Novel semi-supervised sparse stacked autoencoder integrated with local linear embedding for industrial soft sensing
Data-driven industrial soft sensor modeling techniques have been widely applied in predicting key variables in complex industrial processes. However, with industrial processes becoming increasingly intricate, the data they produce exhibit characteristics such as strong temporal dependencies, high di...
Saved in:
| Published in: | ISA transactions |
|---|---|
| Main Authors: | , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
Elsevier Ltd
04.06.2025
|
| Subjects: | |
| ISSN: | 0019-0578, 1879-2022, 1879-2022 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Data-driven industrial soft sensor modeling techniques have been widely applied in predicting key variables in complex industrial processes. However, with industrial processes becoming increasingly intricate, the data they produce exhibit characteristics such as strong temporal dependencies, high dimensionality, and local structures, posing significant challenges for soft sensing. To address these issues, this paper proposes novel Semi-Supervised Sparse Stacked Autoencoder integrated with the Local Linear Embedding algorithm (SS-SAE-LLE). Unlike traditional autoencoders (AE), which capture hierarchical data features by minimizing global fitting error, SS-SAE-LLE simultaneously accounts for the spatio-temporal characteristics of the data through the local linear embedding algorithm. Moreover, it incorporates supervised tuning by leveraging labeled data and training with a semi-supervised learning framework, further improving prediction accuracy. To evaluate the feasibility of the proposed method, experiments are conducted on PTA solvent and SRU system datasets. The simulation results demonstrate that SS-SAE-LLE achieves higher prediction accuracy than other models, highlighting its applicability in the field of industrial soft sensor modeling.
•SS-SAE-LLE is proposed for data-driven industrial soft sensor modeling.•SS-SAE-LLE captures hierarchical and spatio-temporal features simultaneously.•Supervised tuning with labeled data enhances the regression performance.•SS-SAE-LLE effectively addresses high dimensionality and temporal dependencies in process data.•Experimental results on PTA solvent and SRU datasets demonstrate the superior accuracy of SS-SAE-LLE. |
|---|---|
| AbstractList | Data-driven industrial soft sensor modeling techniques have been widely applied in predicting key variables in complex industrial processes. However, with industrial processes becoming increasingly intricate, the data they produce exhibit characteristics such as strong temporal dependencies, high dimensionality, and local structures, posing significant challenges for soft sensing. To address these issues, this paper proposes novel Semi-Supervised Sparse Stacked Autoencoder integrated with the Local Linear Embedding algorithm (SS-SAE-LLE). Unlike traditional autoencoders (AE), which capture hierarchical data features by minimizing global fitting error, SS-SAE-LLE simultaneously accounts for the spatio-temporal characteristics of the data through the local linear embedding algorithm. Moreover, it incorporates supervised tuning by leveraging labeled data and training with a semi-supervised learning framework, further improving prediction accuracy. To evaluate the feasibility of the proposed method, experiments are conducted on PTA solvent and SRU system datasets. The simulation results demonstrate that SS-SAE-LLE achieves higher prediction accuracy than other models, highlighting its applicability in the field of industrial soft sensor modeling.Data-driven industrial soft sensor modeling techniques have been widely applied in predicting key variables in complex industrial processes. However, with industrial processes becoming increasingly intricate, the data they produce exhibit characteristics such as strong temporal dependencies, high dimensionality, and local structures, posing significant challenges for soft sensing. To address these issues, this paper proposes novel Semi-Supervised Sparse Stacked Autoencoder integrated with the Local Linear Embedding algorithm (SS-SAE-LLE). Unlike traditional autoencoders (AE), which capture hierarchical data features by minimizing global fitting error, SS-SAE-LLE simultaneously accounts for the