Artificial intelligence-based forecasting model for incinerator in sulfur recovery units to predict SO2 emissions
Pollutant emissions from chemical plants are a major concern in the context of environmental safety. A reliable emission forecasting model can provide important information for optimizing the process and improving the environmental performance. In this work, forecasting models are developed for the...
Saved in:
| Published in: | Environmental research Vol. 249; p. 118329 |
|---|---|
| Main Authors: | , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Inc
15.05.2024
|
| Subjects: | |
| ISSN: | 0013-9351, 1096-0953, 1096-0953 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Pollutant emissions from chemical plants are a major concern in the context of environmental safety. A reliable emission forecasting model can provide important information for optimizing the process and improving the environmental performance. In this work, forecasting models are developed for the prediction of SO2 emission from a Sulfur Recovery Unit (SRU). Since SRUs incorporate complex chemical reactions, first-principle models are not suitable to predict emission levels based on a given feed condition. Accordingly, artificial intelligence-based models such as standard machine learning (ML) algorithms, multi-layer perceptron (MLP), long short-term memory (LSTM), one-dimensional convolution (1D-CNN), and CNN-LSTM models were tested, and their performance was evaluated. The input features and hyperparameters of the models were optimized to achieve maximum performance. The performance was evaluated in terms of mean squared error (MSE) and mean absolute percentage Error (MAPE) for 1 h, 3 h and 5 h ahead of forecasting. The reported results show that the CNN-LSTM encoder-decoder model outperforms other tested models, with its superiority becoming more pronounced as the forecasting horizon increased from 1 h to 5 h. For the 5-h ahead forecasting, the proposed model showed a MAPE advantage of 17.23%, 4.41%, and 2.83%, respectively over the 1D-CNN, Deep LSTM, and single-layer LSTM models in the larger dataset.
•Pollutant emissions from chemical plants are a major environmental concern.•Emission forecasting models help in decision making to reduce emissions.•First principle models are unsuitable due to complexity of the system.•Machine learning models are tested for predicting SO2 emissions.•CNN-LSTM Encoder-Decoder model is suggested for SO2 emission forecasting. |
|---|---|
| AbstractList | Pollutant emissions from chemical plants are a major concern in the context of environmental safety. A reliable emission forecasting model can provide important information for optimizing the process and improving the environmental performance. In this work, forecasting models are developed for the prediction of SO2 emission from a Sulfur Recovery Unit (SRU). Since SRUs incorporate complex chemical reactions, first-principle models are not suitable to predict emission levels based on a given feed condition. Accordingly, artificial intelligence-based models such as standard machine learning (ML) algorithms, multi-layer perceptron (MLP), long short-term memory (LSTM), one-dimensional convolution (1D-CNN), and CNN-LSTM models were tested, and their performance was evaluated. The input features and hyperparameters of the models were optimized to achieve maximum performance. The performance was evaluated in terms of mean squared error (MSE) and mean absolute percentage Error (MAPE) for 1 h, 3 h and 5 h ahead of forecasting. The reported results show that the CNN-LSTM encoder-decoder model outperforms other tested models, with its superiority becoming more pronounced as the forecasting horizon increased from 1 h to 5 h. For the 5-h ahead forecasting, the proposed model showed a MAPE advantage of 17.23%, 4.41%, and 2.83%, respectively