Deep quality-related feature extraction for soft sensing modeling: A deep learning approach with hybrid VW-SAE
Soft sensors have been extensively used to predict difficult-to-measure quality variables for effective modeling, control and optimization of industrial processes. To construct accurate soft sensors, it is significant to carry out feature extraction for massive high-dimensional process data. Recentl...
Saved in:
| Published in: | Neurocomputing (Amsterdam) Vol. 396; pp. 375 - 382 |
|---|---|
| Main Authors: | , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier B.V
05.07.2020
|
| Subjects: | |
| ISSN: | 0925-2312, 1872-8286 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Soft sensors have been extensively used to predict difficult-to-measure quality variables for effective modeling, control and optimization of industrial processes. To construct accurate soft sensors, it is significant to carry out feature extraction for massive high-dimensional process data. Recently, deep learning has been introduced for feature representation in process data modeling. However, most of them cannot capture deep quality-related features for output prediction. In this paper, a hybrid variable-wise weighted stacked autoencoder (HVW-SAE) is developed to learn quality-related features for soft sensor modeling. By measuring the linear Pearson and nonlinear Spearman correlations for variables at the input layer with the quality variable at each encoder, a corresponding weighted reconstruction objective function is designed to successively pretrain the deep networks. With the constraint of preferential reconstruction for more quality-related variables, it can ensure that the learned features contain more information for quality prediction. Finally, the effectiveness of the proposed HVW-SAE based soft sensor method is validated on an industrial debutanizer column process. |
|---|---|
| AbstractList | Soft sensors have been extensively used to predict difficult-to-measure quality variables for effective modeling, control and optimization of industrial processes. To construct accurate soft sensors, it is significant to carry out feature extraction for massive high-dimensional process data. Recently, deep learning has been introduced for feature representation in process data modeling. However, most of them cannot capture deep quality-related features for output prediction. In this paper, a hybrid variable-wise weighted stacked autoencoder (HVW-SAE) is developed to learn quality-related features for soft sensor modeling. By measuring the linear Pearson and nonlinear Spearman correlations for variables at the input layer with the quality variable at each encoder, a corresponding weighted reconstruction objective function is designed to successively pretrain the deep networks. With the constraint of preferential reconstruction for more quality-related variables, it can ensure that the learned features contain more information for quality prediction. Finally, the effectiveness of the proposed HVW-SAE based soft sensor method is validated on an industrial debutanizer column process. |
| Author | Gui, Weihua Yuan, Xiaofeng Wang, Yalin Yang, Chunhua Ou, Chen |
| Author_xml | – sequence: 1 givenname: Xiaofeng orcidid: 0000-0002-9072-7179 surname: Yuan fullname: Yuan, Xiaofeng email: yuanxf@csu.edu.cn – sequence: 2 givenname: Chen surname: Ou fullname: Ou, Chen – sequence: 3 givenname: Yalin surname: Wang fullname: Wang, Yalin – sequence: 4 givenname: Chunhua surname: Yang fullname: Yang, Chunhua – sequence: 5 givenname: Weihua surname: Gui fullname: Gui, Weihua |
| BookMark | eNqFkMtqHDEQRUWwIWM7f5CFfqDHKvVD3V4EBj_igMELO8lS6FHKaOiRxpImyfy9u5mssrBXVdziXKhzRk5CDEjIZ2BLYNBdbpYB9yZul5xBvwSYUvGBLKAXvOp5352QBRt4W_Ea-EdylvOGMRDAhwUJN4g7-rJXoy-HKuGoClrqUJV9Qop_S1Km-Bioi4nm6ArNGLIPv-g2Whyn5YquqJ1LRlQpzBe126WozJr-8WVN1wedvKU_flZPq9sLcurUmPHTv3lOvt_dPl_fVw-PX79drx4qU7OuVA1orXvNWyc4YtMMznagbQsaUKAwyvaDahvhDBt05zpbG6uEalnPnLZ1W5-T5thrUsw5oZO75LcqHSQwOTuTG3l0JmdnEmBKxYRd_YcZX9T8_-TBj-_BX44wTo_99phkNh6DQesTmiJt9G8XvAKieY9J |