spatio-temporal characteristics of the data through the local linear embedding algorithm. Moreover, it incorporates supervised tuning by leveraging labeled data and training with a semi-supervised learning framework, further improving prediction accuracy. To evaluate the feasibility of the proposed method, experiments are conducted on PTA solvent and SRU system datasets. The simulation results demonstrate that SS-SAE-LLE achieves higher prediction accuracy than other models, highlighting its applicability in the field of industrial soft sensor modeling. Data-driven industrial soft sensor modeling techniques have been widely applied in predicting key variables in complex industrial processes. However, with industrial processes becoming increasingly intricate, the data they produce exhibit characteristics such as strong temporal dependencies, high dimensionality, and local structures, posing significant challenges for soft sensing. To address these issues, this paper proposes novel Semi-Supervised Sparse Stacked Autoencoder integrated with the Local Linear Embedding algorithm (SS-SAE-LLE). Unlike traditional autoencoders (AE), which capture hierarchical data features by minimizing global fitting error, SS-SAE-LLE simultaneously accounts for the spatio-temporal characteristics of the data through the local linear embedding algorithm. Moreover, it incorporates supervised tuning by leveraging labeled data and training with a semi-supervised learning framework, further improving prediction accuracy. To evaluate the feasibility of the proposed method, experiments are conducted on PTA solvent and SRU system datasets. The simulation results demonstrate that SS-SAE-LLE achieves higher prediction accuracy than other models, highlighting its applicability in the field of industrial soft sensor modeling. •SS-SAE-LLE is proposed for data-driven industrial soft sensor modeling.•SS-SAE-LLE captures hierarchical and spatio-temporal features simultaneously.•Supervised tuning with labeled data enhances the regression performance.•SS-SAE-LLE effectively addresses high dimensionality and temporal dependencies in process data.•Experimental results on PTA solvent and SRU datasets demonstrate the superior accuracy of SS-SAE-LLE. Data-driven industrial soft sensor modeling techniques have been widely applied in predicting key variables in complex industrial processes. However, with industrial processes becoming increasingly intricate, the data they produce exhibit characteristics such as strong temporal dependencies, high dimensionality, and local structures, posing significant challenges for soft sensing. To address these issues, this paper proposes novel Semi-Supervised Sparse Stacked Autoencoder integrated with the Local Linear Embedding algorithm (SS-SAE-LLE). Unlike traditional autoencoders (AE), which capture hierarchical data features by minimizing global fitting error, SS-SAE-LLE simultaneously accounts for the spatio-temporal characteristics of the data through the local linear embedding algorithm. Moreover, it incorporates supervised tuning by leveraging labeled data and training with a semi-supervised learning framework, further improving prediction accuracy. To evaluate the feasibility of the proposed method, experiments are conducted on PTA solvent and SRU system datasets. The simulation results demonstrate that SS-SAE-LLE achieves higher prediction accuracy than other models, highlighting its applicability in the field of industrial soft sensor modeling. |
| Author | Gao, Hui-Hui Xu, Yuan He, Yan-Lin Zhu, Qun-Xiong Jiang, Yu |
| Author_xml | – sequence: 1 givenname: Yan-Lin orcidid: 0000-0001-9999-3679 surname: He fullname: He, Yan-Lin email: heyl@mail.buct.edu.cn organization: College of Information Science & Technology, Beijing University of Chemical Technology, Beijing, 100029, China – sequence: 2 givenname: Yu orcidid: 0009-0003-0550-2421 surname: Jiang fullname: Jiang, Yu email: 2022200816@mail.buct.edu.cn organization: College of Information Science & Technology, Beijing University of Chemical Technology, Beijing, 100029, China – sequence: 3 givenname: Hui-Hui surname: Gao fullname: Gao, Hui-Hui email: gaohh@bjut.edu.cn organization: School of Information Science and Technology, Engineering Research Center of Digital Community, Ministry of Education, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing, 