016\/j.jfranklin.2026.108525_bib0022","doi-asserted-by":"crossref","first-page":"11891","DOI":"10.1007\/s10586-024-04663-5","article-title":"Causal network construction based on KICA-ECCM for root cause diagnosis of industrial processes","volume":"27","author":"He","year":"2024","journal-title":"Clust. Comput."},{"issue":"8","key":"10.1016\/j.jfranklin.2026.108525_bib0023","doi-asserted-by":"crossref","first-page":"2054","DOI":"10.1021\/acs.iecr.6b01916","article-title":"Root cause diagnosis of process fault using KPCA and Bayesian network","volume":"56","author":"Gharahbagheri","year":"2017","journal-title":"Ind. Eng. Chem. Res."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0024","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.jprocont.2020.09.006","article-title":"Simplified Granger causality map for data-driven root cause diagnosis of process disturbances","volume":"95","author":"Liu","year":"2020","journal-title":"J. Process Control"},{"key":"10.1016\/j.jfranklin.2026.108525_bib0025","series-title":"Partial cross mapping based on sparse variable selection for direct fault root cause diagnosis for industrial processes","first-page":"6218","volume":"35","author":"Jiang","year":"2023"},{"key":"10.1016\/j.jfranklin.2026.108525_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.jprocont.2023.103062","article-title":"Data-driven root cause diagnosis of process disturbances by exploring causality change among variables","volume":"129","author":"Wang","year":"2023","journal-title":"J. Process Control"},{"issue":"5","key":"10.1016\/j.jfranklin.2026.108525_bib0027","doi-asserted-by":"crossref","first-page":"3358","DOI":"10.1109\/TII.2020.3011069","article-title":"A multiagent-based methodology for known and novel faults diagnosis in industrial processes","volume":"17","author":"Koujok","year":"2020","journal-title":"IEEE Trans. Ind. Inf."},{"issue":"7","key":"10.1016\/j.jfranklin.2026.108525_bib0028","doi-asserted-by":"crossref","first-page":"4374","DOI":"10.1109\/TSMC.2021.3096529","article-title":"Quality-discriminative localization of multisensor signals for root cause analysis","volume":"52","author":"Cho","year":"2021","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"4","key":"10.1016\/j.jfranklin.2026.108525_bib0029","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.1109\/TII.2018.2855189","article-title":"Hierarchical monitoring and root-cause diagnosis framework for key performance indicator-related multiple faults in process industries","volume":"15","author":"Ma","year":"2019","journal-title":"IEEE Trans. Ind. Inf."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.conengprac.2024.106140","article-title":"Causal similarity learning with multi-level predictive relation aggregation for grouped root cause diagnosis of industrial faults","volume":"154","author":"Zhao","year":"2025","journal-title":"Control Eng. Pract."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0031","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.jprocont.2022.06.014","article-title":"Root cause diagnosis in multivariate time series based on modified temporal convolution and multi-head self-attention","volume":"117","author":"Zhou","year":"2022","journal-title":"J. Process Control"},{"key":"10.1016\/j.jfranklin.2026.108525_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.chemolab.2022.104559","article-title":"Root cause analysis of industrial faults based on binary extreme gradient boosting and temporal causal discovery network","volume":"225","author":"Qin","year":"2022","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0033","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/j.isatra.2021.06.005","article-title":"Towards robust and understandable fault detection and diagnosis using denoising sparse autoencoder and smooth integrated gradients","volume":"125","author":"Peng","year":"2022","journal-title":"ISA Trans."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0034","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.jprocont.2022.12.006","article-title":"Root cause diagnosis for process faults based on multisensor time-series causality discovery","volume":"122","author":"Wang","year":"2023","journal-title":"J. Process Control"},{"key":"10.1016\/j.jfranklin.2026.108525_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.measurement.2024.114219","article-title":"Root cause diagnosis and fault propagation path identification for complex industrial processes based on data space","volume":"226","author":"Qiao","year":"2024","journal-title":"Measurement"},{"key":"10.1016\/j.jfranklin.2026.108525_bib0036","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.isatra.2019.06.004","article-title":"A novel key performance indicator oriented hierarchical monitoring and propagation path identification framework for complex industrial processes","volume":"96","author":"Ma","year":"2020","journal-title":"ISA Trans."},{"issue":"25","key":"10.1016\/j.jfranklin.2026.108525_bib0037","doi-asserted-by":"crossref","first-page":"11559","DOI":"10.1021\/acs.iecr.0c00417","article-title":"Attention-based long short-term memory method for alarm root-cause diagnosis in chemical processes","volume":"59","author":"He","year":"2020","journal-title":"Ind. Eng. Chem. Res."