FA-SconvAE-LSTM: Feature-Aligned Stacked Convolutional Autoencoder with Long Short-Term Memory Network for Soft Sensor Modeling
The advancement of soft sensor technology has enabled the real-time estimation of critical parameters in complex industrial processes, where direct measurement through hardware sensors is often infeasible. Industrial process data typically exhibit both spatial correlations and temporal dependencies,...
Saved in:
| Published in: | Engineering applications of artificial intelligence Vol. 150; p. 110535 |
|---|---|
| Main Authors: | , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Ltd
15.06.2025
|
| Subjects: | |
| ISSN: | 0952-1976 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | The advancement of soft sensor technology has enabled the real-time estimation of critical parameters in complex industrial processes, where direct measurement through hardware sensors is often infeasible. Industrial process data typically exhibit both spatial correlations and temporal dependencies, necessitating sophisticated modeling approaches to capture these characteristics effectively. In this study, a spatio-temporal model, termed the feature-aligned stacked convolutional autoencoder with long short-term memory, is proposed to develop soft sensors for nonlinear dynamic industrial processes. The proposed model begins with the systematic training of a stacked convolutional autoencoder using a layer-by-layer pre-training technique. This approach facilitates the extraction of high-level spatial feature representations from the process variables. To address the issue of feature misalignment in the spatial features extracted by the stacked convolutional autoencoder, a feature alignment strategy is implemented, ensuring that the extracted spatial features are properly aligned. Subsequently, the aligned spatial features are fed into a long short-term memory network to capture temporal dependencies, with quality variables serving as the output for soft sensor development. The effectiveness and superiority of the proposed method are demonstrated through experiments conducted on two industrial processes: the sulfur recovery unit and the multiphase flow process. Comparative analyses with other state-of-the-art methods reveal that the proposed model achieves the highest performance, with R2 values of 0.86222 for the sulfur recovery unit and 0.94307 for the multiphase flow process, outperforming all compared methods.
[Display omitted]
•A feature alignment strategy is developed to align spatial features from the stacked convolutional autoencoder, preserving temporal consistency.•A spatio-temporal model integrating a feature-aligned stacked convolutional autoencoder and LSTM is developed for soft sensors, simultaneously capturing spatial and temporal dependencies in industrial processes.•The proposed method’s effectiveness and superiority are demonstrated through comprehensive experiments on the sulfur recovery unit and multiphase flow process. |
|---|---|
| AbstractList | The advancement of soft sensor technology has enabled the real-time estimation of critical parameters in complex industrial processes, where direct measurement through hardware sensors is often infeasible. Industrial process data typically exhibit both spatial correlations and temporal dependencies, necessitating sophisticated modeling approaches to capture these characteristics effectively. In this study, a spatio-temporal model, termed the feature-aligned stacked convolutional autoencoder with long short-term memory, is proposed to develop soft sensors for nonlinear dynamic industrial processes. The proposed model begins with the systematic training of a stacked convolutional autoencoder using a layer-by-layer pre-training technique. This approach facilitates the extraction of high-level spatial feature representations from the process variables. To address the issue of feature misalignment in the spatial features extracted by the stacked convolutional autoencoder, a feature alignment strategy is implemented, ensuring that the extracted spatial features are properly aligned. Subsequently, the aligned spatial features are fed into a long short-term memory network to capture temporal dependencies, with quality variables serving as the output for soft sensor development. The effectiveness and superiority of the proposed method are demonstrated through experiments conducted on two industrial processes: the sulfur recovery unit and the multiphase flow process. Comparative analyses with other state-of-the-art methods reveal that the proposed model achieves the highest performance, with R2 values of 0.86222 for the sulfur recovery unit and 0.94307 for the multiphase flow process, outperforming all compared methods.