100124, China – sequence: 4 givenname: Yuan surname: Xu fullname: Xu, Yuan email: xuyuan@mail.buct.edu.cn organization: College of Information Science & Technology, Beijing University of Chemical Technology, Beijing, 100029, China – sequence: 5 givenname: Qun-Xiong surname: Zhu fullname: Zhu, Qun-Xiong email: zhuqx@mail.buct.edu.cn organization: College of Information Science & Technology, Beijing University of Chemical Technology, Beijing, 100029, China |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/40517087$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kUFP4zAQhS3EirbAP0AoRy4pjuMkzgUJIRaQEHvZPVsTe1pckrh4nK7236-rAkekkSzP-2Ysv7dgx6MfkbGLgi8LXtTXm6UjiAGWgotqyVNJecTmhWraPLXEMZtzXrQ5rxo1YwuiDeeJbNUJm0leFQ1XzZzRi99hnxEOLqdpi2HnCG1GWwiEGUUwb-kKU_Q4Gm8xZG6MuA4QU_uvi69Z7w30We9GhJDh0KG1blxnK79H7UQxuKSTX8X0ykhJO2M_VtATnn-cp-zPz_vfd4_586-Hp7vb59wIoWJuwIKoZWnLClvTlabtamNrU3dCCNmYVhkBUiqhkoLQtmVRVqrigKjACluesqvD3m3w7xNS1IMjg30PI_qJdCmSWU1VN1VCLz_QqRvQ6m1wA4R_-tOoBMgDYIInCrj6Qgqu93nojT7kofd5aJ5KyjR2cxjD9M-dw6DJuOQkWhfQRG29-37Bf0Htl9s |
| Cites_doi | 10.1016/j.engappai.2022.105737 10.1016/j.measurement.2022.111439 10.1016/j.isatra.2025.02.010 10.1016/j.conengprac.2024.106181 10.1109/TII.2018.2809730 10.1109/TCYB.2024.3365068 10.1016/j.isatra.2020.10.006 10.1021/acs.iecr.0c03839 10.1016/j.ins.2024.120389 10.1016/j.ins.2024.121565 10.1016/j.cjche.2015.11.012 10.1016/j.compchemeng.2008.12.012 10.1016/j.ress.2024.110135 10.1016/j.engappai.2021.104341 10.1016/j.ins.2022.10.036 10.1109/TII.2023.3268745 10.1016/j.eswa.2024.125052 10.1109/TII.2023.3313631 10.1016/j.jprocont.2024.103300 10.1016/j.cose.2023.103144 10.1016/j.engappai.2024.109065 10.1016/j.ins.2024.121072 10.1109/TIE.2016.2622668 10.1016/j.ifacol.2024.08.320 10.1016/j.aei.2020.101136 10.1016/j.isatra.2023.04.012 10.1016/j.knosys.2024.112341 10.1016/j.patcog.2024.111187 10.1109/TII.2024.3465597 10.1016/j.compchemeng.2024.108925 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Ltd Copyright © 2025 Elsevier Ltd. All rights reserved. |
| Copyright_xml | – notice: 2025 Elsevier Ltd – notice: Copyright © 2025 Elsevier Ltd. All rights reserved. |
| DBID | AAYXX CITATION NPM 7X8 |
| DOI | 10.1016/j.isatra.2025.05.044 |
| DatabaseName | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Sciences (General) |
| EISSN | 1879-2022 |
| ExternalDocumentID | 40517087 10_1016_j_isatra_2025_05_044 S0019057825002782 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 29J 4.4 457 4G. 53G 5GY 5VS 6P2 7-5 71M 8P~ 9JN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYWO ABFNM ABFRF ABJNI ABMAC ABNEU ABWVN ABXDB ACDAQ ACFVG ACGFO ACNNM ACRLP ACRPL ACVFH ADBBV ADCNI ADEZE ADMUD ADNMO ADTZH AEBSH AECPX AEFWE AEIPS AEKER AENEX AEUPX AFFNX AFJKZ AFPUW AFTJW AFXIZ AGCQF AGHFR AGQPQ AGRNS AGUBO AGYEJ AHHHB AHJVU AIEXJ AIGII AIIUN AIKHN AITUG AIVDX AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU APXCP ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC BNPGV CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 GBLVA HVGLF HZ~ IHE J1W JJJVA KOM LY7 M41 MO0 N9A O-L O9- OAUVE OGIMB OZT P-8 P-9 P2P PC. Q38 R2- ROL RPZ SDF SDG SES SET SEW SPC SPCBC SPD SSH SSQ SST SSZ T5K T9H TAE TN5 UHS UNMZH WUQ XPP ZMT ZY4 ~G- 9DU AAYXX ACLOT CITATION EFKBS EFLBG ~HD NPM 7X8 |
| ID | FETCH-LOGICAL-c228t-cada2643d35e9cb3c9b6cd6c6b22247c98c2a44828c9bea993135850aee8ad2d3 |
| ISSN | 0019-0578 1879-2022 |
| IngestDate | Thu Oct 02 22:35:29 EDT 2025 Mon Jul 21 05:59:04 EDT 2025 Sat Nov 29 07:48:34 EST 2025 Sat Jul 05 17:12:53 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Industrial processes Industrial soft sensors Local features Data-driven modelling |
| Language | English |
| License | Copyright © 2025 Elsevier Ltd. All rights reserved. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c228t-cada2643d35e9cb3c9b6cd6c6b22247c98c2a44828c9bea993135850aee8ad2d3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0009-0003-0550-2421 0000-0001-9999-3679 |
| PMID | 40517087 |
| PQID | 3218775675 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_3218775675 pubmed_primary_40517087 crossref_primary_10_1016_j_isatra_2025_05_044 elsevier_sciencedirect_doi_10_1016_j_isatra_2025_05_044 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-Jun-04 |
| PublicationDateYYYYMMDD | 2025-06-04 |
| PublicationDate_xml | – month: 06 year: 2025 text: 2025-Jun-04 day: 04 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | ISA transactions |