over the 1D-CNN, Deep LSTM, and single-layer LSTM models in the larger dataset.Pollutant emissions from chemical plants are a major concern in the context of environmental safety. A reliable emission forecasting model can provide important information for optimizing the process and improving the environmental performance. In this work, forecasting models are developed for the prediction of SO2 emission from a Sulfur Recovery Unit (SRU). Since SRUs incorporate complex chemical reactions, first-principle models are not suitable to predict emission levels based on a given feed condition. Accordingly, artificial intelligence-based models such as standard machine learning (ML) algorithms, multi-layer perceptron (MLP), long short-term memory (LSTM), one-dimensional convolution (1D-CNN), and CNN-LSTM models were tested, and their performance was evaluated. The input features and hyperparameters of the models were optimized to achieve maximum performance. The performance was evaluated in terms of mean squared error (MSE) and mean absolute percentage Error (MAPE) for 1 h, 3 h and 5 h ahead of forecasting. The reported results show that the CNN-LSTM encoder-decoder model outperforms other tested models, with its superiority becoming more pronounced as the forecasting horizon increased from 1 h to 5 h. For the 5-h ahead forecasting, the proposed model showed a MAPE advantage of 17.23%, 4.41%, and 2.83%, respectively over the 1D-CNN, Deep LSTM, and single-layer LSTM models in the larger dataset. Pollutant emissions from chemical plants are a major concern in the context of environmental safety. A reliable emission forecasting model can provide important information for optimizing the process and improving the environmental performance. In this work, forecasting models are developed for the prediction of SO2 emission from a Sulfur Recovery Unit (SRU). Since SRUs incorporate complex chemical reactions, first-principle models are not suitable to predict emission levels based on a given feed condition. Accordingly, artificial intelligence-based models such as standard machine learning (ML) algorithms, multi-layer perceptron (MLP), long short-term memory (LSTM), one-dimensional convolution (1D-CNN), and CNN-LSTM models were tested, and their performance was evaluated. The input features and hyperparameters of the models were optimized to achieve maximum performance. The performance was evaluated in terms of mean squared error (MSE) and mean absolute percentage Error (MAPE) for 1 h, 3 h and 5 h ahead of forecasting. The reported results show that the CNN-LSTM encoder-decoder model outperforms other tested models, with its superiority becoming more pronounced as the forecasting horizon increased from 1 h to 5 h. For the 5-h ahead forecasting, the proposed model showed a MAPE advantage of 17.23%, 4.41%, and 2.83%, respectively over the 1D-CNN, Deep LSTM, and single-layer LSTM models in the larger dataset. •Pollutant emissions from chemical plants are a major environmental concern.•Emission forecasting models help in decision making to reduce emissions.•First principle models are unsuitable due to complexity of the system.•Machine learning models are tested for predicting SO2 emissions.•CNN-LSTM Encoder-Decoder model is suggested for SO2 emission forecasting. Pollutant emissions from chemical plants are a major concern in the context of environmental safety. A reliable emission forecasting model can provide important information for optimizing the process and improving the environmental performance. In this work, forecasting models are developed for the prediction of SO₂ emission from a Sulfur Recovery Unit (SRU). Since SRUs incorporate complex chemical reactions, first-principle models are not suitable to predict emission levels based on a given feed condition. Accordingly, artificial intelligence-based