[Display omitted]
•A feature alignment strategy is developed to align spatial features from the stacked convolutional autoencoder, preserving temporal consistency.•A spatio-temporal model integrating a feature-aligned stacked convolutional autoencoder and LSTM is developed for soft sensors, simultaneously capturing spatial and temporal dependencies in industrial processes.•The proposed method’s effectiveness and superiority are demonstrated through comprehensive experiments on the sulfur recovery unit and multiphase flow process. |
| ArticleNumber | 110535 |
| Author | Zhang, Xujie Wang, Ke Yang, Chunjie Wu, Ping Miao, Zengdi Gao, Jinfeng Lou, Siwei |
| Author_xml | – sequence: 1 givenname: Ping orcidid: 0000-0002-2729-9669 surname: Wu fullname: Wu, Ping email: pingwu@zstu.edu.cn organization: School of Information Science and Engineering, Zhejiang Sci-Tech University, Hangzhou, China – sequence: 2 givenname: Zengdi orcidid: 0009-0008-5343-4802 surname: Miao fullname: Miao, Zengdi organization: School of Information Science and Engineering, Zhejiang Sci-Tech University, Hangzhou, China – sequence: 3 givenname: Ke surname: Wang fullname: Wang, Ke organization: School of Information Science and Engineering, Zhejiang Sci-Tech University, Hangzhou, China – sequence: 4 givenname: Jinfeng surname: Gao fullname: Gao, Jinfeng organization: School of Information Science and Engineering, Zhejiang Sci-Tech University, Hangzhou, China – sequence: 5 givenname: Xujie surname: Zhang fullname: Zhang, Xujie organization: College of Control Science and Engineering, Zhejiang University, Hangzhou, China – sequence: 6 givenname: Siwei surname: Lou fullname: Lou, Siwei organization: College of Control Science and Engineering, Zhejiang University, Hangzhou, China – sequence: 7 givenname: Chunjie surname: Yang fullname: Yang, Chunjie organization: College of Control Science and Engineering, Zhejiang University, Hangzhou, China |
| BookMark | eNqFkLFuwjAURT1QqUD7C5V_INSOE5NUHRohaCuFdgidLeO8BEOwkWNATP31BtEuXZjuG9650j0D1DPWAEIPlIwoofxxPQJTy91O6lFIwnhEKYlZ3EN9ksZhQNMxv0WDtl0TQlgS8T76nmVBoaw5ZNMgLxbzJzwD6fcOgqzRtYESF16qTZeT7sk2e6-tkQ3O9t6CUbYEh4_ar3BuTY2LlXU-WIDb4jlsrTvhD_BH6za4sg4XtvK4ANN297wjG23qO3RTyaaF-98coq_ZdDF5C_LP1_dJlgcqjEIfKFqloMYhU6ribFlSxijnEIJMUkVIWkY8rngiI7KsZMrimEEESUQZVTEwDmyIni-9ytm2dVAJpb08j_FO6kZQIs4CxVr8CRRngeIisMP5P3zn9Fa603Xw5QJCN-6gwYlW6U4clNqB8qK0-lrFD6tjlGM |
| CitedBy_id | crossref_primary_10_1016_j_compchemeng_2025_109328 crossref_primary_10_1016_j_knosys_2025_114500 |
| Cites_doi | 10.1016/j.engappai.2023.106847 10.1016/j.asoc.2024.111974 10.1016/j.engappai.2023.106149 10.1109/TIM.2022.3152856 10.1016/j.conengprac.2020.104614 10.1109/TNNLS.2021.3085869 10.1016/j.compchemeng.2008.12.012 10.1016/S0967-0661(03)00079-0 10.1109/JSEN.2020.3033153 10.1109/TII.2018.2869899 10.3390/info15090517 10.1109/TIE.2020.2984443 10.1007/s10462-023-10678-y 10.1016/j.conengprac.2022.105292 10.7717/peerj-cs.623 10.1109/TIM.2021.3118090 10.1016/j.eswa.2009.08.008 10.1016/j.chemolab.2015.12.011 10.1109/TII.2019.2902129 10.1109/TIM.2020.2985614 10.1021/acs.iecr.9b02513 10.1109/TII.2020.3025204 10.1109/TII.2021.3053128 10.1109/TII.2009.2025124 10.1016/j.engappai.2022.105737 10.1109/TNNLS.2021.3084827 10.1016/j.measurement.2023.113491 10.1162/neco_a_01199 10.1162/neco.1997.9.8.1735 10.1038/nature14539 10.1109/ACCESS.2024.3440631 10.1016/j.jnca.2024.104048 10.1016/j.jprocont.2014.01.012 10.1016/j.knosys.2024.112026 10.1016/j.conengprac.2015.04.012 10.1109/TII.2022.3183211 10.1080/00031305.1989.10475612 10.1021/ie4041252 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Ltd |
| Copyright_xml | – notice: 2025 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.engappai.2025.110535 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Computer Science |
| ExternalDocumentID | 10_1016_j_engappai_2025_110535 S0952197625005354 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABNK AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABJNI ABMAC ACDAQ ACGFS ACRLP ACVFH ACZNC ADBBV ADCNI ADEZE ADTZH AEBSH AECPX AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AGCQF AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APXCP AXJTR BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFKBS EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W JJJVA KOM LG9 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SST SSV SSZ T5K TN5 ~G- 29G 9DU AAQXK AAYXX ABWVN ABXDB ACLOT ACNNM ACRPL ADJOM ADMUD ADNMO AGQPQ ASPBG AVWKF AZFZN CITATION EJD FEDTE FGOYB G-2 HLZ HVGLF HZ~ R2- SBC SET UHS WUQ ZMT ~HD |
| ID | FETCH-LOGICAL-c242t-c1f9ec723ccf63bd133166e2ea89c009d465f68a40bfa93553e4e84131c5e36e3 |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001449933100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0952-1976 |