| PublicationTitleAlternate | ISA Trans |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Zhang, Xu, He, Zhu (bib0165) 2021; 109 Tian, He, Zhu (bib0160) 2020; 59 Yue, Wang, Zhu, Yuan, Yang (bib0045) 2024; 665 Yu, Zhang, Jiang, Yan (bib0035) 2024; 301 He, Lu, Zhu (bib0145) 2025; 21 Yuan, Huang, Ye, Wang, Wang, Yang (bib0150) 2024; 54 Zhao, Deng, Li (bib0020) 2023; 139 Wang, Chen, Hao, Cai, Wei (bib0110) 2025; 690 Lee, Kim, Maqsood, Moon, Rho (bib0120) 2024; 81 Cheng, Yu, Wang, Jiang, Cao (bib0055) 2024; 137 He, Li, Ma, Zhu, Lu (bib0060) 2023; 119 Liu, Wang, Wang, Yuan (bib0095) 2021; 104 Wang, Zhu, He (bib0040) 2024; 58 Zhang, Dong, Peng, Sun (bib0090) 2024; 257 Li, Xu, Zhu, He (bib0080) 2025 Zhang, Chen, Liu, Wu (bib0130) 2023; 128 Xu, Xie, Sun, Cao (bib0050) 2025; 155 Ren, Liu, Wan (bib0070) 2022; 198 Wang, Shao, Huang, Lu, Zhang, Chen (bib0135) 2022; 614 Kadlec, Gabrys, Strandt (bib0030) 2009; 33 Yuan, Huang, Wang, Yang, Gui (bib0065) 2018; 14 Tian, Xu, Zhu, He (bib0025) 2021; 70 Xiao, Qiu, Ha, Bani, Zhou, Sotiras (bib0125) 2025; 161 Zhou, Wang, Wang, Guan (bib0085) 2024; 680 Liu, Shi, Lu, Gao, Zhang (bib0140) 2024; 247 Yan, Tang, Lin (bib0170) 2016; 64 Xu, Zhu, Ke, He, Zhang, Xu (bib0005) 2025; 193 Jin, Dong, Qian, Wang, Yang, Chen (bib0010) 2025; 159 He, Wang, Zhu (bib0155) 2024; 20 Yin, Niu, He, Li, Lee (bib0105) 2020; 46 Tian, Zhu, He (bib0075) 2024; 20 Shao, Tian, Wang (bib0100) 2015; 23 Song, Zhang, Shi, He, Xu, Zhu (bib0015) 2024; 142 Chen, Xu, Zhu, He (bib0115) 2024; 73 Yin (10.1016/j.isatra.2025.05.044_bib0105) 2020; 46 He (10.1016/j.isatra.2025.05.044_bib0060) 2023; 119 Zhang (10.1016/j.isatra.2025.05.044_bib0130) 2023; 128 Jin (10.1016/j.isatra.2025.05.044_bib0010) 2025; 159 Wang (10.1016/j.isatra.2025.05.044_bib0135) 2022; 614 Xu (10.1016/j.isatra.2025.05.044_bib0050) 2025; 155 Wang (10.1016/j.isatra.2025.05.044_bib0040) 2024; 58 Zhang (10.1016/j.isatra.2025.05.044_bib0165) 2021; 109 Liu (10.1016/j.isatra.2025.05.044_bib0095) 2021; 104 Tian (10.1016/j.isatra.2025.05.044_bib0160) 2020; 59 Cheng (10.1016/j.isatra.2025.05.044_bib0055) 2024; 137 Shao (10.1016/j.isatra.2025.05.044_bib0100) 2015; 23 Liu (10.1016/j.isatra.2025.05.044_bib0140) 2024; 247 Tian (10.1016/j.isatra.2025.05.044_bib0025) 2021; 70 Yan (10.1016/j.isatra.2025.05.044_bib0170) 2016; 64 Li (10.1016/j.isatra.2025.05.044_bib0080) 2025 Song (10.1016/j.isatra.2025.05.044_bib0015) 2024; 142 Wang (10.1016/j.isatra.2025.05.044_bib0110) 2025; 690 Kadlec (10.1016/j.isatra.2025.05.044_bib0030) 2009; 33 Lee (10.1016/j.isatra.2025.05.044_bib0120) 2024; 81 Zhou (10.1016/j.isatra.2025.05.044_bib0085) 2024; 680 Xu (10.1016/j.isatra.2025.05.044_bib0005) 2025; 193 Yue (10.1016/j.isatra.2025.05.044_bib0045) 2024; 665 Zhao (10.1016/j.isatra.2025.05.044_bib0020) 2023; 139 Yuan (10.1016/j.isatra.2025.05.044_bib0065) 2018; 14 Tian (10.1016/j.isatra.2025.05.044_bib0075) 2024; 20 Chen (10.1016/j.isatra.2025.05.044_bib0115) 2024; 73 Ren (10.1016/j.isatra.2025.05.044_bib0070) 2022; 198 Yuan (10.1016/j.isatra.2025.05.044_bib0150) 2024; 54 Yu (10.1016/j.isatra.2025.05.044_bib0035) 2024; 301 Xiao (10.1016/j.isatra.2025.05.044_bib0125) 2025; 161 He (10.1016/j.isatra.2025.05.044_bib0155) 2024; 20 Zhang (10.1016/j.isatra.2025.05.044_bib0090) 2024; 257 He (10.1016/j.isatra.2025.05.044_bib0145) 2025; 21 |
| References_xml | – volume: 128 year: 2023 ident: bib0130 article-title: An intrusion detection method based on stacked sparse autoencoder and improved Gaussian mixture model publication-title: Comput Secur – volume: 690 year: 2025 ident: bib0110 article-title: A novel self-training framework for semi-supervised soft sensor modeling based on indeterminate variational autoencoder publication-title: Inf Sci (Ny) – volume: 20 start-page: 3748 year: 2024 end-page: 3755 ident: bib0155 article-title: Improved Bi-LSTM with distributed nonlinear extensions and parallel inputs for soft sensing publication-title: IEEE Trans Ind Inf – volume: 680 year: 2024 ident: bib0085 article-title: Predicting air quality using a multi-scale spatiotemporal graph attention network publication-title: Inf Sci (Ny) – volume: 198 year: 2022 ident: bib0070 article-title: VMD-SEAE-TL-based data-driven soft sensor modeling for a complex industrial batch processes publication-title: Measurement – volume: 46 