| CitedBy_id | crossref_primary_10_1016_j_chemolab_2020_104050 crossref_primary_10_1109_JSEN_2023_3274156 crossref_primary_10_3390_pr8091079 crossref_primary_10_1016_j_neucom_2020_12_028 crossref_primary_10_1109_JSEN_2024_3375072 crossref_primary_10_1109_TII_2023_3323675 crossref_primary_10_1109_TNNLS_2019_2951708 crossref_primary_10_3390_s19235255 crossref_primary_10_1109_JSEN_2022_3147306 crossref_primary_10_1002_cjce_25084 crossref_primary_10_1016_j_isatra_2025_02_010 crossref_primary_10_1109_JSEN_2024_3420124 crossref_primary_10_1155_2020_6347625 crossref_primary_10_1109_TIM_2021_3092784 crossref_primary_10_1007_s11633_022_1401_9 crossref_primary_10_1109_TIM_2021_3073702 crossref_primary_10_1016_j_conengprac_2020_104614 crossref_primary_10_1016_j_measurement_2024_114749 crossref_primary_10_1016_j_measurement_2022_111439 crossref_primary_10_1109_TIM_2022_3200088 crossref_primary_10_1109_TIM_2025_3548073 crossref_primary_10_1109_TIM_2022_3214611 crossref_primary_10_1109_TII_2021_3065377 crossref_primary_10_1016_j_asoc_2021_108321 crossref_primary_10_1016_j_neucom_2021_07_086 crossref_primary_10_1109_TIE_2020_2984443 crossref_primary_10_1109_TII_2022_3221219 crossref_primary_10_1109_ACCESS_2023_3334012 crossref_primary_10_1002_apj_2406 crossref_primary_10_1016_j_compchemeng_2020_106964 crossref_primary_10_1155_2021_1497964 crossref_primary_10_1109_TIM_2020_3035464 crossref_primary_10_1016_j_mineng_2023_108179 crossref_primary_10_1109_TASE_2023_3279575 crossref_primary_10_1109_TIM_2020_2977793 crossref_primary_10_1109_ACCESS_2021_3077958 crossref_primary_10_1002_cem_3225 crossref_primary_10_1016_j_ins_2022_02_049 crossref_primary_10_1109_TIM_2024_3502784 crossref_primary_10_1016_j_cherd_2022_01_026 crossref_primary_10_1109_TII_2019_2959784 crossref_primary_10_1109_TIM_2020_2985614 crossref_primary_10_1002_cem_3185 crossref_primary_10_1016_j_asoc_2023_110608 crossref_primary_10_1016_j_psep_2024_08_023 crossref_primary_10_1109_JSEN_2020_3025805 crossref_primary_10_1016_j_conengprac_2024_106143 crossref_primary_10_1016_j_jtice_2025_106328 crossref_primary_10_1109_TII_2024_3371990 crossref_primary_10_1016_j_measurement_2024_116025 crossref_primary_10_1016_j_measurement_2023_113477 crossref_primary_10_1088_1361_6501_ab7bbd crossref_primary_10_1109_TII_2019_2938890 crossref_primary_10_1002_cem_3529 crossref_primary_10_1109_TCYB_2021_3059002 crossref_primary_10_1002_apj_70048 crossref_primary_10_1002_cjce_70039 crossref_primary_10_1088_1361_6501_ad7483 crossref_primary_10_1109_TIM_2022_3152856 crossref_primary_10_1109_TIM_2022_3225004 crossref_primary_10_1007_s00521_024_09752_5 crossref_primary_10_1016_j_jprocont_2020_05_015 crossref_primary_10_1016_j_engappai_2022_105180 crossref_primary_10_1016_j_conengprac_2019_104187 crossref_primary_10_1016_j_jtice_2024_105666 crossref_primary_10_1016_j_rsase_2021_100643 crossref_primary_10_3390_s21103430 crossref_primary_10_1016_j_jclepro_2024_144132 crossref_primary_10_1016_j_engappai_2023_105988 crossref_primary_10_1109_TII_2021_3110507 crossref_primary_10_1109_TITS_2022_3154750 crossref_primary_10_1109_TNNLS_2019_2957366 crossref_primary_10_3390_s21248471 crossref_primary_10_1016_j_compchemeng_2023_108543 crossref_primary_10_1016_j_neucom_2019_08_006 crossref_primary_10_3390_pr12030495 crossref_primary_10_1088_1361_6501_aba6b9 crossref_primary_10_1109_ACCESS_2023_3336424 crossref_primary_10_1109_JSEN_2025_3580404 crossref_primary_10_1109_TII_2022_3220857 crossref_primary_10_1016_j_asoc_2022_108898 crossref_primary_10_1016_j_istruc_2021_02_069 crossref_primary_10_1016_j_measurement_2023_113491 |