| IngestDate | Sat Nov 29 06:58:01 EST 2025 Tue Nov 18 22:43:12 EST 2025 Sat Sep 06 17:18:16 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Spatiotemporal feature extraction Soft sensor Stacked convolutional autoencoder Feature alignment |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c242t-c1f9ec723ccf63bd133166e2ea89c009d465f68a40bfa93553e4e84131c5e36e3 |
| ORCID | 0009-0008-5343-4802 0000-0002-2729-9669 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_engappai_2025_110535 crossref_primary_10_1016_j_engappai_2025_110535 elsevier_sciencedirect_doi_10_1016_j_engappai_2025_110535 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-06-15 |
| PublicationDateYYYYMMDD | 2025-06-15 |
| PublicationDate_xml | – month: 06 year: 2025 text: 2025-06-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationTitle | Engineering applications of artificial intelligence |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Vaswani (b34) 2017 Plevris, Solorzano, Bakas, Ben Seghier (b24) 2022 Yuan, Ge, Song (b42) 2014; 53 Hochreiter, Schmidhuber (b9) 1997; 9 Yuan, Qi, Wang (b45) 2020; 69 Kadlec, Gabrys, Strandt (b13) 2009; 33 Yuan, Li, Shardt, Wang, Yang (b43) 2020; 68 Tian, Zhu, He (b32) 2023 Mizdrakovic, Kljajic, Zivkovic, Bacanin, Jovanovic, Deveci, Pedrycz (b22) 2024 Liu, Zhou, Xu, Mei (b18) 2010; 37 Lui, Liu, Xie (b19) 2022; 71 Yuan, Qi, Wang, Xia (b46) 2020; 104 Liu, Wang, Wang, Xie, Yang (b17) 2021; 70 Shao, Han, Li, Ge, Zhao (b28) 2022; 127 Ullah, Ahsan, Hasanat, Haris, Yousaf, Raza, Tandon, Abid, Ullah (b33) 2024 Yuan, Li, Wang (b44) 2019; 16 Dey, Salem (b4) 2017 Wang, Liu, Srinivasan (b35) 2009; 6 Ruiz-Cárcel, Cao, Mba, Lao, Samuel (b26) 2015; 42 Yao, Shen, Cui, Zheng, Ge (b40) 2022; 19 Fortuna, Graziani, Rizzo, Xibilia (b5) 2007 Bono, Radicioni, Cinquemani (b1) 2023; 122 Mienye, Swart, Obaido (b21) 2024; 15 Li, Peng, Sun, Ji, Wang, Tao, Zhang, Nazir (b16) 2023 Zhou, Yang, Wang, Cao (b49) 2023; 126 Chicco, Warrens, Jurman (b3) 2021; 7 Shang, Yang, Huang, Lyu (b27) 2014; 24 Chai, Zhao, Huang, Chen (b2) 2021; 33 Zhou, Wang, Hu, Zhu, Zhang, Kong, Zhou, Wu, Cui (b48) 2024 Jiang, Ge (b10) 2021; 70 Pavlov-Kagadejev, Jovanovic, Bacanin, Deveci, Zivkovic, Tuba, Strumberger, Pedrycz (b23) 2024; 57 LeCun, Bengio, Hinton (b14) 2015; 521 Yu, Si, Hu, Zhang (b41) 2019; 31 Li, Liu, Yang, Peng, Zhou (b15) 2021; 33 Wang, Shang, Liu, Jiang, Huang, Yang (b37) 2019; 58 Xie, Wang, Xing, Guo, Guo, Zhu (b39) 2020; 17 Rosipal, Trejo (b25) 2001; 2 Sun, Ge (b31) 2021; 17 Wang, Qi, Zhang (b36) 2024; 164 Wang, Wang, Chen, Hao (b38) 2023; 221 Zheng, Liu, Liu, Hou, Yao, Zhou (b47) 2023 Fortuna, Rizzo, Sinatra, Xibilia (b6) 2003; 11 Jovanovic, Jovanovic, Zivkovic, Bacanin, Simic, Pamucar, Antonijevic (b12) 2025; 233 He, Li, Ma, Zhu, Lu (b8) 2023; 119 Frigge, Hoaglin, Iglewicz (b7) 1989; 43 Jiang, Yin, Dong, Kaynak (b11) 2020; 21 Souza, Araújo, Mendes (b29) 2016; 152 Sun, Ge (b30) 2018; 15 Meng, Liu, Yang, Zhou, Cheung (b20) 2023 Chicco (10.1016/j.engappai.2025.110535_b3) 2021; 7 Wang (10.1016/j.engappai.2025.110535_b38) 2023; 221 Ullah (10.1016/j.engappai.2025.110535_b33) 2024 Fortuna (10.1016/j.engappai.2025.110535_b6) 2003; 11 Zheng (10.1016/j.engappai.2025.110535_b47) 2023 Bono (10.1016/j.engappai.2025.110535_b1) 2023; 122 Frigge (10.1016/j.engappai.2025.110535_b7) 1989; 43 Yao (10.1016/j.engappai.2025.110535_b40) 2022; 19 Plevris (10.1016/j.engappai.2025.110535_b24) 2022 Lui (10.1016/j.engappai.2025.110535_b19) 2022; 71 Tian (10.1016/j.engappai.2025.110535_b32) 2023 Shang (10.1016/j.engappai.2025.110535_b27) 2014; 24 Xie (10.1016/j.engappai.2025.110535_b39) 2020; 17 Zhou (10.1016/j.engappai.2025.110535_b49) 2023; 126 Liu (10.1016/j.engappai.2025.110535_b17) 2021; 70 LeCun (10.1016/j.engappai.2025.110535_b14) 2015; 521 Yuan (10.1016/j.engappai.2025.110535_b43) 2020; 68 Vaswani (10.1016/j.engappai.2025.110535_b34) 2017 Wang (10.1016/j.engappai.2025.110535_b35) 2009; 6 Zhou (10.1016/j.engappai.2025.110535_b48) 2024 Mienye (10.1016/j.engappai.2025.110535_b21) 2024; 15 Shao (10.1016/j.engappai.2025.110535_b28) 2022; 127 Jovanovic (10.1016/j.engappai.2025.110535_b12) 2025; 233 Mizdrakovic (10.1016/j.engappai.2025.110535_b22) 2024 Yuan (10.1016/j.engappai.2025.110535_b45) 2020; 69 Rosipal (10.1016/j.engappai.2025.110535_b25) 2001; 2 He (10.1016/j.engappai.2025.110535_b8) 2023; 119 Li (10.1016/j.engappai.2025.110535_b15) 2021; 33 Chai (10.1016/j.engappai.2025.110535_b2) 2021; 33 Sun (10.1016/j.engappai.2025.110535_b30) 2018; 15 Ruiz-Cárcel (10.1016/j.engappai.2025.110535_b26) 2015; 42 Wang (10.1016/j.engappai.2025.110535_b36) 2024; 164 Fortuna (10.1016/j.engappai.2025.110535_b5) 2007 Yuan (10.1016/j.engappai.2025.110535_b42) 2014; 53 Dey (10.1016/j.engappai.2025.110535_b4) 2017 Meng (10.1016/j.engappai.2025.110535_b20) 2023 Wang (10.1016/j.engappai.2025.110535_b37) 2019; 58 Jiang (10.1016/j.engappai.2025.110535_b11) 2020; 21 Pavlov-Kagadejev (10.1016/j.engappai.2025.110535_b23) 2024; 57 Hochreiter (10.1016/j.engappai.2025.110535_b9) 1997; 9 Sun (10.1016/j.engappai.2025.110535_b31) 2021; 17 Liu (10.1016/j.engappai.2025.110535_b18) 2010; 37 Kadlec (10.1016/j.engappai.2025.110535_b13) 2009; 33 Yu (10.1016/j.engappai.2025.110535_b41) 2019; 31 Li (10.1016/j.engappai.2025.110535_b16) 2023 Souza (10.1016/j.engappai.2025.110535_b29) 2016; 152 Yuan (10.1016/j.engappai.2025.110535_b46) 2020; 104 Jiang (10.1016/j.engappai.2025.110535_b10) 2021; 70 Yuan (10.1016/j.engappai.2025.110535_b44) 2019; 16 |