models such as standard machine learning (ML) algorithms, multi-layer perceptron (MLP), long short-term memory (LSTM), one-dimensional convolution (1D-CNN), and CNN-LSTM models were tested, and their performance was evaluated. The input features and hyperparameters of the models were optimized to achieve maximum performance. The performance was evaluated in terms of mean squared error (MSE) and mean absolute percentage Error (MAPE) for 1 h, 3 h and 5 h ahead of forecasting. The reported results show that the CNN-LSTM encoder-decoder model outperforms other tested models, with its superiority becoming more pronounced as the forecasting horizon increased from 1 h to 5 h. For the 5-h ahead forecasting, the proposed model showed a MAPE advantage of 17.23%, 4.41%, and 2.83%, respectively over the 1D-CNN, Deep LSTM, and single-layer LSTM models in the larger dataset. |
| ArticleNumber | 118329 |
| Author | Jaoude, Maguy A. Berrouk, Abdallah Raj, Abhijeet AlHammadi, Ali A. Thameem, Muhammed |
| Author_xml | – sequence: 1 givenname: Muhammed surname: Thameem fullname: Thameem, Muhammed organization: Department of Chemical Engineering, Khalifa University of Science and Technology, P.O. Box 127788, Abu Dhabi, United Arab Emirates – sequence: 2 givenname: Abhijeet surname: Raj fullname: Raj, Abhijeet organization: Department of Chemical Engineering, Indian Institute of Technology Delhi, New Delhi 110016, India – sequence: 3 givenname: Abdallah orcidid: 0000-0001-7616-726X surname: Berrouk fullname: Berrouk, Abdallah organization: Department of Mechanical Engineering, Khalifa University of Science and Technology, P.O. Box 127788, Abu Dhabi, United Arab Emirates – sequence: 4 givenname: Maguy A. orcidid: 0000-0003-3988-1610 surname: Jaoude fullname: Jaoude, Maguy A. organization: Center for Catalysis and Separations, Khalifa University of Science and Technology, P.O. Box 127788, Abu Dhabi, United Arab Emirates – sequence: 5 givenname: Ali A. orcidid: 0000-0002-2747-2492 surname: AlHammadi fullname: AlHammadi, Ali A. email: ali.aalhammadi@ku.ac.ae organization: Department of Chemical Engineering, Khalifa University of Science and Technology, P.O. Box 127788, Abu Dhabi, United Arab Emirates |
| BookMark | eNqFkT9v2zAQxYkiAeq4-QYdOHaRwyMlS-pQwAiaP4CBDGlmgqJOwRkyaZOUgXz70lGnDgk4kEf83uHuvSt24bxDxr6DWIGA9c1uhe4UMK6kkOUKoFGy_cIWINp1IdpKXbCFEKCKVlXwlV3FuMslVEos2HETEg1kyYycXMJxpFd0FovOROz54ANaExO5V773PY7nnwxachhMen_zOI3DFHgm_QnDG58cpciT54eAPdnEn58kxz3FSN7Fb-xyMGPE63_3kr3c_f5z-1Bsn-4fbzfbwqpapgIRKwEIbW2xXhuQJWDXdKJpRA1VZ2U9NP26A9FZ6AbbG2lEkyExKCihVWrJfsx9D8EfJ4xJ5wlsXtA49FPUKhsATT7lp6hspWpB1SAzWs6oDT7GgIM-BNqb8KZB6HMYeqfnMPQ5DD2HkWU__5NZSiZlP1IwNH4m_jWLMdt1Igw6WjqH1FP2POne08cN_gIphKub |
| CitedBy_id | crossref_primary_10_1002_apj_3136 crossref_primary_10_1016_j_gerr_2025_100132 crossref_primary_10_1002_cjce_25590 crossref_primary_10_1016_j_envres_2024_119832 crossref_primary_10_1007_s41660_025_00500_3 crossref_primary_10_1016_j_envsoft_2025_106438 crossref_primary_10_1061_JHTRBP_HZENG_1483 |
| Cites_doi | 10.1162/neco.1997.9.8.1735 10.1109/TIA.2016.2639456 10.1016/j.compchemeng.2010.07.034 10.1016/j.ins.2021.03.013 10.1016/j.jiec.2015.05.001 10.3390/s22239517 10.1016/j.jngse.2019.103106 10.1016/j.pecs.2020.100848 10.1016/j.applthermaleng.2016.05.012 10.1109/TNNLS.2019.2957366 10.32614/RJ-2017-009 10.1023/A:1022643204877 10.1007/s10462-020-09838-1 10.1016/j.applthermaleng.2019.04.105 10.1016/S0967-0661(03)00079-0 10.3390/s21030823 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier Inc. Copyright © 2024 Elsevier Inc. All rights reserved. |
| Copyright_xml | – notice: 2024 Elsevier Inc. – notice: Copyright © 2024 Elsevier Inc. All rights reserved. |
| DBID | AAYXX CITATION 7X8 7S9 L.6 |
| DOI | 10.1016/j.envres.2024.118329 |