| Cites_doi | 10.1109/TNNLS.2016.2599820 10.1109/TIP.2017.2781299 10.1109/TIE.2018.2803727 10.1109/TCST.2016.2579609 10.1109/TII.2015.2509247 10.1109/TIM.2018.2810678 10.1109/TIM.2017.2658158 10.1002/aic.14663 10.1109/TIE.2017.2739691 10.1109/ACCESS.2017.2756872 10.1109/TCYB.2016.2536638 10.1109/TII.2016.2610839 10.1016/j.jprocont.2017.06.002 10.1109/TCST.2016.2550426 10.1109/TIE.2017.2698422 10.1109/TII.2018.2809730 10.1016/j.jprocont.2013.05.007 10.1016/j.conengprac.2004.04.013 10.1016/j.compchemeng.2008.12.012 10.1109/TII.2016.2612640 10.1016/j.compchemeng.2008.05.019 10.1109/TIE.2017.2733501 10.1002/cem.3040 10.1109/TIE.2015.2466557 10.1021/ie4041252 10.1109/TIE.2017.2733443 10.1016/j.jprocont.2013.03.008 10.1109/TIM.2006.887331 |
| ContentType | Journal Article |
| Copyright | 2019 Elsevier B.V. |
| Copyright_xml | – notice: 2019 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.neucom.2018.11.107 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-8286 |
| EndPage | 382 |
| ExternalDocumentID | 10_1016_j_neucom_2018_11_107 S0925231219304503 |
| GroupedDBID | --- --K --M .DC .~1 0R~ 123 1B1 1~. 1~5 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXLA AAXUO AAYFN ABBOA ABCQJ ABFNM ABJNI ABMAC ABYKQ ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE AEBSH AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W KOM LG9 M41 MO0 MOBAO N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SDP SES SPC SPCBC SSN SSV SSZ T5K ZMT ~G- 29N 9DU AAQXK AATTM AAXKI AAYWO AAYXX ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD FEDTE FGOYB HLZ HVGLF HZ~ R2- SBC SEW WUQ XPP ~HD |
| ID | FETCH-LOGICAL-c306t-41bbb8b25f72ee449fd61bd51b1e7e7cad89a547fc09b6f6d3cda7a5080fbd353 |
| ISICitedReferencesCount | 94 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000536806600014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0925-2312 |
| IngestDate | Sat Nov 29 07:19:26 EST 2025 Tue Nov 18 22:30:01 EST 2025 Fri Feb 23 02:47:56 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Stacked autoencoder (SAE) Soft sensor Hybrid variable-wise weighted SAE (HVW-SAE) Feature representation |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c306t-41bbb8b25f72ee449fd61bd51b1e7e7cad89a547fc09b6f6d3cda7a5080fbd353 |
| ORCID | 0000-0002-9072-7179 |
| PageCount | 8 |
| ParticipantIDs | crossref_primary_10_1016_j_neucom_2018_11_107 crossref_citationtrail_10_1016_j_neucom_2018_11_107 elsevier_sciencedirect_doi_10_1016_j_neucom_2018_11_107 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-07-05 |
| PublicationDateYYYYMMDD | 2020-07-05 |
| PublicationDate_xml | – month: 07 year: 2020 text: 2020-07-05 day: 05 |
| PublicationDecade | 2020 |
| PublicationTitle | Neurocomputing (Amsterdam) |
| PublicationYear | 2020 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Yu, Hong, Rui, Tao (bib0026) 2018; 65 Samek, Binder, Montavon, Lapuschkin, Muller (bib0028) 2016; 28 Chen, Ding, Peng, Yang, Gui (bib0012) 2018; 65 Fortuna, Graziani, Rizzo, Xibilia (bib0035) 2007 Fortuna, Graziani, Xibilia (bib0034) 2005; 13 Ge, Chen (bib0002) 2017; 12 Jia, Shao, Li, Zhao, Fu (bib0031) 2018 Yuan, Huang, Wang, Yang, Gui (bib0032) 2018; 14 Hauke, Kossowski (bib0033) 2011; 30 Bengio, Lamblin, Popovici, Larocchelle (bib0025) 2006 Liu, Chen (bib0018) 2013; 23 Majumdar, Tripathi (bib0029) 2017 Lee, Chang (bib0027) 2016; 13 Huang, Qi, Murshed (bib0014) 2012 Jiang, Ding, Wang, Yan (bib0004) 2017; 64 Yuan, Wang, Yang, Gui, Ye (bib0013) 2017; 57 Yuan, Ge, Huang, Song (bib0017) 2017; 25 Yuan, Li, Wang (bib0007) 2019 Kadlec, Gabrys, Strandt (bib0006) 2009; 33 Yuan, Zhou, Wang, Yang (bib0020) 2018; 32 Ge, Song, Ding, Huang (bib0009) 2017; 5 Zhou, Zheng, Ge, Song, Shan (bib0003) 2018; 65 Ma, Khatibisepehr, Huang (bib0016) 2014; 61 Khatibisepehr, Huang, Khare (bib0005) 2013; 23 Gonzaga, Meleiro, Kiang, Maciel Filho (bib0019) 2009; 33 Yuan, Ge, Huang, Song, Wang (bib0015) 2017; 13 Jiang, Yan, Huang (bib0010) 2016; 63 Yuan, Ge, Song, Wang, Yang, Zhang (bib0008) 2017; 66 Zhou, Li, Song, Qin (bib0011) 2017; 25 Chen, Dai, Yuan, Gui, Ren, Koivo (bib0021) 2018; 67 Du, Xiong, Wu, Zhang, Zhang, Tao (bib0030) 2016; 47 Yuan, Ge, Song (bib0022) 2014; 53 Rosipal, Trejo (bib0023) 2002; 2 Fortuna, Giannone, Graziani, Xibilia (bib0024) 2007; 56 Yuan, Wang, Yang, Ge, Song, Gui (bib0001) 2018; 65 Gonzaga (10.1016/j.neucom.2018.11.107_bib0019) 2009; 33 Du (10.1016/j.neucom.2018.11.107_bib0030) 2016; 47 Yuan (10.1016/j.neucom.2018.11.107_bib0017) 2017; 25 Yuan (10.1016/j.neucom.2018.11.107_bib0007) 2019 Yu (10.1016/j.neucom.2018.11.107_bib0026) 2018; 65 Yuan (10.1016/j.neucom.2018.11.107_bib0020) 2018; 32 Jiang (10.1016/j.neucom.2018.11.107_bib0010) 2016; 63 Chen (10.1016/j.neucom.2018.11.107_bib0021) 2018; 67 Jiang (10.1016/j.neucom.2018.11.107_bib0004) 2017; 64 Jia (10.1016/j.neucom.2018.11.107_bib0031) 2018 Rosipal (10.1016/j.neucom.2018.11.107_bib0023) 2002; 2 Ge (10.1016/j.neucom.2018.11.107_bib0002) 2017; 12 Fortuna (10.1016/j.neucom.2018.11.107_bib0035) 2007 Ge (10.1016/j.neucom.2018.11.107_bib0009) 2017; 5 Samek (10.1016/j.neucom.2018.11.107_bib0028) 2016; 28 Majumdar (10.1016/j.neucom.2018.11.107_bib0029) 2017 Fortuna (10.1016/j.neucom.2018.11.107_bib0034) 2005; 13 Huang (10.1016/j.neucom.2018.11.107_bib0014) 2012 Bengio (10.1016/j.neucom.2018.11.107_bib0025) 2006 Lee (10.1016/j.neucom.2018.11.107_bib0027) 2016; 13 Yuan (10.1016/j.neucom.2018.11.107_bib0015) 2017; 13 Liu (10.1016/j.neucom.2018.11.107_bib0018) 2013; 23 Fortuna (10.1016/j.neucom.2018.11.107_bib0024) 2007; 56 Yuan (10.1016/j.neucom.2018.11.107_bib0001) 2018; 65 Yuan (10.1016/j.neucom.2018.11.107_bib0032) 2018; 14 Kadlec (10.1016/j.neucom.2018.11.107_bib0006) 2009; 33 Chen (10.1016/j.neucom.2018.11.107_bib0012) 2018; 65 Yuan (10.1016/j.neucom.2018.11.107_bib0013) 2017; 57 Ma (10.1016/j.neucom.2018.11.107_bib0016) 2014; 61 Hauke (10.1016/j.neucom.2018.11.107_bib0033) 2011; 30 Zhou (10.1016/j.neucom.2018.11.107_bib0011) 2017; 25 Yuan (10.1016/j.neucom.2018.11.107_bib0008) 2017; 66 Zhou (10.1016/j.neucom.2018.11.107_bib0003) 2018; 65 Khatibisepehr (10.1016/j.neucom.2018.11.107_bib0005) 2013; 23 Yuan (10.1016/j.neucom.2018.11.107_bib0022) 2014; 53 |
| References_xml | – volume: 33 start-page: 795 year: 2009 end-page: 814 ident: bib0006 article-title: Data-driven soft sensors in the process industry publication-title: Comput. Chem. Eng. – year: 2012 ident: bib0014 article-title: Dynamic modelling and predictive control in solid oxide fuel cells: First principle and data-based approaches – year: 2019 ident: bib0007 article-title: Nonlinear dynamic soft sensor modeling with supervised long short-term memory network publication-title: IEEE. T. Ind. Inf. – year: 2007 ident: bib0035 article-title: Soft Sensors for Monitoring and Control of Industrial Processes – start-page: 1878 year: 2018 end-page: 1887 ident: bib0031 article-title: Stacked denoising tensor auto-encoder for action recognition with spatiotemporal corruptions publication-title: IEEE Trans. Image Process. – volume: 64 start-page: 8148 year: 2017 end-page: 8157 ident: bib0004 article-title: Data-driven distributed local fault detection for large-scale processes based on GA-regularized Canonical Correlation analysis publication-title: IEEE Trans. Ind. Electron. – volume: 65 start-page: 1559 year: 2018 end-page: 1567 ident: bib0012 article-title: Fault detection for non-gaussian processes using generalized canonical correlation analysis and randomized algorithms publication-title: IEEE Trans. Ind. Electron. – volume: 32 start-page: e3040 year: 2018 ident: bib0020 article-title: Multi-similarity measurement driven ensemble just-in-time learning for soft sensing of industrial processes publication-title: J. Chemom. – volume: 14 start-page: 3235 year: 2018 end-page: 3243 ident: bib0032 article-title: Deep learning based feature representation and its application for soft sensor modeling with variable-wise weighted SAE publication-title: IEEE Trans. Ind. Inform. – volume: 23 start-page: 793 year: 2013 end-page: 804 ident: bib0018 article-title: Integrated soft sensor using just-in-time support vector regression and probabilistic analysis for quality prediction of multi-grade processes publication-title: J. Process Control – volume: 65 start-page: 8184 year: 2018 end-page: 8194 ident: bib0003 article-title: Multimode process monitoring based on switching autoregressive dynamic latent variable model publication-title: IEEE Trans. Ind. Electron. – volume: 66 start-page: 837 year: 2017 end-page: 845 ident: bib0008 article-title: Soft sensor modeling of nonlinear industrial processes based on weighted probabilistic projection regression publication-title: IEEE Trans. Instrum. Meas. – volume: 25 start-page: 1124 year: 2017 end-page: 1132 ident: bib0017 article-title: A probabilistic just-in-time learning framework for soft sensor development with missing data publication-title: IEEE Trans. Control Syst. Technol. – volume: 13 start-page: 499 year: 2005 end-page: 508 ident: bib0034 article-title: Soft sensors for product quality monitoring in debutanizer distillation columns publication-title: Control Eng. Pract. – volume: 57 start-page: 15 year: 2017 end-page: 25 ident: bib0013 article-title: Probabilistic density-based regression model for soft sensing of nonlinear industrial processes publication-title: J. Process Control – volume: 23 start-page: 1575 year: 2013 end-page: 1596 ident: bib0005 article-title: Design of inferential sensors in the process industry: a review of Bayesian methods publication-title: J. Process Control – volume: 61 start-page: 518 year: 2014 end-page: 529 ident: bib0016 article-title: A Bayesian framework for real‐time identification of locally weighted partial least squares publication-title: AIChE J. – volume: 2 start-page: 97 year: 2002 end-page: 123 ident: bib0023 article-title: Kernel partial least squares regression in reproducing kernel Hilbert space publication-title: J. Mach. Learn. Res. – volume: 28 start-page: 2660 year: 2016 end-page: 2673 ident: bib0028 article-title: Evaluating the visualization of what a deep neural network has learned publication-title: IEEE Trans. Neural Netw. Learn. Systems. – volume: 53 start-page: 13736 year: 2014 end-page: 13749 ident: bib0022 article-title: Locally weighted kernel principal component regression model for soft sensing of nonlinear time-variant processes publication-title: Ind. Eng. Chem. Res. – volume: 56 start-page: 95 year: 2007 end-page: 101 ident: bib0024 article-title: Virtual instruments based on stacked neural networks to improve product quality monitoring in a refinery publication-title: IEEE Trans. Instrum. Meas. – volume: 30 start-page: 87 year: 2011 end-page: 93 ident: bib0033 article-title: Comparison of values of pearson's and spearman's correlation coefficients on the same sets of data publication-title: Quaest. Geogr. – volume: 13 start-page: 532 year: 2017 end-page: 541 ident: bib0015 article-title: Semisupervised JITL framework for nonlinear industrial soft sensing based on locally semisupervised weighted PCR publication-title: IEEE Trans. Ind. Inform. – volume: 65 start-page: 5060 year: 2018 end-page: 5068 ident: bib0026 article-title: Multi-task autoencoder model for recovering human poses publication-title: IEEE Trans. Ind. Electron. – start-page: 911 year: 2017 end-page: 918 ident: bib0029 article-title: Asymmetric stacked autoencoder publication-title: Proceedings of the International Joint Conference on Neural Networks – volume: 13 start-page: 461 year: 2016 end-page: 472 ident: bib0027 article-title: Oscillometric blood pressure estimation based on deep learning publication-title: IEEE Trans. Ind. Inform. – volume: 67 start-page: 2001 year: 2018 end-page: 2010 ident: bib0021 article-title: Temperature prediction model for roller kiln by ALD-based double locally weighted kernel principal component regression publication-title: IEEE Trans. Instrum. Meas. – volume: 65 start-page: 1508 year: 2018 end-page: 1517 ident: bib0001 article-title: Weighted linear dynamic system for feature representation and soft sensor application in nonlinear dynamic industrial processes publication-title: IEEE Trans. Ind. Electron. – volume: 33 start-page: 43 year: 2009 end-page: 49 ident: bib0019 article-title: ANN-based soft-sensor for real-time