| References_xml | – year: 2017 ident: b34 article-title: Attention is all you need publication-title: Adv. Neural Inf. Process. Syst. – volume: 68 start-page: 4404 year: 2020 end-page: 4414 ident: b43 article-title: Deep learning with spatiotemporal attention-based LSTM for industrial soft sensor model development publication-title: IEEE Trans. Ind. Electron. – volume: 70 start-page: 1 year: 2021 end-page: 10 ident: b17 article-title: Deep nonlinear dynamic feature extraction for quality prediction based on spatiotemporal neighborhood preserving SAE publication-title: IEEE Trans. Instrum. Meas. – start-page: 1597 year: 2017 end-page: 1600 ident: b4 article-title: Gate-variants of Gated Recurrent Unit (GRU) neural networks publication-title: 2017 IEEE 60th International Midwest Symposium on Circuits and Systems – volume: 7 year: 2021 ident: b3 article-title: The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation publication-title: PeerJ Comput. Sci. – volume: 164 year: 2024 ident: b36 article-title: Deep learning with local spatiotemporal structure preserving for soft sensor development of complex industrial processes publication-title: Appl. Soft Comput. – volume: 21 start-page: 12868 year: 2020 end-page: 12881 ident: b11 article-title: A review on soft sensors for monitoring, control, and optimization of industrial processes publication-title: IEEE Sens. J. – volume: 43 start-page: 50 year: 1989 end-page: 54 ident: b7 article-title: Some implementations of the boxplot publication-title: Amer. Statist. – volume: 11 start-page: 1491 year: 2003 end-page: 1500 ident: b6 article-title: Soft analyzers for a sulfur recovery unit publication-title: Control Eng. Pract. – year: 2024 ident: b48 article-title: ISSA-LSTM: A new data-driven method of heat load forecasting for building air conditioning publication-title: Energy Build. – volume: 152 start-page: 69 year: 2016 end-page: 79 ident: b29 article-title: Review of soft sensor methods for regression applications publication-title: Chemom. Intell. Lab. Syst. – volume: 58 start-page: 11521 year: 2019 end-page: 11531 ident: b37 article-title: Dynamic soft sensor development based on convolutional neural networks publication-title: Ind. Eng. Chem. Res. – volume: 70 start-page: 1 year: 2021 end-page: 10 ident: b10 article-title: Augmented multidimensional convolutional neural network for industrial soft sensing publication-title: IEEE Trans. Instrum. Meas. – volume: 31 start-page: 1235 year: 2019 end-page: 1270 ident: b41 article-title: A review of recurrent neural networks: LSTM cells and network architectures publication-title: Neural Comput. – year: 2023 ident: b32 article-title: Novel deep layers-extended autoencoder with correlation and its industrial soft sensing publication-title: IEEE Trans. Ind. Inf. – volume: 69 start-page: 7953 year: 2020 end-page: 7961 ident: b45 article-title: Stacked enhanced auto-encoder for data-driven soft sensing of quality variable publication-title: IEEE Trans. Instrum. Meas. – volume: 17 start-page: 5853 year: 2021 end-page: 5866 ident: b31 article-title: A survey on deep learning for data-driven soft sensors publication-title: IEEE Trans. Ind. Inf. – year: 2023 ident: b16 article-title: A soft sensor model based on CNN-BiLSTM and IHHO algorithm for Tennessee Eastman process publication-title: Measurement – volume: 221 year: 2023 ident: b38 article-title: A novel soft sensor method based on stacked fusion autoencoder with feature enhancement for industrial application publication-title: Measurement – volume: 17 start-page: 5325 year: 2020 end-page: 5334 ident: b39 article-title: Variational autoencoder bidirectional long and short-term memory neural network soft-sensor model based on batch training strategy publication-title: IEEE Trans. Ind. Inf. – volume: 42 start-page: 74 year: 2015 end-page: 88 ident: b26 article-title: Statistical process monitoring of a multiphase flow facility publication-title: Control Eng. Pract. – volume: 19 start-page: 6056 year: 2022 end-page: 6068 ident: b40 article-title: Semi-supervised deep dynamic probabilistic