Predictive control of particlesize distribution of crystallization process using deep learning based image analysis
The challenges to regulate the particle‐size distribution (PSD) stem from on‐line measurement of the full distribution and the distributed nature of crystallization process. In this article, a novel nonlinear model predictive control method of PSD for crystallization process is proposed. Radial basi...
Gespeichert in:
| Veröffentlicht in: | AIChE journal 2022-11, Vol.68 (11), p.n/a |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | n/a |
|---|---|
| container_issue | 11 |
| container_start_page | |
| container_title | AIChE journal |
| container_volume | 68 |
| creator | Wang, Liangyong Zhu, Yaolong Gan, Chenyang |
| description | The challenges to regulate the particle‐size distribution (PSD) stem from on‐line measurement of the full distribution and the distributed nature of crystallization process. In this article, a novel nonlinear model predictive control method of PSD for crystallization process is proposed. Radial basis function neural network is adopted to approximate the PSD such that the population balance model with distributed nature can be transformed into the ordinary differential equation (ODE) models. Data driven nonlinear prediction model of the crystallization process is then constructed from the input and output data and further be used in the proposed nonlinear model predictive control algorithm. A deep learning based image analysis technology is developed for online measurement of the PSD. The proposed PSD control method is experimentally implemented on a jacketed batch crystallizer. The results of crystallization experiments demonstrate the effectiveness of the proposed control method. |
| doi_str_mv | 10.1002/aic.17817 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2722980122</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2722980122</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2277-149cfe9c131d92a1da1190dea1b3ecfdcb5a2a9244663bb5b78ca6a9f0f591293</originalsourceid><addsrcrecordid>eNp1kM1OwzAQhC0EEqVw4A0sceKQ1naSJj5WFX9SJTjAOdo4m8qVSYI3AaVPj9tw5bSa2W9Xo2HsVoqFFEItwZqFzHKZnbGZTJMsSrVIz9lMCCGjYMhLdkW0D0pluZoxevNYWdPbb-SmbXrfOt7WvAPfW-OQ7AF5Zan3thx62zbHpfEj9eCcPcDJ6nxrkIgPZJsdrxA77hB8c1QlEFbcfsIOOTTgRrJ0zS5qcIQ3f3POPh4f3jfP0fb16WWz3kZGqSyLZKJNjdrIWFZagaxASi0qBFnGaOrKlCko0CpJVqu4LNMyyw2sQNeiTrVUOp6zu-lvCPg1IPXFvh18CEGFypTSeShBBep-ooxviTzWRedDXj8WUhTHTovQaXHqNLDLif2xDsf_wWL9spkufgHrsXtK</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2722980122</pqid></control><display><type>article</type><title>Predictive control of particlesize distribution of crystallization process using deep learning based image analysis</title><source>Wiley Online Library Journals Frontfile Complete</source><creator>Wang, Liangyong ; Zhu, Yaolong ; Gan, Chenyang</creator><creatorcontrib>Wang, Liangyong ; Zhu, Yaolong ; Gan, Chenyang</creatorcontrib><description>The challenges to regulate the particle‐size distribution (PSD) stem from on‐line measurement of the full distribution and the distributed nature of crystallization process. In this article, a novel nonlinear model predictive control method of PSD for crystallization process is proposed. Radial basis function neural network is adopted to approximate the PSD such that the population balance model with distributed nature can be transformed into the ordinary differential equation (ODE) models. Data driven nonlinear prediction model of the crystallization process is then constructed from the input and output data and further be used in the proposed nonlinear model predictive control algorithm. A deep learning based image analysis technology is developed for online measurement of the PSD. The proposed PSD control method is experimentally implemented on a jacketed batch crystallizer. The results of crystallization experiments demonstrate the effectiveness of the proposed control method.