| DatabaseName | CrossRef MEDLINE - Academic AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef MEDLINE - Academic AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | MEDLINE - Academic AGRICOLA |
| Database_xml | – sequence: 1 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Public Health Environmental Sciences |
| EISSN | 1096-0953 |
| ExternalDocumentID | 10_1016_j_envres_2024_118329 S0013935124002330 |
| GroupedDBID | --- --K --M -~X .DC .~1 0R~ 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5RE 5VS 7-5 71M 8P~ 9JM AAEDT AAEDW AAHBH AAIKJ AAKOC AALRI AAOAW AAQFI AATTM AAXKI AAXUO AAYWO ABFYP ABJNI ABLST ABMAC ACDAQ ACGFS ACLOT ACNCT ACRLP ACVFH ADBBV ADCNI ADEZE AEBSH AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AFXIZ AGHFR AGUBO AGYEJ AHEUO AHHHB AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKIFW AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU APXCP AXJTR BKOJK BLECG BLXMC C45 CS3 DM4 DU5 EBS EFBJH EFKBS EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA IHE J1W KCYFY KOM L7B LG5 LY8 M41 MO0 N9A O-L O9- OAUVE OVD OZT P-8 P-9 P2P PC. Q38 RNS ROL RPZ SDF SDG SDP SES SPCBC SSJ SSZ T5K TAE TEORI TN5 TWZ UPT WH7 ZCA ZU3 ~02 ~G- ~HD ~KM .GJ 29G 3O- 53G 9DU AAQXK AAYJJ AAYXX ABEFU ABFNM ABXDB ACRPL ADFGL ADMUD ADNMO ADXHL AEGFY AFFNX AGQPQ ASPBG AVWKF AZFZN CAG CITATION COF EJD FEDTE FGOYB G-2 HMC HVGLF HZ~ OHT R2- SEN SEW VOH WUQ XOL XPP ZGI ZKB ZMT ZXP 7X8 7S9 L.6 |
| ID | FETCH-LOGICAL-c372t-eee501e197ce76a1241eb8b0880715bc27f8d6b10bc1bfcda2a082410f3141933 |
| ISICitedReferencesCount | 6 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001182951900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0013-9351 1096-0953 |
| IngestDate | Thu Oct 02 21:46:27 EDT 2025 Wed Oct 01 13:03:43 EDT 2025 Tue Nov 18 22:43:13 EST 2025 Sat Nov 29 07:03:51 EST 2025 Sat Nov 22 16:51:06 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Claus process Long short-term memory Sulfur recovery unit Convolutional neural network CNN-LSTM Emission forecasting |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c372t-eee501e197ce76a1241eb8b0880715bc27f8d6b10bc1bfcda2a082410f3141933 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0001-7616-726X 0000-0002-2747-2492 0000-0003-3988-1610 |
| PQID | 2923913712 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_3153181814 proquest_miscellaneous_2923913712 crossref_primary_10_1016_j_envres_2024_118329 crossref_citationtrail_10_1016_j_envres_2024_118329 elsevier_sciencedirect_doi_10_1016_j_envres_2024_118329 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-05-15 |
| PublicationDateYYYYMMDD | 2024-05-15 |
| PublicationDate_xml | – month: 05 year: 2024 text: 2024-05-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationTitle | Environmental research |
| PublicationYear | 2024 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Drucker, Burges, Kaufman, Smola, Vapnik (bib6) 1996 Markova (bib17) 2022 Moritz, Bartz-Beielstein (bib19) 2017; 9 Fortuna, Graziani, Rizzo, Xibilia (bib7) 2007 Nabikandi, Fatemi (bib20) 2015; 30 Yuan, Gu, Wang, Yang, Gui (bib31) 2020; 31 Bolf, Mohler, Golob, Galinec, Ivandic (bib1) 2009; 17 Chung, Gulcehre, Cho, Bengio (bib3) 2015 Kadlec, Grbić, Gabrys (bib15) 2011; 35 Jang, Sun, Mizutani (bib13) 1997 Quek, Balasubramanian, Rangaiah (bib23) 2000; 79 Van Houdt, Mosquera, Nápoles (bib28) 2020; 53 Wijesekara, Liyanage (bib29) 2020 Jacobs (bib12) 1992 Zarei, Ganji, Sadi, Rashidzadeh (bib32) 2016; 103 Hochreiter, Schmidhuber (bib10) 1997; 9 Mehmood, Alhasani, Alamoodi, AlWahedi, Ibrahim, Raj (bib18) 2020; 74 (bib4) 1974 Fortuna, Rizzo, Sinatra, Xibilia (bib8) 2003; 11 Yoav, Murphy, Ku, Peterson, Spiro, Stylianos, Wu (bib30) 2019 Ke, Huang, Yang, Jiang (bib16) 2017 Patanè, Xibilia (bib22) 2021; 566 Quinlan (bib24) 1986; 1 Rasmussen, Williams (bib26) 2005 Jones (bib14) 2011 Ibrahim, Rahman, Raj (bib11) 2019; 156 Curreri, Patanè, Xibilia (bib5) 2021; 21 Smith, Cole (bib27) 