year: 2020 ident: bib0105 article-title: Ensemble deep learning based semi-supervised soft sensor modeling method and its application on quality prediction for coal preparation process publication-title: Adv Eng Inf – volume: 59 start-page: 19361 year: 2020 end-page: 19369 ident: bib0160 article-title: Soft sensor development using improved whale optimization and regularization-based functional link neural network publication-title: Ind Eng Chem Res – volume: 14 start-page: 3235 year: 2018 end-page: 3243 ident: bib0065 article-title: Deep learning-based feature representation and its application for soft sensor modeling with variable-wise weighted SAE publication-title: IEEE Trans Ind Inf – volume: 119 year: 2023 ident: bib0060 article-title: Attribute-relevant distributed variational autoencoder integrated with LSTM for dynamic industrial soft sensing publication-title: Eng Appl Artif Intell – volume: 161 year: 2025 ident: bib0125 article-title: SC-VAE: sparse coding-based variational autoencoder with learned ISTA publication-title: Pattern Recognit – volume: 104 year: 2021 ident: bib0095 article-title: Deep learning with nonlocal and local structure preserving stacked autoencoder for soft sensor in industrial processes publication-title: Eng Appl Artif Intell – volume: 54 start-page: 2696 year: 2024 end-page: 2707 ident: bib0150 article-title: Quality prediction modeling for industrial processes using multiscale attention-based convolutional neural network publication-title: IEEE Trans Cybern – volume: 614 start-page: 416 year: 2022 end-page: 431 ident: bib0135 article-title: Deep locally linear embedding network publication-title: Inf Sci (Ny) – volume: 20 start-page: 596 year: 2024 end-page: 604 ident: bib0075 article-title: Novel deep layers-extended autoencoder with correlation and its industrial soft sensing publication-title: IEEE Trans Ind Inf – volume: 64 start-page: 4237 year: 2016 end-page: 4245 ident: bib0170 article-title: A data-driven soft sensor modeling method based on deep learning and its application publication-title: IEEE Trans Ind Electron – volume: 58 start-page: 97 year: 2024 end-page: 102 ident: bib0040 article-title: Novel distributed broad seasonal trend learning system for industrial soft sensing application publication-title: IFAC-PapersOnLine – volume: 23 start-page: 1925 year: 2015 end-page: 1934 ident: bib0100 article-title: Supervised local and non-local structure preserving projections with application to just-in-time learning for adaptive soft sensor publication-title: Chin J Chem Eng – volume: 73 start-page: 1 year: 2024 end-page: 9 ident: bib0115 article-title: Soft sensor enhancement for multimodal industrial process data: meta regression Gaussian mixture variational autoencoder publication-title: IEEE Trans Instrum Meas – volume: 139 start-page: 548 year: 2023 end-page: 560 ident: bib0020 article-title: A nonlinear industrial soft sensor modeling method based on locality preserving stochastic configuration network with utilizing unlabeled samples publication-title: ISA Trans – volume: 665 year: 2024 ident: bib0045 article-title: Spiking autoencoder for nonlinear industrial process fault detection publication-title: Inf Sci (Ny) – volume: 155 year: 2025 ident: bib0050 article-title: A novel soft sensor modeling method based on gated stacked target-supervised VAE with variable weights publication-title: Control Eng Pract – volume: 137 year: 2024 ident: bib0055 article-title: Semi-supervised soft sensor method for fermentation processes based on physical monotonicity and variational autoencoders publication-title: Eng Appl Artif Intell – volume: 21 start-page: 858 year: 2025 end-page: 865 ident: bib0145 article-title: Novel manifold autoencoder for industrial process fault diagnosis publication-title: IEEE Trans Ind Inf – volume: 257 year: 2024 ident: bib0090 article-title: Spatio-temporal feature extraction network based multi-performance indicators synergetic monitoring method for complex industrial processes publication-title: Expert Syst Appl – volume: 193 year: 2025 ident: bib0005 article-title: Virtual sample generation for soft-sensing in small sample scenarios using glow-embedded variational autoencoder publication-title: Comput Chem Eng – volume: 142 year: 2024 ident: bib0015 article-title: Quality-driven deep feature representation learning and