latent variable model for multimode process soft sensor application publication-title: IEEE Trans. Ind. Inf. – year: 2007 ident: b5 publication-title: Soft Sensors for Monitoring and Control of Industrial Processes – year: 2024 ident: b33 article-title: Short-term load forecasting: A comprehensive review and simulation study with CNN-LSTM hybrids approach publication-title: IEEE Access – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: b9 article-title: Long short-term memory publication-title: Neural Comput. – volume: 15 start-page: 517 year: 2024 ident: b21 article-title: Recurrent neural networks: A comprehensive review of architectures, variants, and applications publication-title: Information – volume: 33 start-page: 6999 year: 2021 end-page: 7019 ident: b15 article-title: A survey of convolutional neural networks: analysis, applications, and prospects publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 71 start-page: 1 year: 2022 end-page: 13 ident: b19 article-title: A supervised bidirectional long short-term memory network for data-driven dynamic soft sensor modeling publication-title: IEEE Trans. Instrum. Meas. – year: 2023 ident: b47 article-title: Semi-supervised process data regression and application based on latent factor analysis model publication-title: IEEE Trans. Instrum. Meas. – volume: 24 start-page: 223 year: 2014 end-page: 233 ident: b27 article-title: Data-driven soft sensor development based on deep learning technique publication-title: J. Process Control – volume: 119 year: 2023 ident: b8 article-title: Attribute-relevant distributed variational autoencoder integrated with LSTM for dynamic industrial soft sensing publication-title: Eng. Appl. Artif. Intell. – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: b14 article-title: Deep learning publication-title: Nature – volume: 53 start-page: 13736 year: 2014 end-page: 13749 ident: b42 article-title: Locally weighted kernel principal component regression model for soft sensing of nonlinear time-variant processes publication-title: Ind. Eng. Chem. Res. – volume: 57 start-page: 45 year: 2024 ident: b23 article-title: Optimizing long-short-term memory models via metaheuristics for decomposition aided wind energy generation forecasting publication-title: Artif. Intell. Rev. – volume: 233 year: 2025 ident: b12 article-title: Particle swarm optimization tuned multi-headed long short-term memory networks approach for fuel prices forecasting publication-title: J. Netw. Comput. Appl. – year: 2024 ident: b22 article-title: Forecasting bitcoin: Decomposition aided long short-term memory based time series modelling and its explanation with shapley values publication-title: Knowledge- Based Syst. – volume: 33 start-page: 7598 year: 2021 end-page: 7609 ident: b2 article-title: A deep probabilistic transfer learning framework for soft sensor modeling with missing data publication-title: IEEE Trans. Neural Networks Learn. Syst. – volume: 37 start-page: 2708 year: 2010 end-page: 2713 ident: b18 article-title: Model optimization of SVM for a fermentation soft sensor publication-title: Expert Syst. Appl. – volume: 15 start-page: 2700 year: 2018 end-page: 2709 ident: b30 article-title: Probabilistic sequential network for deep learning of complex process data and soft sensor application publication-title: IEEE Trans. Ind. Inf. – volume: 33 start-page: 795 year: 2009 end-page: 814 ident: b13 article-title: Data-driven soft sensors in the process industry publication-title: Comput. Chem. Eng. – volume: 16 start-page: 3168 year: 2019 end-page: 3176 ident: b44 article-title: Nonlinear dynamic soft sensor modeling with supervised long short-term memory network publication-title: IEEE Trans. Ind. Inf. – volume: 2 start-page: 97 year: 2001 end-page: 123 ident: b25 article-title: Kernel partial least squares regression in reproducing kernel hilbert space publication-title: J. Mach. Learn. Res. – year: 2023 ident: b20 article-title: A novel deep learning-based robust dual-rate dynamic data modeling for quality prediction publication-title: IEEE Trans. Ind. Inf. – year: 2022 ident: b24 article-title: Investigation of performance metrics in regression analysis and machine learning-based prediction models publication-title: 8th European Congress on Computational Methods in Applied Sciences and Engineering – volume: 122 year: 2023 ident: b1 article-title: A novel approach for quality control of automated production lines working under highly inconsistent conditions publication-title: Eng. Appl. Artif. Intell. – volume: 127 year: 2022 ident: b28 article-title: Enhancing the reliability and accuracy of data-driven dynamic soft sensor based on selective dynamic partial least squares models publication-title: Control Eng. Pract. – volume: 