2017; 53 Ouyang, Zeng, Li, Luo (bib21) 2020 Raj, Ibrahim, Jagannath (bib25) 2020; 80 Chen, Grant, Cowan (bib2) 1991 Guessoum, Belda, Ferrandiz, Modiri, Raut, Dhar, Heinkelmann, Schuh (bib9) 2022; 22 Quek (10.1016/j.envres.2024.118329_bib23) 2000; 79 Van Houdt (10.1016/j.envres.2024.118329_bib28) 2020; 53 Hochreiter (10.1016/j.envres.2024.118329_bib10) 1997; 9 Quinlan (10.1016/j.envres.2024.118329_bib24) 1986; 1 Smith (10.1016/j.envres.2024.118329_bib27) 2017; 53 Kadlec (10.1016/j.envres.2024.118329_bib15) 2011; 35 Jacobs (10.1016/j.envres.2024.118329_bib12) 1992 Nabikandi (10.1016/j.envres.2024.118329_bib20) 2015; 30 Ke (10.1016/j.envres.2024.118329_bib16) 2017 Fortuna (10.1016/j.envres.2024.118329_bib8) 2003; 11 Ouyang (10.1016/j.envres.2024.118329_bib21) 2020 Markova (10.1016/j.envres.2024.118329_bib17) 2022 Chen (10.1016/j.envres.2024.118329_bib2) 1991 Fortuna (10.1016/j.envres.2024.118329_bib7) 2007 Bolf (10.1016/j.envres.2024.118329_bib1) 2009; 17 Curreri (10.1016/j.envres.2024.118329_bib5) 2021; 21 Drucker (10.1016/j.envres.2024.118329_bib6) 1996 Jones (10.1016/j.envres.2024.118329_bib14) 2011 (10.1016/j.envres.2024.118329_bib4) 1974 Chung (10.1016/j.envres.2024.118329_bib3) 2015 Zarei (10.1016/j.envres.2024.118329_bib32) 2016; 103 Mehmood (10.1016/j.envres.2024.118329_bib18) 2020; 74 Jang (10.1016/j.envres.2024.118329_bib13) 1997 Rasmussen (10.1016/j.envres.2024.118329_bib26) 2005 Yoav (10.1016/j.envres.2024.118329_bib30) 2019 Wijesekara (10.1016/j.envres.2024.118329_bib29) 2020 Yuan (10.1016/j.envres.2024.118329_bib31) 2020; 31 Ibrahim (10.1016/j.envres.2024.118329_bib11) 2019; 156 Raj (10.1016/j.envres.2024.118329_bib25) 2020; 80 Guessoum (10.1016/j.envres.2024.118329_bib9) 2022; 22 Moritz (10.1016/j.envres.2024.118329_bib19) 2017; 9 Patanè (10.1016/j.envres.2024.118329_bib22) 2021; 566 |
| References_xml | – start-page: 5027 year: 2020 end-page: 5032 ident: bib21 article-title: A novel spatial-temporal fusion deep neural network for soft sensing of industrial processes publication-title: 2020 Chinese Automation Congress (CAC) – year: 1996 ident: bib6 article-title: Support vector regression machines publication-title: Advances in Neural Information Processing Systems – volume: 11 start-page: 1491 year: 2003 end-page: 1500 ident: bib8 article-title: Soft analyzers for a sulfur recovery unit publication-title: Control Eng. Pract. – volume: 53 start-page: 1717 year: 2017 end-page: 1721 ident: bib27 article-title: Software versus hardware approach to emissions monitoring publication-title: IEEE Trans. Ind. Appl. – year: 1974 ident: bib4 article-title: Air Quality and Stationary Source Emission Control – volume: 1 start-page: 81 year: 1986 end-page: 106 ident: bib24 article-title: Induction of decision trees publication-title: Mach. Learn. – volume: 103 start-page: 1095 year: 2016 end-page: 1104 ident: bib32 article-title: Thermo-kinetic modeling and optimization of the sulfur recovery unit thermal stage publication-title: Appl. Therm. Eng. – year: 2011 ident: bib14 article-title: Steady State and Dynamic Modeling of the Modified Claus Process as Part of an IGCC Power Plant – volume: 9 start-page: 207 year: 2017 ident: bib19 article-title: imputeTS: time series missing value imputation in R publication-title: R J – year: 2019 ident: bib30 article-title: CRU Sulphur 2019 – AI in Sulfur Recovery – Integration of Analyzers to Achieve Tighter Control – start-page: 2067 year: 2015 end-page: 2075 ident: bib3 article-title: Gated feedback recurrent neural networks publication-title: Proceedings of the 32nd International Conference on Machine Learning, Proceedings of Machine Learning Research – volume: 79 start-page: 101 year: 2000 end-page: 106 ident: bib23 article-title: Consider using “soft analyzers” to improve SRU control publication-title: Hydrocarb. Process. – volume: 566 start-page: 195 