Research on Hyperparameter Optimization of Concrete Slump Prediction Model Based on Response Surface Method
In this paper, eight variables of cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate and flow are used as network input and slump is used as network output to construct a back-propagation (BP) neural network. On this basis, the learning rate, momentum fact...
Gespeichert in:
| Veröffentlicht in: | Materials 2022-07, Vol.15 (13), p.4721 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 13 |
| container_start_page | 4721 |
| container_title | Materials |
| container_volume | 15 |
| creator | Chen, Yuan Wu, Jiaye Zhang, Yingqian Fu, Lei Luo, Yunrong Liu, Yong Li, Lindan |
| description | In this paper, eight variables of cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate and flow are used as network input and slump is used as network output to construct a back-propagation (BP) neural network. On this basis, the learning rate, momentum factor, number of hidden nodes and number of iterations are used as hyperparameters to construct 2-layer and 3-layer neural networks respectively. Finally, the response surface method (RSM) is used to optimize the parameters of the network model obtained previously. The results show that the network model with parameters obtained by the response surface method (RSM) has a better coefficient of determination for the test set than the model before optimization, and the optimized model has higher prediction accuracy. At the same time, the model is used to evaluate the influencing factors of each variable on slump. The results show that flow, water, coarse aggregate and fine aggregate are the four main influencing factors, and the maximum influencing factor of flow is 0.875. This also provides a new idea for quickly and effectively adjusting the parameters of the neural network model to improve the prediction accuracy of concrete slump. |
| doi_str_mv | 10.3390/ma15134721 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9267923</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2686035759</sourcerecordid><originalsourceid>FETCH-LOGICAL-c383t-e37c0025d2dc4c02e55dc5ac52ebff33eb58c1737d1d1f2f5c0383003a7681423</originalsourceid><addsrcrecordid>eNpdkU1LxDAQhoMoKroXf0HBiwirSaZp2ougi7qCovhxDtlk6lbbpiatoL_erC5-5TKB95mHGYaQHUYPAAp62GgmGKSSsxWyyYoiG7MiTVd__TfIKIQnGh8Ay3mxTjZA5DTLU9gkz7cYUHszT1ybTN869J32usEefXLd9VVTveu-ipkrk4lrjY9JclcPTZfceLSV-QyvnMU6OdEB7cITnZ1rQwQHX2qDyRX2c2e3yVqp64CjZd0iD2en95Pp-PL6_GJyfDk2kEM_RpCGUi4styY1lKMQ1ghtBMdZWQLgTOSGSZCWWVbyUhga--J2WmY5SzlskaMvbzfMGrQG297rWnW-arR_U05X6m_SVnP16F5VwTNZcIiCvaXAu5cBQ6-aKhisa92iG4LiWS4lzzmXEd39hz65wbdxvQWVURBSFJHa_6KMdyF4LL-HYVQtzqh-zggfzmePAw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2686035759</pqid></control><display><type>article</type><title>Research on Hyperparameter Optimization of Concrete Slump Prediction Model Based on Response Surface Method</title><source>PubMed Central Open Access</source><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><source>Free Full-Text Journals in Chemistry</source><creator>Chen, Yuan ; Wu, Jiaye ; Zhang, Yingqian ; Fu, Lei ; Luo, Yunrong ; Liu, Yong ; Li, Lindan</creator><creatorcontrib>Chen, Yuan ; Wu, Jiaye ; Zhang, Yingqian ; Fu, Lei ; Luo, Yunrong ; Liu, Yong ; Li, Lindan</creatorcontrib><description>In this paper, eight variables of cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate and flow are used as network input and slump is used as network output to construct a back-propagation (BP) neural network. On this basis, the learning rate, momentum factor, number of hidden nodes and number of iterations are used as hyperparameters to construct 2-layer and 3-layer neural networks respectively. Finally, the response surface method (RSM) is used to optimize the parameters of the network model obtained previously. The results show that the network model with parameters obtained by the response surface method (RSM) has a better coefficient of determination for the test set than the model before optimization, and the optimized model has higher prediction accuracy. At the same time, the model is used to evaluate the influencing factors of each variable on slump. The results show that flow, water, coarse aggregate and fine aggregate are the four main influencing factors, and the maximum influencing factor of flow is 0.875. This also provides a new idea for quickly and effectively adjusting the parameters of the neural network model to improve the prediction accuracy of concrete slump.