process monitoring and control of an industrial polymerization process publication-title: Comput. Chem. Eng. – start-page: 153 year: 2006 end-page: 160 ident: bib0025 article-title: Greedy layer-wise training of deep networks publication-title: Proceedings of the International Conference on Neural Information Processing Systems – volume: 47 start-page: 1017 year: 2016 end-page: 1027 ident: bib0030 article-title: Stacked convolutional denoising auto-encoders for feature representation publication-title: IEEE Trans. Cybern. – volume: 12 start-page: 310 year: 2017 end-page: 321 ident: bib0002 article-title: Plant-wide industrial process monitoring: a distributed modeling framework publication-title: IEEE Trans. Ind. Inform. – volume: 63 start-page: 377 year: 2016 end-page: 386 ident: bib0010 article-title: Performance-driven distributed PCA process monitoring based on fault-relevant variable selection and bayesian inference publication-title: IEEE Trans. Ind. Electron. – volume: 5 start-page: 20590 year: 2017 end-page: 20616 ident: bib0009 article-title: Data mining and analytics in the process industry: the role of machine learning publication-title: IEEE Access – volume: 25 start-page: 366 year: 2017 end-page: 373 ident: bib0011 article-title: Autoregressive dynamic latent variable models for process monitoring publication-title: IEEE Trans. Control Syst. Technol. – volume: 28 start-page: 2660 year: 2016 ident: 10.1016/j.neucom.2018.11.107_bib0028 article-title: Evaluating the visualization of what a deep neural network has learned publication-title: IEEE Trans. Neural Netw. Learn. Systems. doi: 10.1109/TNNLS.2016.2599820 – start-page: 1878 year: 2018 ident: 10.1016/j.neucom.2018.11.107_bib0031 article-title: Stacked denoising tensor auto-encoder for action recognition with spatiotemporal corruptions publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2017.2781299 – volume: 65 start-page: 8184 year: 2018 ident: 10.1016/j.neucom.2018.11.107_bib0003 article-title: Multimode process monitoring based on switching autoregressive dynamic latent variable model publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2018.2803727 – volume: 25 start-page: 1124 year: 2017 ident: 10.1016/j.neucom.2018.11.107_bib0017 article-title: A probabilistic just-in-time learning framework for soft sensor development with missing data publication-title: IEEE Trans. Control Syst. Technol. doi: 10.1109/TCST.2016.2579609 – volume: 12 start-page: 310 year: 2017 ident: 10.1016/j.neucom.2018.11.107_bib0002 article-title: Plant-wide industrial process monitoring: a distributed modeling framework publication-title: IEEE Trans. Ind. Inform. doi: 10.1109/TII.2015.2509247 – volume: 67 start-page: 2001 year: 2018 ident: 10.1016/j.neucom.2018.11.107_bib0021 article-title: Temperature prediction model for roller kiln by ALD-based double locally weighted kernel principal component regression publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2018.2810678 – volume: 66 start-page: 837 year: 2017 ident: 10.1016/j.neucom.2018.11.107_bib0008 article-title: Soft sensor modeling of nonlinear industrial processes based on weighted probabilistic projection regression publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2017.2658158 – volume: 61 start-page: 518 year: 2014 ident: 10.1016/j.neucom.2018.11.107_bib0016 article-title: A Bayesian framework for real‐time identification of locally weighted partial least squares publication-title: AIChE J. doi: 10.1002/aic.14663 – volume: 65 start-page: 5060 year: 2018 ident: 10.1016/j.neucom.2018.11.107_bib0026 article-title: Multi-task autoencoder model for recovering human poses publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2017.2739691 – volume: 5 start-page: 20590 year: 2017 ident: 10.1016/j.neucom.2018.11.107_bib0009 article-title: Data mining and analytics in the process industry: the role of machine learning publication-title: IEEE Access doi: 10.1109/ACCESS.2017.2756872 – volume: 2 start-page: 