its industrial application to soft sensors publication-title: J Process Control – start-page: 1 year: 2025 end-page: 12 ident: bib0080 article-title: Industrial data imputation based on multiscale spatiotemporal information embedding with asymmetrical transformer publication-title: IEEE Trans Neural Netw Learn Syst – volume: 81 start-page: 1275 year: 2024 end-page: 1300 ident: bib0120 article-title: Advancing autoencoder architectures for enhanced anomaly detection in multivariate industrial time series publication-title: Comput Mater Contin – volume: 70 start-page: 1 year: 2021 end-page: 10 ident: bib0025 article-title: Novel virtual sample generation using target-relevant autoencoder for small data-based soft sensor publication-title: IEEE Trans Instrum Meas – volume: 33 start-page: 795 year: 2009 end-page: 814 ident: bib0030 article-title: Data-driven soft sensors in the process industry publication-title: Comput Chem Eng – volume: 159 start-page: 293 year: 2025 end-page: 311 ident: bib0010 article-title: Soft sensor modeling using deep learning with maximum relevance and minimum redundancy for quality prediction of industrial processes publication-title: ISA Trans – volume: 301 year: 2024 ident: bib0035 article-title: Neural network-based hybrid modeling approach incorporating Bayesian optimization with industrial soft sensor application publication-title: Knowl-Based Syst – volume: 109 start-page: 229 year: 2021 end-page: 241 ident: bib0165 article-title: Novel manifold learning based virtual sample generation for optimizing soft sensor with small data publication-title: ISA Trans – volume: 247 year: 2024 ident: bib0140 article-title: A novel local linear embedding algorithm via local mutual representation for bearing fault diagnosis publication-title: Reliab Eng Syst Saf – volume: 119 year: 2023 ident: 10.1016/j.isatra.2025.05.044_bib0060 article-title: Attribute-relevant distributed variational autoencoder integrated with LSTM for dynamic industrial soft sensing publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2022.105737 – volume: 70 start-page: 1 year: 2021 ident: 10.1016/j.isatra.2025.05.044_bib0025 article-title: Novel virtual sample generation using target-relevant autoencoder for small data-based soft sensor publication-title: IEEE Trans Instrum Meas – volume: 198 year: 2022 ident: 10.1016/j.isatra.2025.05.044_bib0070 article-title: VMD-SEAE-TL-based data-driven soft sensor modeling for a complex industrial batch processes publication-title: Measurement doi: 10.1016/j.measurement.2022.111439 – start-page: 1 year: 2025 ident: 10.1016/j.isatra.2025.05.044_bib0080 article-title: Industrial data imputation based on multiscale spatiotemporal information embedding with asymmetrical transformer publication-title: IEEE Trans Neural Netw Learn Syst – volume: 159 start-page: 293 year: 2025 ident: 10.1016/j.isatra.2025.05.044_bib0010 article-title: Soft sensor modeling using deep learning with maximum relevance and minimum redundancy for quality prediction of industrial processes publication-title: ISA Trans doi: 10.1016/j.isatra.2025.02.010 – volume: 155 year: 2025 ident: 10.1016/j.isatra.2025.05.044_bib0050 article-title: A novel soft sensor modeling method based on gated stacked target-supervised VAE with variable weights publication-title: Control Eng Pract doi: 10.1016/j.conengprac.2024.106181 – volume: 14 start-page: 3235 issue: 7 year: 2018 ident: 10.1016/j.isatra.2025.05.044_bib0065 article-title: Deep learning-based feature representation and its application for soft sensor modeling with variable-wise weighted SAE publication-title: IEEE Trans Ind Inf doi: 10.1109/TII.2018.2809730 – volume: 54 start-page: 2696 issue: 5 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0150 article-title: Quality prediction modeling for industrial processes using multiscale attention-based convolutional neural network publication-title: IEEE Trans Cybern doi: 10.1109/TCYB.2024.3365068 – volume: 109 start-page: 229 year: 2021 ident: 10.1016/j.isatra.2025.05.044_bib0165 article-title: Novel manifold learning based virtual sample generation for optimizing soft sensor with small data publication-title: ISA Trans doi: 10.1016/j.isatra.2020.10.006 – volume: 59 start-page: 19361 issue: 43 year: 2020 ident: 10.1016/j.isatra.2025.05.044_bib0160 article-title: Soft sensor development using improved