104 year: 2020 ident: b46 article-title: A dynamic CNN for nonlinear dynamic feature learning in soft sensor modeling of industrial process data publication-title: Control Eng. Pract. – volume: 6 start-page: 11 year: 2009 end-page: 17 ident: b35 article-title: Data-driven soft sensor approach for quality prediction in a refining process publication-title: IEEE Trans. Ind. Inf. – volume: 126 year: 2023 ident: b49 article-title: A soft sensor modeling framework embedded with domain knowledge based on spatio-temporal deep LSTM for process industry publication-title: Eng. Appl. Artif. Intell. – volume: 126 year: 2023 ident: 10.1016/j.engappai.2025.110535_b49 article-title: A soft sensor modeling framework embedded with domain knowledge based on spatio-temporal deep LSTM for process industry publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2023.106847 – volume: 164 year: 2024 ident: 10.1016/j.engappai.2025.110535_b36 article-title: Deep learning with local spatiotemporal structure preserving for soft sensor development of complex industrial processes publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2024.111974 – volume: 122 year: 2023 ident: 10.1016/j.engappai.2025.110535_b1 article-title: A novel approach for quality control of automated production lines working under highly inconsistent conditions publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2023.106149 – volume: 71 start-page: 1 year: 2022 ident: 10.1016/j.engappai.2025.110535_b19 article-title: A supervised bidirectional long short-term memory network for data-driven dynamic soft sensor modeling publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2022.3152856 – volume: 104 year: 2020 ident: 10.1016/j.engappai.2025.110535_b46 article-title: A dynamic CNN for nonlinear dynamic feature learning in soft sensor modeling of industrial process data publication-title: Control Eng. Pract. doi: 10.1016/j.conengprac.2020.104614 – volume: 33 start-page: 7598 issue: 12 year: 2021 ident: 10.1016/j.engappai.2025.110535_b2 article-title: A deep probabilistic transfer learning framework for soft sensor modeling with missing data publication-title: IEEE Trans. Neural Networks Learn. Syst. doi: 10.1109/TNNLS.2021.3085869 – volume: 33 start-page: 795 issue: 4 year: 2009 ident: 10.1016/j.engappai.2025.110535_b13 article-title: Data-driven soft sensors in the process industry publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2008.12.012 – volume: 11 start-page: 1491 issue: 12 year: 2003 ident: 10.1016/j.engappai.2025.110535_b6 article-title: Soft analyzers for a sulfur recovery unit publication-title: Control Eng. Pract. doi: 10.1016/S0967-0661(03)00079-0 – volume: 21 start-page: 12868 issue: 11 year: 2020 ident: 10.1016/j.engappai.2025.110535_b11 article-title: A review on soft sensors for monitoring, control, and optimization of industrial processes publication-title: IEEE Sens. J. doi: 10.1109/JSEN.2020.3033153 – volume: 15 start-page: 2700 issue: 5 year: 2018 ident: 10.1016/j.engappai.2025.110535_b30 article-title: Probabilistic sequential network for deep learning of complex process data and soft sensor application publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2018.2869899 – volume: 15 start-page: 517 issue: 9 year: 2024 ident: 10.1016/j.engappai.2025.110535_b21 article-title: Recurrent neural networks: A comprehensive review of architectures, variants, and applications publication-title: Information doi: 10.3390/info15090517 – volume: 68 start-page: 4404 issue: 5 year: 2020 ident: 10.1016/j.engappai.2025.110535_b43 article-title: Deep learning with spatiotemporal attention-based LSTM for industrial soft sensor model development publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2020.2984443 – volume: 57 start-page: 45 issue: 3 year: 2024 ident: 10.1016/j.engappai.2025.110535_b23 article-title: Optimizing long-short-term memory models via metaheuristics for decomposition aided wind energy generation forecasting publication-title: Artif. Intell. Rev. doi: 10.1007/s10462-023-10678-y – year: 2022 ident: 10.1016/j.engappai.2025.110535_b24 article-title: Investigation of performance metrics in regression analysis and machine learning-based prediction models – volume: 127 year: 2022 ident: 10.1016/j.engappai.2025.110535_b28 article-title: Enhancing the reliability and accuracy of data-driven dynamic soft sensor based on selective dynamic partial least squares models publication-title: Control Eng. Pract. doi: 10.1016/j.conengprac.2022.105292 – volume: 7 year: 2021 ident: 10.1016/j.engappai.2025.110535_b3 article-title: The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation publication-title: PeerJ Comput. Sci. doi: 10.7717/peerj-cs.623 – volume: 70 start-page: 1 year: 2021 ident: 10.1016/j.engappai.2025.110535_b17 