</description><identifier>ISSN: 0001-1541</identifier><identifier>EISSN: 1547-5905</identifier><identifier>DOI: 10.1002/aic.17817</identifier><language>eng</language><publisher>Hoboken, USA: John Wiley & Sons, Inc</publisher><subject>Algorithms ; Control methods ; Control theory ; Crystallization ; crystallization process ; Deep learning ; deep learning network ; Differential equations ; Image analysis ; Image processing ; Machine learning ; model predictive control ; Neural networks ; Nonlinear control ; particle‐size distribution ; Population balance models ; Prediction models ; Predictive control ; Radial basis function ; Size distribution ; Technology assessment</subject><ispartof>AIChE journal, 2022-11, Vol.68 (11), p.n/a</ispartof><rights>2022 American Institute of Chemical Engineers.</rights><rights>2022 American Institute of Chemical Engineers</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c2277-149cfe9c131d92a1da1190dea1b3ecfdcb5a2a9244663bb5b78ca6a9f0f591293</citedby><cites>FETCH-LOGICAL-c2277-149cfe9c131d92a1da1190dea1b3ecfdcb5a2a9244663bb5b78ca6a9f0f591293</cites><orcidid>0000-0001-7811-5228</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2Faic.17817$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Faic.17817$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,776,780,1411,27901,27902,45550,45551</link.rule.ids></links><search><creatorcontrib>Wang, Liangyong</creatorcontrib><creatorcontrib>Zhu, Yaolong</creatorcontrib><creatorcontrib>Gan, Chenyang</creatorcontrib><title>Predictive control of particlesize distribution of crystallization process using deep learning based image analysis</title><title>AIChE journal</title><description>The challenges to regulate the particle‐size distribution (PSD) stem from on‐line measurement of the full distribution and the distributed nature of crystallization process. In this article, a novel nonlinear model predictive control method of PSD for crystallization process is proposed. Radial basis function neural network is adopted to approximate the PSD such that the population balance model with distributed nature can be transformed into the ordinary differential equation (ODE) models. Data driven nonlinear prediction model of the crystallization process is then constructed from the input and output data and further be used in the proposed nonlinear model predictive control algorithm. A deep learning based image analysis technology is developed for online measurement of the PSD. The proposed PSD control method is experimentally implemented on a jacketed batch crystallizer. The results of crystallization experiments demonstrate the effectiveness of the proposed control method.</description><subject>Algorithms</subject><subject>Control methods</subject><subject>Control theory</subject><subject>Crystallization</subject><subject>crystallization process</subject><subject>Deep learning</subject><subject>deep learning network</subject><subject>Differential equations</subject><subject>Image analysis</subject><subject>Image processing</subject><subject>Machine learning</subject><subject>model predictive control</subject><subject>Neural networks</subject><subject>Nonlinear control</subject><subject>particle‐size distribution</subject><subject>Population balance models</subject><subject>Prediction models</subject><subject>Predictive control</subject><subject>Radial basis function</subject><subject>Size distribution</subject><subject>Technology assessment</subject><issn>0001-1541</issn><issn>1547-5905</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNp1kM1OwzAQhC0EEqVw4A0sceKQ1naSJj5WFX9SJTjAOdo4m8qVSYI3AaVPj9tw5bSa2W9Xo2HsVoqFFEItwZqFzHKZnbGZTJMsSrVIz9lMCCGjYMhLdkW0D0pluZoxevNYWdPbb-SmbXrfOt7WvAPfW-OQ7AF5Zan3thx62zbHpfEj9eCcPcDJ6nxrkIgPZJsdrxA77hB8c1QlEFbcfsIOOTTgRrJ0zS5qcIQ3f3POPh4f3jfP0fb16WWz3kZGqSyLZKJNjdrIWFZagaxASi0qBFnGaOrKlCko0CpJVqu4LNMyyw2sQNeiTrVUOp6zu-lvCPg1IPXFvh18CEGFypTSeShBBep-ooxviTzWRedDXj8WUhTHTovQaXHqNLDLif2xDsf_wWL9spkufgHrsXtK</recordid><startdate>202211</startdate><enddate>202211</enddate><creator>Wang, Liangyong</creator><creator>Zhu, Yaolong</creator><creator>Gan, Chenyang</creator><general>John Wiley & Sons, Inc</general><general>American Institute of Chemical Engineers</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7ST</scope><scope>7U5</scope><scope>8FD</scope><scope>C1K</scope><scope>L7M</scope><scope>SOI</scope><orcidid>https://orcid.org/0000-0001-7811-5228</orcidid></search><sort><creationdate>202211</creationdate><title>Predictive control of particlesize distribution of crystallization process using deep learning based