whale optimization and regularization-based functional link neural network publication-title: Ind Eng Chem Res doi: 10.1021/acs.iecr.0c03839 – volume: 665 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0045 article-title: Spiking autoencoder for nonlinear industrial process fault detection publication-title: Inf Sci (Ny) doi: 10.1016/j.ins.2024.120389 – volume: 690 year: 2025 ident: 10.1016/j.isatra.2025.05.044_bib0110 article-title: A novel self-training framework for semi-supervised soft sensor modeling based on indeterminate variational autoencoder publication-title: Inf Sci (Ny) doi: 10.1016/j.ins.2024.121565 – volume: 23 start-page: 1925 issue: 12 year: 2015 ident: 10.1016/j.isatra.2025.05.044_bib0100 article-title: Supervised local and non-local structure preserving projections with application to just-in-time learning for adaptive soft sensor publication-title: Chin J Chem Eng doi: 10.1016/j.cjche.2015.11.012 – volume: 33 start-page: 795 issue: 4 year: 2009 ident: 10.1016/j.isatra.2025.05.044_bib0030 article-title: Data-driven soft sensors in the process industry publication-title: Comput Chem Eng doi: 10.1016/j.compchemeng.2008.12.012 – volume: 247 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0140 article-title: A novel local linear embedding algorithm via local mutual representation for bearing fault diagnosis publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2024.110135 – volume: 104 year: 2021 ident: 10.1016/j.isatra.2025.05.044_bib0095 article-title: Deep learning with nonlocal and local structure preserving stacked autoencoder for soft sensor in industrial processes publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2021.104341 – volume: 614 start-page: 416 year: 2022 ident: 10.1016/j.isatra.2025.05.044_bib0135 article-title: Deep locally linear embedding network publication-title: Inf Sci (Ny) doi: 10.1016/j.ins.2022.10.036 – volume: 20 start-page: 596 issue: 1 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0075 article-title: Novel deep layers-extended autoencoder with correlation and its industrial soft sensing publication-title: IEEE Trans Ind Inf doi: 10.1109/TII.2023.3268745 – volume: 257 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0090 article-title: Spatio-temporal feature extraction network based multi-performance indicators synergetic monitoring method for complex industrial processes publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2024.125052 – volume: 20 start-page: 3748 issue: 3 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0155 article-title: Improved Bi-LSTM with distributed nonlinear extensions and parallel inputs for soft sensing publication-title: IEEE Trans Ind Inf doi: 10.1109/TII.2023.3313631 – volume: 142 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0015 article-title: Quality-driven deep feature representation learning and its industrial application to soft sensors publication-title: J Process Control doi: 10.1016/j.jprocont.2024.103300 – volume: 128 year: 2023 ident: 10.1016/j.isatra.2025.05.044_bib0130 article-title: An intrusion detection method based on stacked sparse autoencoder and improved Gaussian mixture model publication-title: Comput Secur doi: 10.1016/j.cose.2023.103144 – volume: 137 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0055 article-title: Semi-supervised soft sensor method for fermentation processes based on physical monotonicity and variational autoencoders publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2024.109065 – volume: 680 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0085 article-title: Predicting air quality using a multi-scale spatiotemporal graph attention network publication-title: Inf Sci (Ny) doi: 10.1016/j.ins.2024.121072 – volume: 81 start-page: 1275 issue: 1 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0120 article-title: Advancing autoencoder architectures for enhanced anomaly detection in multivariate industrial time series publication-title: Comput Mater Contin – volume: 64 start-page: 4237 issue: 5 year: 2016 ident: 10.1016/j.isatra.2025.05.044_bib0170 article-title: A data-driven soft sensor modeling method based on deep learning and its application publication-title: IEEE Trans Ind Electron doi: 10.1109/TIE.2016.2622668 – volume: 58 start-page: 97 issue: 14 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0040 