year: 2021 end-page: 214 ident: bib22 article-title: Echo-state networks for soft sensor design in an SRU process publication-title: Inf. Sci. – volume: 74 year: 2020 ident: bib18 article-title: An evaluation of kinetic models for the simulation of Claus reaction furnaces in sulfur recovery units under different feed conditions publication-title: J. Nat. Gas Sci. Eng. – year: 1991 ident: bib2 article-title: Orthogonal least squares algorithm for training multi-output radial basis function networks publication-title: Second International Conference on Artificial Neural Networks – volume: 21 start-page: 823 year: 2021 ident: bib5 article-title: RNN- and LSTM-based soft sensors transferability for an industrial process publication-title: Sensors – year: 1997 ident: bib13 article-title: Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence – volume: 31 start-page: 4737 year: 2020 end-page: 4746 ident: bib31 article-title: A deep supervised learning framework for data-driven soft sensor modeling of industrial processes publication-title: IEEE Transact. Neural Networks Learn. Syst. – volume: 30 start-page: 50 year: 2015 end-page: 63 ident: bib20 article-title: Kinetic modelling of a commercial sulfur recovery unit based on Claus straight through process: comparison with equilibrium model publication-title: J. Ind. Eng. Chem. – year: 2022 ident: bib17 article-title: Convolutional Neural Networks for Forex Time Series Forecasting – volume: 53 start-page: 5929 year: 2020 end-page: 5955 ident: bib28 article-title: A review on the long short-term memory model publication-title: Artif. Intell. Rev. – volume: 35 start-page: 1 year: 2011 end-page: 24 ident: bib15 article-title: Review of adaptation mechanisms for data-driven soft sensors publication-title: Comput. Chem. Eng. – volume: 17 start-page: 1191 year: 2009 end-page: 1196 ident: bib1 article-title: Software sensor for sulphur recovery unit control publication-title: Chem Eng Trans – volume: 22 start-page: 9517 year: 2022 ident: bib9 article-title: The short-term prediction of length of day using 1D convolutional neural networks (1D CNN) publication-title: Sensors – start-page: 65 year: 1992 end-page: 101 ident: bib12 article-title: Independent identically distributed (IID) random variables publication-title: Discrete Stochastics – year: 2005 ident: bib26 article-title: Gaussian Processes for Machine Learning – volume: 80 year: 2020 ident: bib25 article-title: Combustion kinetics of H2S and other sulfurous species with relevance to industrial processes publication-title: Prog. Energy Combust. Sci. – year: 2007 ident: bib7 article-title: Soft Sensors for Monitoring and Control of Industrial Processes – start-page: 257 year: 2020 end-page: 269 ident: bib29 article-title: Comparison of Imputation Methods for Missing Values in Air Pollution Data: Case Study on Sydney Air Quality Index – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: bib10 article-title: Long short-term memory publication-title: Neural Comput. – start-page: 1 year: 2017 end-page: 6 ident: bib16 article-title: Soft sensor development and applications based on LSTM in deep neural networks publication-title: 2017 IEEE Symposium Series on Computational Intelligence (SSCI) – volume: 156 start-page: 576 year: 2019 end-page: 586 ident: bib11 article-title: Dual-stage acid gas combustion to increase sulfur recovery and decrease the number of catalytic units in sulfur recovery units publication-title: Appl. Therm. Eng. – volume: 17 start-page: 1191 year: 2009 ident: 10.1016/j.envres.2024.118329_bib1 article-title: Software sensor for sulphur recovery unit control publication-title: Chem Eng Trans – year: 1974 ident: 10.1016/j.envres.2024.118329_bib4 – volume: 9 start-page: 1735 year: 1997 ident: 10.1016/j.envres.2024.118329_bib10 article-title: Long short-term memory publication-title: Neural Comput. doi: 10.1162/neco.1997.9.8.1735 – volume: 53 start-page: 1717 year: 2017 ident: 10.1016/j.envres.2024.118329_bib27 article-title: Software versus hardware approach to emissions monitoring publication-title: IEEE Trans. Ind. Appl. doi: 10.1109/TIA.2016.2639456 – volume: 35 start-page: 1 year: 2011 ident: 10.1016/j.envres.2024.118329_bib15 article-title: Review of adaptation mechanisms for data-driven soft sensors publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2010.07.034 – volume: 566 start-page: 195 year: 2021 ident: 10.1016/j.envres.2024.118329_bib22 article-title: Echo-state networks for soft sensor design in an SRU process publication-title: Inf. Sci. doi: 10.1016/j.ins.2021.03.013 – volume: 30 start-page: 50 year: 2015 ident: 10.1016/j.envres.2024.118329_bib20 article-title: Kinetic modelling of a commercial sulfur recovery unit based on Claus straight through process: comparison with equilibrium model publication-title: J. Ind. Eng. Chem. doi: 10.1016/j.jiec.2015.05.001 – year: 2005 ident: 10.1016/j.envres.2024.118329_bib26 – year: 2007 ident: 10.1016/j.envres.2024.118329_bib7 – start-page: 2067 year: 2015 ident: 10.1016/j.envres.2024.118329_bib3 article-title: Gated feedback recurrent neural networks – volume: 79 start-page: 101 year: 2000 ident: 10.1016/j.envres.2024.118329_bib23 article-title: Consider using “soft analyzers” to improve SRU control publication-title: Hydrocarb. Process. – start-page: 1 year: 2017 ident: 10.1016/j.envres.2024.118329_bib16 article-title: Soft sensor development and applications based on LSTM in deep neural networks – volume: 22 start-page: 9517 year: 2022 ident: 10.1016/j.envres.2024.118329_bib9 article-title: The short-term prediction of length of day using 1D convolutional neural networks (1D CNN) publication-title: Sensors doi: 10.3390/s22239517 – start-page: 257 year: 2020 ident: 10.1016/j.envres.2024.118329_bib29 – start-page: 5027 year: 2020 ident: 10.1016/j.envres.2024.118329_bib21 article-title: A novel spatial-temporal fusion deep neural network for soft sensing of industrial processes – volume: 74 year: 2020 ident: 10.1016/j.envres.2024.118329_bib18 article-title: An evaluation of kinetic models for the simulation of Claus reaction furnaces in sulfur recovery units under different feed conditions publication-title: J. Nat. Gas Sci. Eng. doi: 10.1016/j.jngse.2019.103106 – volume: 80 year: 2020 ident: 10.1016/j.envres.2024.118329_bib25 article-title: Combustion kinetics of H2S and other sulfurous species with relevance to industrial processes publication-title: Prog. Energy Combust. Sci. doi: 10.1016/j.pecs.2020.100848 – year: 2011 ident: 10.1016/j.envres.2024.118329_bib14 – year: 2022 ident: 10.1016/j.envres.2024.118329_bib17 – volume: 103 start-page: 1095 year: 2016 ident: 10.1016/j.envres.2024.118329_bib32 article-title: Thermo-kinetic modeling and optimization of the sulfur recovery unit thermal stage publication-title: Appl. Therm. Eng. doi: 10.1016/j.applthermaleng.2016.05.012 – volume: 31 start-page: 4737 year: 2020 ident: 10.1016/j.envres.2024.118329_bib31 article-title: A deep supervised learning framework for data-driven soft sensor modeling of industrial processes publication-title: IEEE Transact. Neural Networks Learn. Syst. doi: 10.1109/TNNLS.2019.2957366 – year: 2019 ident: 10.1016/j.envres.2024.118329_bib30 – year: 1996 ident: 10.1016/j.envres.2024.118329_bib6 article-title: Support vector regression machines – start-page: 65 year: 1992 ident: 10.1016/j.envres.2024.118329_bib12 article-title: Independent identically distributed (IID) random variables – volume: 9 start-page: 207 year: 2017 ident: 10.1016/j.envres.2024.118329_bib19 article-title: imputeTS: time series missing value imputation in R publication-title: R J doi: 10.32614/RJ-2017-009 – volume: 1 start-page: 81 year: 1986 ident: 10.1016/j.envres.2024.118329_bib24 article-title: Induction of decision trees publication-title: Mach. Learn. doi: 10.1023/A:1022643204877 – volume: 53 start-page: 5929 year: 2020 ident: 10.1016/j.envres.2024.118329_bib28 article-title: A review on the long short-term memory model publication-title: Artif. Intell. Rev. doi: 10.1007/s10462-020-09838-1 – year: 1997 ident: 10.1016/j.envres.2024.118329_bib13 – volume: 156 start-page: 576 year: 2019 ident: 10.1016/j.envres.2024.118329_bib11 article-title: Dual-stage acid gas combustion to increase sulfur recovery and decrease the number of catalytic units in sulfur recovery units publication-title: Appl. Therm. Eng. doi: 10.1016/j.applthermaleng.2019.04.105 – volume: 11 start-page: 1491 year: 2003 ident: 10.1016/j.envres.2024.118329_bib8 article-title: Soft analyzers for a sulfur recovery unit publication-title: Control Eng. Pract. doi: 10.1016/S0967-0661(03)00079-0 – year: 1991 ident: 10.1016/j.envres.2024.118329_bib2 article-title: Orthogonal least squares algorithm for training multi-output radial basis function networks – volume: 21 start-page: 823 year: 2021 ident: 10.1016/j.envres.2024.118329_bib5 article-title: RNN- and LSTM-based soft sensors transferability for an industrial process publication-title: Sensors doi: 10.3390/s21030823 |
| SSID | ssj0011530 |
| Score | 2.4523952 |
| Snippet | Pollutant emissions from chemical plants are a major concern in the context of environmental safety. A reliable emission forecasting model can provide... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 118329 |
| SubjectTerms | Claus process CNN-LSTM Convolutional neural network data collection Emission forecasting environmental performance incinerators Long short-term memory neural networks pollutants prediction sulfur Sulfur recovery unit |
| Title | Artificial intelligence-based forecasting model for incinerator in sulfur recovery units to predict SO2 emissions |
| URI | https://dx.doi.org/10.1016/j.envres.2024.118329 https://www.proquest.com/docview/2923913712 https://www.proquest.com/docview/3153181814 |
| Volume | 249 |
| WOSCitedRecordID | wos001182951900001&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: 1096-0953 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0011530 issn: 0013-9351 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLa6jgckhGAwMS6TkXirUiVxMiePBQ3BJAbShtS3yLEdtm4kJU2qTeLHc46d26imARIvkeUmzuX76nN8fC6EvJFKhcJnmQPTYuBgQjknUkI4mRSKmQzoyjXFJvjxcTSfx19Go59tLMz6kud5dHUVL_8r1NAHYGPo7F_A3Q0KHdAG0OEIsMPxj4Cflcb9xxTjGOTbdFBeKfQq1FKsjLOzqYJj_AzR4I7ppyvTRpf1rC4nuFiG17-e1DluL4CWuixxX6eanHz2J1gobtVZ-1rjfh83ZyoGDGxlxvtEfNfaGmHrM7SZq36fyWwjzdKz84Xug7Lf6rIs6gv7k0KjfzfYkShqmzP4k_hWX09m06EFAyiByU_D3qzWhtbc8Pw0ZSdi1mSjbaZq36Y33Zj2rQViMdX5Gt5sijcBWQCTVdyLuc758MSovTAyus_6jLlbZNsHkkZjsj37eDg_6nahQBq4bQUMvKANvTT-gZv3uk21-U3IG83l9BF52Cw56MxS5TEZ6XyH7N5AijZT_GqHPLCGXGrj056QHz2f6Caf6IBP1PAJe-iAT9Cmlk-05RM1fKJVQRs-UeAT7fj0lHx9f3j67oPT1OlwJON-5WitQ9fTXsyl5gcCvqun0ygF-QX6a5hKn2eROkg9N5VemkklfAGKZ-C5GfMCWECwXTLOi1w_IzQMeOy6qQhTUDuFL2OXwwJFZYCEkm4W7xHWfuJENknssZbKZdJ6Ky4SC0yCwCQWmD3idFctbRKXO87nLXpJo4haBTMBwt1x5esW7AS-Gm6-iVwXNZwEK6nYY9zzbz-HwWuCxh15wfN_foIX5H7_H3tJxlVZ61fknlxX56tyn2zxebTf8PwXKL_N6g |
| 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=Artificial+intelligence-based+forecasting+model+for+incinerator+in+sulfur+recovery+units+to+predict+SO2+emissions&rft.jtitle=Environmental+research&rft.au=Thameem%2C+Muhammed&rft.au=Raj%2C+Abhijeet&rft.au=Berrouk%2C+Abdallah&rft.au=Jaoude%2C+Maguy+A.&rft.date=2024-05-15&rft.pub=Elsevier+Inc&rft.issn=0013-9351&rft.volume=249&rft_id=info:doi/10.1016%2Fj.envres.2024.118329&rft.externalDocID=S0013935124002330 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0013-9351&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0013-9351&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0013-9351&client=summon |