article-title: Deep nonlinear dynamic feature extraction for quality prediction based on spatiotemporal neighborhood preserving SAE publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2021.3118090 – volume: 37 start-page: 2708 issue: 4 year: 2010 ident: 10.1016/j.engappai.2025.110535_b18 article-title: Model optimization of SVM for a fermentation soft sensor publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2009.08.008 – volume: 152 start-page: 69 year: 2016 ident: 10.1016/j.engappai.2025.110535_b29 article-title: Review of soft sensor methods for regression applications publication-title: Chemom. Intell. Lab. Syst. doi: 10.1016/j.chemolab.2015.12.011 – year: 2024 ident: 10.1016/j.engappai.2025.110535_b48 article-title: ISSA-LSTM: A new data-driven method of heat load forecasting for building air conditioning publication-title: Energy Build. – volume: 16 start-page: 3168 issue: 5 year: 2019 ident: 10.1016/j.engappai.2025.110535_b44 article-title: Nonlinear dynamic soft sensor modeling with supervised long short-term memory network publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2019.2902129 – volume: 69 start-page: 7953 issue: 10 year: 2020 ident: 10.1016/j.engappai.2025.110535_b45 article-title: Stacked enhanced auto-encoder for data-driven soft sensing of quality variable publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2020.2985614 – volume: 58 start-page: 11521 issue: 26 year: 2019 ident: 10.1016/j.engappai.2025.110535_b37 article-title: Dynamic soft sensor development based on convolutional neural networks publication-title: Ind. Eng. Chem. Res. doi: 10.1021/acs.iecr.9b02513 – volume: 17 start-page: 5325 issue: 8 year: 2020 ident: 10.1016/j.engappai.2025.110535_b39 article-title: Variational autoencoder bidirectional long and short-term memory neural network soft-sensor model based on batch training strategy publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2020.3025204 – volume: 17 start-page: 5853 issue: 9 year: 2021 ident: 10.1016/j.engappai.2025.110535_b31 article-title: A survey on deep learning for data-driven soft sensors publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2021.3053128 – volume: 6 start-page: 11 issue: 1 year: 2009 ident: 10.1016/j.engappai.2025.110535_b35 article-title: Data-driven soft sensor approach for quality prediction in a refining process publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2009.2025124 – volume: 70 start-page: 1 year: 2021 ident: 10.1016/j.engappai.2025.110535_b10 article-title: Augmented multidimensional convolutional neural network for industrial soft sensing publication-title: IEEE Trans. Instrum. Meas. – year: 2023 ident: 10.1016/j.engappai.2025.110535_b20 article-title: A novel deep learning-based robust dual-rate dynamic data modeling for quality prediction publication-title: IEEE Trans. Ind. Inf. – year: 2023 ident: 10.1016/j.engappai.2025.110535_b47 article-title: Semi-supervised process data regression and application based on latent factor analysis model publication-title: IEEE Trans. Instrum. Meas. – volume: 119 year: 2023 ident: 10.1016/j.engappai.2025.110535_b8 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: 33 start-page: 6999 issue: 12 year: 2021 ident: 10.1016/j.engappai.2025.110535_b15 article-title: A survey of convolutional neural networks: analysis, applications, and prospects publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2021.3084827 – volume: 221 year: 2023 ident: 10.1016/j.engappai.2025.110535_b38 article-title: A novel soft sensor method based on stacked fusion autoencoder with feature enhancement for industrial application publication-title: Measurement doi: 10.1016/j.measurement.2023.113491 – year: 2023 ident: 10.1016/j.engappai.2025.110535_b16 article-title: A soft sensor model based on CNN-BiLSTM and IHHO algorithm for Tennessee Eastman process publication-title: Measurement – volume: 31 start-page: 1235 issue: 7 year: 2019 ident: 10.1016/j.engappai.2025.110535_b41 article-title: A review of recurrent neural networks: LSTM cells and network architectures publication-title: Neural Comput. doi: 10.1162/neco_a_01199 – volume: 2 start-page: 97 issue: Dec year: 2001 ident: 10.1016/j.engappai.2025.110535_b25 article-title: Kernel partial least squares regression in reproducing kernel hilbert space publication-title: J. Mach. Learn. Res. – volume: 9 start-page: 1735 issue: 8 year: 1997 ident: 10.1016/j.engappai.2025.110535_b9 article-title: Long short-term memory publication-title: Neural Comput. doi: 10.1162/neco.1997.9.8.1735 – year: 2023 ident: 10.1016/j.engappai.2025.110535_b32 article-title: Novel deep layers-extended autoencoder with correlation and its industrial soft sensing publication-title: IEEE Trans. Ind. Inf. – start-page: 1597 year: 