article-title: Novel distributed broad seasonal trend learning system for industrial soft sensing application publication-title: IFAC-PapersOnLine doi: 10.1016/j.ifacol.2024.08.320 – volume: 46 year: 2020 ident: 10.1016/j.isatra.2025.05.044_bib0105 article-title: Ensemble deep learning based semi-supervised soft sensor modeling method and its application on quality prediction for coal preparation process publication-title: Adv Eng Inf doi: 10.1016/j.aei.2020.101136 – volume: 73 start-page: 1 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0115 article-title: Soft sensor enhancement for multimodal industrial process data: meta regression Gaussian mixture variational autoencoder publication-title: IEEE Trans Instrum Meas – volume: 139 start-page: 548 year: 2023 ident: 10.1016/j.isatra.2025.05.044_bib0020 article-title: A nonlinear industrial soft sensor modeling method based on locality preserving stochastic configuration network with utilizing unlabeled samples publication-title: ISA Trans doi: 10.1016/j.isatra.2023.04.012 – volume: 301 year: 2024 ident: 10.1016/j.isatra.2025.05.044_bib0035 article-title: Neural network-based hybrid modeling approach incorporating Bayesian optimization with industrial soft sensor application publication-title: Knowl-Based Syst doi: 10.1016/j.knosys.2024.112341 – volume: 161 year: 2025 ident: 10.1016/j.isatra.2025.05.044_bib0125 article-title: SC-VAE: sparse coding-based variational autoencoder with learned ISTA publication-title: Pattern Recognit doi: 10.1016/j.patcog.2024.111187 – volume: 21 start-page: 858 issue: 1 year: 2025 ident: 10.1016/j.isatra.2025.05.044_bib0145 article-title: Novel manifold autoencoder for industrial process fault diagnosis publication-title: IEEE Trans Ind Inf doi: 10.1109/TII.2024.3465597 – volume: 193 year: 2025 ident: 10.1016/j.isatra.2025.05.044_bib0005 article-title: Virtual sample generation for soft-sensing in small sample scenarios using glow-embedded variational autoencoder publication-title: Comput Chem Eng doi: 10.1016/j.compchemeng.2024.108925 |
| SSID | ssj0002598 |
| Score | 2.3936214 |
| Snippet | Data-driven industrial soft sensor modeling techniques have been widely applied in predicting key variables in complex industrial processes. However, with... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Publisher |
| SubjectTerms | Data-driven modelling Industrial processes Industrial soft sensors Local features |
| Title | Novel semi-supervised sparse stacked autoencoder integrated with local linear embedding for industrial soft sensing |
| URI | https://dx.doi.org/10.1016/j.isatra.2025.05.044 https://www.ncbi.nlm.nih.gov/pubmed/40517087 https://www.proquest.com/docview/3218775675 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1879-2022 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002598 issn: 0019-0578 databaseCode: AIEXJ dateStart: 19950301 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1ba9swGBVpuoftYazdrbsUDcbYCC6ub5Ifw0hJS8gGS4f7MqFICri0ThbHoT9_n25Ot1DWPQwSExQ7NjnHn47kT-dD6P1UUq26wyCd6dmqhIqAxyoPVAhqOZlFXJoqEd9HZDymRZF_7XR--LUw6ytSVfTmJl_8V6ihDcDWS2f_Ae72R6EBPgPosAXYYXsv4Mfztbrq1eq6DOpmoUNBDaISAsey1m6yHG5b2ePNaq4tLLWTROsY4RLRTffW0_KTL3vqeqqk9OmW5abQRw3xG85S1b7vcwr39Ftf153wRchbyT40M6cXvApGZUvIs9JNV180bSIQN5O3w6YM4O1bi8bu5bjspimi1KRTJbciKyU54GQXIR-p7batWG6nFS5NWtNSW0RFqTFZtX6Rv1tnj7-wk_PRiE0GxeTD4megq4rpp--uxMoO2o1ImtMu2u2fDoqztq-GwZ9ZLOkvxC-uNBmA2ye-S7zcNTgxImXyBD12owvct6zYQx1V7aNHtzwn99Gei-Y1_ugsxz89RbUhDf6DNNiSBjvS4FukwRvSYE0abEiDLWlwSxoMpMEb0mBNGuxI8wydnwwmn4eBK8cRiCiiq0BwyUE-xzJOVS6mscinmZCZyKagMRMicioiDnd7ROEbxUH4HscwGA25UpTLSMbPUbeaV-olwjQEUTRT2SxWKlFRyGfHeS5inhHQo5lMDlDg_2e2sK4rzKcjXjKLC9O4sBBeCexPPBjMKUerCBmQ6S9HvvPYMQis-mkZr9S8qVkM4peQFAbUB-iFBbW9lkQ724WUvLrH0a_Rw8398AZ1V8tGvUUPxHpV1stDtEMKeuho-QvZLafk |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Novel+semi-supervised+sparse+stacked+autoencoder+integrated+with+local+linear+embedding+for+industrial+soft+sensing&rft.jtitle=ISA+transactions&rft.au=He%2C+Yan-Lin&rft.au=Jiang%2C+Yu&rft.au=Gao%2C+Hui-Hui&rft.au=Xu%2C+Yuan&rft.date=2025-06-04&rft.issn=1879-2022&rft.eissn=1879-2022&rft_id=info:doi/10.1016%2Fj.isatra.2025.05.044&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0019-0578&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0019-0578&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0019-0578&client=summon |