},{"issue":"3","key":"10.1016\/j.jfranklin.2026.108525_bib0038","first-page":"439","article-title":"Sparse adjacency forecasting and its application to efficient root cause diagnosis of process faults, IFAC-Pap","volume":"54","author":"Song","year":"2021","journal-title":"OnLine"},{"key":"10.1016\/j.jfranklin.2026.108525_bib0039","first-page":"1","article-title":"A practical root cause diagnosis framework for quality-related faults in manufacturing processes with irregular sampling measurements","volume":"71","author":"Ma","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2023.108453","article-title":"Graph attention network with Granger causality map for fault detection and root cause diagnosis","volume":"180","author":"Liu","year":"2024","journal-title":"Comput. Chem. Eng."},{"issue":"15","key":"10.1016\/j.jfranklin.2026.108525_bib0041","doi-asserted-by":"crossref","first-page":"3932","DOI":"10.1073\/pnas.1517384113","article-title":"Discovering governing equations from data by sparse identification of nonlinear dynamical systems","volume":"113","author":"Brunton","year":"2016","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"issue":"1","key":"10.1016\/j.jfranklin.2026.108525_bib0042","doi-asserted-by":"crossref","first-page":"4287","DOI":"10.1038\/s41467-023-39983-4","article-title":"A general model-based causal inference method overcomes the curse of synchrony and indirect effect","volume":"14","author":"Park","year":"2023","journal-title":"Nat. Commun."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0043","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."},{"issue":"3","key":"10.1016\/j.jfranklin.2026.108525_bib0044","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1214\/aoms\/1177704472","article-title":"On estimation of a probability density function and mode","volume":"33","author":"Parzen","year":"1962","journal-title":"Ann. Math. Stat."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.conengprac.2024.106219","article-title":"Enhanced variational autoencoder with continual learning capability for multimode process monitoring","volume":"156","author":"Yu","year":"2025","journal-title":"Control Eng. Pract."},{"issue":"3","key":"10.1016\/j.jfranklin.2026.108525_bib0046","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1002\/nla.1839","article-title":"Gram-Schmidt orthogonalization: 100 years and more, numer","volume":"20","author":"Leon","year":"2013","journal-title":"Linear Algebra Appl."},{"issue":"4-5","key":"10.1016\/j.jfranklin.2026.108525_bib0047","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0925-2312(93)90006-O","article-title":"Backpropagation and stochastic gradient descent method","volume":"5","author":"Amari","year":"1993","journal-title":"Neurocomput"},{"issue":"11","key":"10.1016\/j.jfranklin.2026.108525_bib0048","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1016\/S0098-1354(02)00127-8","article-title":"A modular simulation package for fed-batch fermentation: penicillin production","volume":"26","author":"Birol","year":"2002","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0049","doi-asserted-by":"crossref","first-page":"1154","DOI":"10.1016\/j.psep.2023.07.080","article-title":"Variational autoencoder based on distributional semantic embedding and cross-modal reconstruction for generalized zero-shot fault diagnosis of industrial processes","volume":"177","author":"Mou","year":"2023","journal-title":"Process Saf. Environ. Prot."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0050","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.cjche.2025.05.003","article-title":"SmdaNet: A hierarchical hard sample mining and domain adaptation neural network for fault diagnosis in industrial process","volume":"84","author":"Yu","year":"2025","journal-title":"Chin. J. Chem. Eng."},{"issue":"3","key":"10.1016\/j.jfranklin.2026.108525_bib0051","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1007\/s11634-018-0335-0","article-title":"Greedy Gaussian segmentation of multivariate time series","volume":"13","author":"Hallac","year":"2019","journal-title":"Adv. Data Anal. Classif."},{"key":"10.1016\/j.jfranklin.2026.108525_bib0052","doi-asserted-by":"crossref","DOI":"10.1016\/j.jprocont.2025.103373","article-title":"Mutual information and attention-based variable selection for soft sensing of industrial processes","volume":"146","author":"Yu","year":"2025","journal-title":"J. Process Control"}],"container-title":["Journal of the Franklin Institute"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0016003226001250?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0016003226001250?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T16:12:51Z","timestamp":1774887171000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0016003226001250"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":52,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["S0016003226001250"],"URL":"https:\/\/doi.org\/10.1016\/j.jfranklin.2026.108525","relation":{},"ISSN":["0016-0032"],"issn-type":[{"value":"0016-0032","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Hierarchical fault root cause diagnosis in multimode process using direct causality and causal polarity analysis","name":"articletitle","label":"Article Title"},{"value":"Journal of the Franklin Institute","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jfranklin.2026.108525","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Franklin Institute. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108525"}}