2017 ident: 10.1016/j.engappai.2025.110535_b4 article-title: Gate-variants of Gated Recurrent Unit (GRU) neural networks – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.engappai.2025.110535_b14 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – year: 2024 ident: 10.1016/j.engappai.2025.110535_b33 article-title: Short-term load forecasting: A comprehensive review and simulation study with CNN-LSTM hybrids approach publication-title: IEEE Access doi: 10.1109/ACCESS.2024.3440631 – volume: 233 year: 2025 ident: 10.1016/j.engappai.2025.110535_b12 article-title: Particle swarm optimization tuned multi-headed long short-term memory networks approach for fuel prices forecasting publication-title: J. Netw. Comput. Appl. doi: 10.1016/j.jnca.2024.104048 – volume: 24 start-page: 223 issue: 3 year: 2014 ident: 10.1016/j.engappai.2025.110535_b27 article-title: Data-driven soft sensor development based on deep learning technique publication-title: J. Process Control doi: 10.1016/j.jprocont.2014.01.012 – year: 2007 ident: 10.1016/j.engappai.2025.110535_b5 – year: 2024 ident: 10.1016/j.engappai.2025.110535_b22 article-title: Forecasting bitcoin: Decomposition aided long short-term memory based time series modelling and its explanation with shapley values publication-title: Knowledge- Based Syst. doi: 10.1016/j.knosys.2024.112026 – volume: 42 start-page: 74 year: 2015 ident: 10.1016/j.engappai.2025.110535_b26 article-title: Statistical process monitoring of a multiphase flow facility publication-title: Control Eng. Pract. doi: 10.1016/j.conengprac.2015.04.012 – volume: 19 start-page: 6056 issue: 4 year: 2022 ident: 10.1016/j.engappai.2025.110535_b40 article-title: Semi-supervised deep dynamic probabilistic latent variable model for multimode process soft sensor application publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2022.3183211 – year: 2017 ident: 10.1016/j.engappai.2025.110535_b34 article-title: Attention is all you need publication-title: Adv. Neural Inf. Process. Syst. – volume: 43 start-page: 50 issue: 1 year: 1989 ident: 10.1016/j.engappai.2025.110535_b7 article-title: Some implementations of the boxplot publication-title: Amer. Statist. doi: 10.1080/00031305.1989.10475612 – volume: 53 start-page: 13736 issue: 35 year: 2014 ident: 10.1016/j.engappai.2025.110535_b42 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 |
| SSID | ssj0003846 |
| Score | 2.4455574 |
| Snippet | The advancement of soft sensor technology has enabled the real-time estimation of critical parameters in complex industrial processes, where direct measurement... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 110535 |
| SubjectTerms | Feature alignment Soft sensor Spatiotemporal feature extraction Stacked convolutional autoencoder |
| Title | FA-SconvAE-LSTM: Feature-Aligned Stacked Convolutional Autoencoder with Long Short-Term Memory Network for Soft Sensor Modeling |
| URI | https://dx.doi.org/10.1016/j.engappai.2025.110535 |
| Volume | 150 |
| WOSCitedRecordID | wos001449933100001&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 issn: 0952-1976 databaseCode: AIEXJ dateStart: 19950201 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0003846 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1La9wwEBbbpIde-i5NX-jQW1BaPyTLuZmySRqSUPAWll6MLcvJhsUbNrtLesqfyA_OjCXZ7jaQltKLMcIj2Z7P0qfxPAj56PmiBM5WsAr2AiwMec5k6WumQq51qEov5EVTbCI6OZHjcfxtMLhxsTCraVTX8uoqvvivqoY2UDaGzv6FuttOoQHOQelwBLXD8Y8Uv5ewFH3JkyE7SkfHuOVHnreca5ZMJ6e1YZjw8ZYY7rey94KaWi5mmNYSs0s05tkjrEOUngFBZyOYwLeP0Sv3J8YIozdX46CYzjDpM2yF4RzLqk3dSuiM_V26w-3-v_LG_WDe-Ck1VUN6iUHbZWLZMFzXYRO3mDeG3R-6Pi0n3a8AO121kvvmskN0NLPS1q7hc_S_MpGdxtjmAm467yZjtfSZF5uSMe0EblLX_rYYGLvE-Q4MBU-YT3ZwGIx74CZDylqi7RQ7x76BFeIl4QOy6Uc8hul-M_k6HB-2K3wgTQCYu5le5Pndo91NenpEZvSUPLY7EJoY5DwjA10_J0_sboTauf4SmlzBD9f2glyvYWuXriGLWmTRX5BFe8iiiCyKyKIdsqhBFrXIooAsisiiBlnUIesl-b43HH05YLaCB1NA_RZMeVWsVeQHSlUiKEovCDwhtK9zGStg92UoeCVkHn4uqhwz_Qc61BJ4lae4DoQOXpGNelbr14QKDeu2iEtVAKHinBdSSh0XXhlEXEei2CLcveJM2fT2WGVlmjk_xvPMqSZD1WRGNVvkUyt3YRK83CsROw1mlqYa-pkB8O6RffMPsm_Jo-47eUc2FvOlfk8eqtVicjn_YDF6C1aJvdE |
| 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=FA-SconvAE-LSTM%3A+Feature-Aligned+Stacked+Convolutional+Autoencoder+with+Long+Short-Term+Memory+Network+for+Soft+Sensor+Modeling&rft.jtitle=Engineering+applications+of+artificial+intelligence&rft.au=Wu%2C+Ping&rft.au=Miao%2C+Zengdi&rft.au=Wang%2C+Ke&rft.au=Gao%2C+Jinfeng&rft.date=2025-06-15&rft.pub=Elsevier+Ltd&rft.issn=0952-1976&rft.volume=150&rft_id=info:doi/10.1016%2Fj.engappai.2025.110535&rft.externalDocID=S0952197625005354 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0952-1976&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0952-1976&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0952-1976&client=summon |