97 year: 2002 ident: 10.1016/j.neucom.2018.11.107_bib0023 article-title: Kernel partial least squares regression in reproducing kernel Hilbert space publication-title: J. Mach. Learn. Res. – volume: 47 start-page: 1017 year: 2016 ident: 10.1016/j.neucom.2018.11.107_bib0030 article-title: Stacked convolutional denoising auto-encoders for feature representation publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2016.2536638 – volume: 13 start-page: 532 year: 2017 ident: 10.1016/j.neucom.2018.11.107_bib0015 article-title: Semisupervised JITL framework for nonlinear industrial soft sensing based on locally semisupervised weighted PCR publication-title: IEEE Trans. Ind. Inform. doi: 10.1109/TII.2016.2610839 – volume: 57 start-page: 15 year: 2017 ident: 10.1016/j.neucom.2018.11.107_bib0013 article-title: Probabilistic density-based regression model for soft sensing of nonlinear industrial processes publication-title: J. Process Control doi: 10.1016/j.jprocont.2017.06.002 – start-page: 153 year: 2006 ident: 10.1016/j.neucom.2018.11.107_bib0025 article-title: Greedy layer-wise training of deep networks – volume: 25 start-page: 366 year: 2017 ident: 10.1016/j.neucom.2018.11.107_bib0011 article-title: Autoregressive dynamic latent variable models for process monitoring publication-title: IEEE Trans. Control Syst. Technol. doi: 10.1109/TCST.2016.2550426 – volume: 64 start-page: 8148 year: 2017 ident: 10.1016/j.neucom.2018.11.107_bib0004 article-title: Data-driven distributed local fault detection for large-scale processes based on GA-regularized Canonical Correlation analysis publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2017.2698422 – volume: 14 start-page: 3235 year: 2018 ident: 10.1016/j.neucom.2018.11.107_bib0032 article-title: Deep learning based feature representation and its application for soft sensor modeling with variable-wise weighted SAE publication-title: IEEE Trans. Ind. Inform. doi: 10.1109/TII.2018.2809730 – volume: 23 start-page: 1575 year: 2013 ident: 10.1016/j.neucom.2018.11.107_bib0005 article-title: Design of inferential sensors in the process industry: a review of Bayesian methods publication-title: J. Process Control doi: 10.1016/j.jprocont.2013.05.007 – volume: 13 start-page: 499 year: 2005 ident: 10.1016/j.neucom.2018.11.107_bib0034 article-title: Soft sensors for product quality monitoring in debutanizer distillation columns publication-title: Control Eng. Pract. doi: 10.1016/j.conengprac.2004.04.013 – volume: 33 start-page: 795 year: 2009 ident: 10.1016/j.neucom.2018.11.107_bib0006 article-title: Data-driven soft sensors in the process industry publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2008.12.012 – volume: 13 start-page: 461 year: 2016 ident: 10.1016/j.neucom.2018.11.107_bib0027 article-title: Oscillometric blood pressure estimation based on deep learning publication-title: IEEE Trans. Ind. Inform. doi: 10.1109/TII.2016.2612640 – volume: 33 start-page: 43 year: 2009 ident: 10.1016/j.neucom.2018.11.107_bib0019 article-title: ANN-based soft-sensor for real-time process monitoring and control of an industrial polymerization process publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2008.05.019 – volume: 65 start-page: 1559 year: 2018 ident: 10.1016/j.neucom.2018.11.107_bib0012 article-title: Fault detection for non-gaussian processes using generalized canonical correlation analysis and randomized algorithms publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2017.2733501 – year: 2012 ident: 10.1016/j.neucom.2018.11.107_bib0014 – year: 2019 ident: 10.1016/j.neucom.2018.11.107_bib0007 article-title: Nonlinear dynamic soft sensor modeling with supervised long short-term memory network publication-title: IEEE. T. Ind. Inf. – volume: 32 start-page: e3040 year: 2018 ident: 10.1016/j.neucom.2018.11.107_bib0020 article-title: Multi-similarity measurement driven ensemble just-in-time learning for soft sensing of industrial processes publication-title: J. Chemom. doi: 