image analysis</title><author>Wang, Liangyong ; Zhu, Yaolong ; Gan, Chenyang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2277-149cfe9c131d92a1da1190dea1b3ecfdcb5a2a9244663bb5b78ca6a9f0f591293</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Control methods</topic><topic>Control theory</topic><topic>Crystallization</topic><topic>crystallization process</topic><topic>Deep learning</topic><topic>deep learning network</topic><topic>Differential equations</topic><topic>Image analysis</topic><topic>Image processing</topic><topic>Machine learning</topic><topic>model predictive control</topic><topic>Neural networks</topic><topic>Nonlinear control</topic><topic>particle‐size distribution</topic><topic>Population balance models</topic><topic>Prediction models</topic><topic>Predictive control</topic><topic>Radial basis function</topic><topic>Size distribution</topic><topic>Technology assessment</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wang, Liangyong</creatorcontrib><creatorcontrib>Zhu, Yaolong</creatorcontrib><creatorcontrib>Gan, Chenyang</creatorcontrib><collection>CrossRef</collection><collection>Environment Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Environment Abstracts</collection><jtitle>AIChE journal</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Liangyong</au><au>Zhu, Yaolong</au><au>Gan, Chenyang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Predictive control of particlesize distribution of crystallization process using deep learning based image analysis</atitle><jtitle>AIChE journal</jtitle><date>2022-11</date><risdate>2022</risdate><volume>68</volume><issue>11</issue><epage>n/a</epage><issn>0001-1541</issn><eissn>1547-5905</eissn><abstract>The challenges to regulate the particle‐size distribution (PSD) stem from on‐line measurement of the full distribution and the distributed nature of crystallization process. In this article, a novel nonlinear model predictive control method of PSD for crystallization process is proposed. Radial basis function neural network is adopted to approximate the PSD such that the population balance model with distributed nature can be transformed into the ordinary differential equation (ODE) models. Data driven nonlinear prediction model of the crystallization process is then constructed from the input and output data and further be used in the proposed nonlinear model predictive control algorithm. A deep learning based image analysis technology is developed for online measurement of the PSD. The proposed PSD control method is experimentally implemented on a jacketed batch crystallizer. The results of crystallization experiments demonstrate the effectiveness of the proposed control method.</abstract><cop>Hoboken, USA</cop><pub>John Wiley & Sons, Inc</pub><doi>10.1002/aic.17817</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0001-7811-5228</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0001-1541 |
| ispartof | AIChE journal, 2022-11, Vol.68 (11), p.n/a |
| issn | 0001-1541 1547-5905 |
| language | eng |
| recordid | cdi_proquest_journals_2722980122 |
| source | Wiley Online Library Journals Frontfile Complete |
| subjects | Algorithms Control methods Control theory Crystallization crystallization process Deep learning deep learning network Differential equations Image analysis Image processing Machine learning model predictive control Neural networks Nonlinear control particle‐size distribution Population balance models Prediction models Predictive control Radial basis function Size distribution Technology assessment |
| title | Predictive control of particlesize distribution of crystallization process using deep learning based image analysis |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T06%3A59%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Predictive%20control%20of%20particlesize%20distribution%20of%20crystallization%20process%20using%20deep%20learning%20based%20image%20analysis&rft.jtitle=AIChE%20journal&rft.au=Wang,%20Liangyong&rft.date=2022-11&rft.volume=68&rft.issue=11&rft.epage=n/a&rft.issn=0001-1541&rft.eissn=1547-5905&rft_id=info:doi/10.1002/aic.17817&rft_dat=%3Cproquest_cross%3E2722980122%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2722980122&rft_id=info:pmid/&rfr_iscdi=true |