</description><identifier>ISSN: 1996-1944</identifier><identifier>EISSN: 1996-1944</identifier><identifier>DOI: 10.3390/ma15134721</identifier><identifier>PMID: 35806843</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Back propagation ; Back propagation networks ; Blast furnace practice ; Blast furnace slags ; Cement ; Civil engineering ; Concrete mixing ; Design optimization ; Design techniques ; Fly ash ; Genetic algorithms ; Mathematical models ; Neural networks ; Optimization ; Parameters ; Prediction models ; Propagation ; Response surface methodology ; Superplasticizers</subject><ispartof>Materials, 2022-07, Vol.15 (13), p.4721</ispartof><rights>2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2022 by the authors. 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c383t-e37c0025d2dc4c02e55dc5ac52ebff33eb58c1737d1d1f2f5c0383003a7681423</citedby><cites>FETCH-LOGICAL-c383t-e37c0025d2dc4c02e55dc5ac52ebff33eb58c1737d1d1f2f5c0383003a7681423</cites><orcidid>0000-0002-3526-2786</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9267923/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9267923/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,27924,27925,53791,53793</link.rule.ids></links><search><creatorcontrib>Chen, Yuan</creatorcontrib><creatorcontrib>Wu, Jiaye</creatorcontrib><creatorcontrib>Zhang, Yingqian</creatorcontrib><creatorcontrib>Fu, Lei</creatorcontrib><creatorcontrib>Luo, Yunrong</creatorcontrib><creatorcontrib>Liu, Yong</creatorcontrib><creatorcontrib>Li, Lindan</creatorcontrib><title>Research on Hyperparameter Optimization of Concrete Slump Prediction Model Based on Response Surface Method</title><title>Materials</title><description>In this paper, eight variables of cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate and flow are used as network input and slump is used as network output to construct a back-propagation (BP) neural network. On this basis, the learning rate, momentum factor, number of hidden nodes and number of iterations are used as hyperparameters to construct 2-layer and 3-layer neural networks respectively. Finally, the response surface method (RSM) is used to optimize the parameters of the network model obtained previously. The results show that the network model with parameters obtained by the response surface method (RSM) has a better coefficient of determination for the test set than the model before optimization, and the optimized model has higher prediction accuracy. At the same time, the model is used to evaluate the influencing factors of each variable on slump. The results show that flow, water, coarse aggregate and fine aggregate are the four main influencing factors, and the maximum influencing factor of flow is 0.875. This also provides a new idea for quickly and effectively adjusting the parameters of the neural network model to improve the prediction accuracy of concrete slump.</description><subject>Back propagation</subject><subject>Back propagation networks</subject><subject>Blast furnace practice</subject><subject>Blast furnace slags</subject><subject>Cement</subject><subject>Civil engineering</subject><subject>Concrete mixing</subject><subject>Design optimization</subject><subject>Design techniques</subject><subject>Fly ash</subject><subject>Genetic algorithms</subject><subject>Mathematical models</subject><subject>Neural networks</subject><subject>Optimization</subject><subject>Parameters</subject><subject>Prediction models</subject><subject>Propagation</subject><subject>Response surface methodology</subject><subject>Superplasticizers</subject><issn>1996-1944</issn><issn>1996-1944</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpdkU1LxDAQhoMoKroXf0HBiwirSaZp2ougi7qCovhxDtlk6lbbpiatoL_erC5-5TKB95mHGYaQHUYPAAp62GgmGKSSsxWyyYoiG7MiTVd__TfIKIQnGh8Ay3mxTjZA5DTLU9gkz7cYUHszT1ybTN869J32usEefXLd9VVTveu-ipkrk4lrjY9JclcPTZfceLSV-QyvnMU6OdEB7cITnZ1rQwQHX2qDyRX2c2e3yVqp64CjZd0iD2en95Pp-PL6_GJyfDk2kEM_RpCGUi4styY1lKMQ1ghtBMdZWQLgTOSGSZCWWVbyUhga--J2WmY5SzlskaMvbzfMGrQG297rWnW-arR_U05X6m_SVnP16F5VwTNZcIiCvaXAu5cBQ6-aKhisa92iG4LiWS4lzzmXEd39hz65wbdxvQWVURBSFJHa_6KMdyF4LL-HYVQtzqh-zggfzmePAw</recordid><startdate>20220705</startdate><enddate>20220705</enddate><creator>Chen, Yuan</creator><creator>Wu, Jiaye</creator><creator>Zhang, Yingqian</creator><creator>Fu, Lei</creator><creator>Luo, Yunrong</creator><creator>Liu, Yong</creator><creator>Li, Lindan</creator><general>MDPI AG</general><general>MDPI</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SR</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>D1I</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>JG9</scope><scope>KB.</scope><scope>PDBOC</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-3526-2786</orcidid></search><sort><creationdate>20220705</creationdate><title>Research on Hyperparameter Optimization of Concrete Slump Prediction Model Based on Response Surface Method</title><author>Chen, Yuan ; Wu, Jiaye ; Zhang, Yingqian ; Fu, Lei ; Luo, Yunrong ; Liu, Yong ; Li, Lindan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c383t-e37c0025d2dc4c02e55dc5ac52ebff33eb58c1737d1d1f2f5c0383003a7681423</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Back propagation</topic><topic>Back propagation networks</topic><topic>Blast furnace practice</topic><topic>Blast furnace slags</topic><topic>Cement</topic><topic>Civil engineering</topic><topic>Concrete mixing</topic><topic>Design optimization</topic><topic>Design techniques</topic><topic>Fly ash</topic><topic>Genetic algorithms</topic><topic>Mathematical models</topic><topic>Neural networks</topic><topic>Optimization</topic><topic>Parameters</topic><topic>Prediction models</topic><topic>Propagation</topic><topic>Response surface methodology</topic><topic>Superplasticizers</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Chen, Yuan</creatorcontrib><creatorcontrib>Wu, Jiaye</creatorcontrib><creatorcontrib>Zhang, Yingqian</creatorcontrib><creatorcontrib>Fu, Lei</creatorcontrib><creatorcontrib>Luo, Yunrong</creatorcontrib><creatorcontrib>Liu, Yong</creatorcontrib><creatorcontrib>Li, Lindan</creatorcontrib><collection>CrossRef</collection><collection>Engineered Materials Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Materials Science Collection</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>Materials Research Database</collection><collection>Materials Science Database</collection><collection>Materials Science Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Materials</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chen, Yuan</au><au>Wu, Jiaye</au><au>Zhang, Yingqian</au><au>Fu, Lei</au><au>Luo, Yunrong</au><au>Liu, Yong</au><au>Li, Lindan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Research on Hyperparameter Optimization of Concrete Slump Prediction Model Based on Response Surface Method</atitle><jtitle>Materials</jtitle><date>2022-07-05</date><risdate>2022</risdate><volume>15</volume><issue>13</issue><spage>4721</spage><pages>4721-</pages><issn>1996-1944</issn><eissn>1996-1944</eissn><abstract>In this paper, eight variables of cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate and flow are used as network input and slump is used as network output to construct a back-propagation (BP) neural network. On this basis, the learning rate, momentum factor, number of hidden nodes and number of iterations are used as hyperparameters to construct 2-layer and 3-layer neural networks respectively. Finally, the response surface method (RSM) is used to optimize the parameters of the network model obtained previously. The results show that the network model with parameters obtained by the response surface method (RSM) has a better coefficient of determination for the test set than the model before optimization, and the optimized model has higher prediction accuracy. At the same time, the model is used to evaluate the influencing factors of each variable on slump. The results show that flow, water, coarse aggregate and fine aggregate are the four main influencing factors, and the maximum influencing factor of flow is 0.875. This also provides a new idea for quickly and effectively adjusting the parameters of the neural network model to improve the prediction accuracy of concrete slump.</abstract><cop>Basel</cop><pub>MDPI AG</pub><pmid>35806843</pmid><doi>10.3390/ma15134721</doi><orcidid>https://orcid.org/0000-0002-3526-2786</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1996-1944 |
| ispartof | Materials, 2022-07, Vol.15 (13), p.4721 |
| issn | 1996-1944 1996-1944 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9267923 |
| source | PubMed Central Open Access; MDPI - Multidisciplinary Digital Publishing Institute; EZB-FREE-00999 freely available EZB journals; PubMed Central; Free Full-Text Journals in Chemistry |
| subjects | Back propagation Back propagation networks Blast furnace practice Blast furnace slags Cement Civil engineering Concrete mixing Design optimization Design techniques Fly ash Genetic algorithms Mathematical models Neural networks Optimization Parameters Prediction models Propagation Response surface methodology Superplasticizers |
| title | Research on Hyperparameter Optimization of Concrete Slump Prediction Model Based on Response Surface Method |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T11%3A01%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Research%20on%20Hyperparameter%20Optimization%20of%20Concrete%20Slump%20Prediction%20Model%20Based%20on%20Response%20Surface%20Method&rft.jtitle=Materials&rft.au=Chen,%20Yuan&rft.date=2022-07-05&rft.volume=15&rft.issue=13&rft.spage=4721&rft.pages=4721-&rft.issn=1996-1944&rft.eissn=1996-1944&rft_id=info:doi/10.3390/ma15134721&rft_dat=%3Cproquest_pubme%3E2686035759%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2686035759&rft_id=info:pmid/35806843&rfr_iscdi=true |