10.1002/cem.3040 – year: 2007 ident: 10.1016/j.neucom.2018.11.107_bib0035 – volume: 63 start-page: 377 year: 2016 ident: 10.1016/j.neucom.2018.11.107_bib0010 article-title: Performance-driven distributed PCA process monitoring based on fault-relevant variable selection and bayesian inference publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2015.2466557 – volume: 53 start-page: 13736 year: 2014 ident: 10.1016/j.neucom.2018.11.107_bib0022 article-title: Locally weighted kernel principal component regression model for soft sensing of nonlinear time-variant processes publication-title: Ind. Eng. Chem. Res. doi: 10.1021/ie4041252 – volume: 65 start-page: 1508 year: 2018 ident: 10.1016/j.neucom.2018.11.107_bib0001 article-title: Weighted linear dynamic system for feature representation and soft sensor application in nonlinear dynamic industrial processes publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2017.2733443 – start-page: 911 year: 2017 ident: 10.1016/j.neucom.2018.11.107_bib0029 article-title: Asymmetric stacked autoencoder – volume: 30 start-page: 87 year: 2011 ident: 10.1016/j.neucom.2018.11.107_bib0033 article-title: Comparison of values of pearson's and spearman's correlation coefficients on the same sets of data publication-title: Quaest. Geogr. – volume: 23 start-page: 793 year: 2013 ident: 10.1016/j.neucom.2018.11.107_bib0018 article-title: Integrated soft sensor using just-in-time support vector regression and probabilistic analysis for quality prediction of multi-grade processes publication-title: J. Process Control doi: 10.1016/j.jprocont.2013.03.008 – volume: 56 start-page: 95 year: 2007 ident: 10.1016/j.neucom.2018.11.107_bib0024 article-title: Virtual instruments based on stacked neural networks to improve product quality monitoring in a refinery publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2006.887331 |
| SSID | ssj0017129 |
| Score | 2.568611 |
| Snippet | Soft sensors have been extensively used to predict difficult-to-measure quality variables for effective modeling, control and optimization of industrial... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 375 |
| SubjectTerms | Deep learning Feature representation Hybrid variable-wise weighted SAE (HVW-SAE) Soft sensor Stacked autoencoder (SAE) |
| Title | Deep quality-related feature extraction for soft sensing modeling: A deep learning approach with hybrid VW-SAE |
| URI | https://dx.doi.org/10.1016/j.neucom.2018.11.107 |
| Volume | 396 |
| WOSCitedRecordID | wos000536806600014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-8286 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LbxMxELZCyoELb0QpIB-4Ra6yr9jb26oEAUIVEoUmp5WfTauwjZJs1f4W_izjtb3ZtqjQA5dVZMWT3cyX8cyXeSD0jo8EGwmZEM6GnKRMcMIjZoiODNe5SGQkm-76X-jBAZtM8q-93q9QC3M-p1XFLi7yxX9VNayBsm3p7B3U3QqFBXgNSocrqB2u_6T491ovfK3kJWlKVcCnNLpp4DkAU7z008FtfuEKjPBgZXPYq2M3FMfXPxcDZcXMA3ESWo873nZ2aeu8Bj-OyLdi3HVvm1YfshkU4SmI4qftxKAs7FrKYVo71nVyws-M9kenJXprlwCwqU478mz2FJ6mXZz6xf1ZXc1q3uUtIEi1nGjWJSDjjIB3ecUWJ3nXmiZuqIo_mBM3peiGzXf0w-lupWubAAQeDYODYNdP073aYvva0dcmJIZct9PSSSmtFIiOYJXeQ1sxzXLWR1vFp_Hkc_snFY1i18rRP0iozGzSB2_ezZ89n443c_gYPfRhCC4cfJ6gnq6eokdhxAf2Fv8Zqiya8DU0YY8mvEETBjRhiybs0YQDmvZwgS2WcMASDljCFkvYYQk7LD1H3z-MD_c_Ej-ig0iINdckjYQQTMSZobHWaZobNYqEyiIRaaqp5IrlPEupkcNcjMxIJVJxyiEqGBqhkix5gfrVWaVfIhyDICMTO78uS1PYBt6kVmqowUEVOY23URK-vlL6_vV2jMq8vE1524i0uxauf8tf3k-DZkrvgzrfsgS43brz1R0_aQc92PwsXqP-elnrN-i-PF-frJZvPdZ-A584rgQ |
| 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=Deep+quality-related+feature+extraction+for+soft+sensing+modeling%3A+A+deep+learning+approach+with+hybrid+VW-SAE&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Yuan%2C+Xiaofeng&rft.au=Ou%2C+Chen&rft.au=Wang%2C+Yalin&rft.au=Yang%2C+Chunhua&rft.date=2020-07-05&rft.issn=0925-2312&rft.volume=396&rft.spage=375&rft.epage=382&rft_id=info:doi/10.1016%2Fj.neucom.2018.11.107&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neucom_2018_11_107 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon |