Prediction of magnetorheological grease compositions using extreme learning machine methods

This paper presents a data-driven model to predict magnetorheological (MR) grease composition as a function of its rheological properties using several machine learning methods. The methods are Single Hidden Layer Feedforward Neural Networks (SLFNs) and Kernel Based-Extreme Learning Ma-chine (KELM)....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bahiuddin, Irfan, Pratama, Nico, Imaduddin, Fitrian, Mazlan, Saiful Amri, Ubaidillah, Mohamad, Norzilawati
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 1
container_start_page
container_title
container_volume 3124
creator Bahiuddin, Irfan
Pratama, Nico
Imaduddin, Fitrian
Mazlan, Saiful Amri
Ubaidillah
Mohamad, Norzilawati
description This paper presents a data-driven model to predict magnetorheological (MR) grease composition as a function of its rheological properties using several machine learning methods. The methods are Single Hidden Layer Feedforward Neural Networks (SLFNs) and Kernel Based-Extreme Learning Ma-chine (KELM). The approach provides high accuracy prediction and the easiness of changing the inputs or outputs as long as the data is available. While the model output is carbonyl iron particles weight percentage, the model in-puts are the slope of the magnetic field density-dependent-yield stress change over the magnetic fields and the off-state yield stress. The kernel functions are varied from radial basis function, wavelet, linear, and polynomial functions. The simulation results of KELM show that R-squared values are more than 90% for both training and testing data. The root mean square errors also show relatively small values. With a relatively lower number of parameters than SLFNs-ELM, KELM can show comparable performance with SLFNs-ELM and Back Propagation neural networks.
doi_str_mv 10.1063/5.0228147
format Conference Proceeding
fullrecord <record><control><sourceid>proquest_scita</sourceid><recordid>TN_cdi_scitation_primary_10_1063_5_0228147</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3111290585</sourcerecordid><originalsourceid>FETCH-LOGICAL-p637-192341dfe6f03a692ec9f7cc68a0277c9cb0de96a389ce1d89b4c3bbec953fbd3</originalsourceid><addsrcrecordid>eNotkM9LwzAcxYMoOKcH_4OAN6EzP5qkOcrQKQz0sIPgIaTpt11G29SkBf3vXdlODx4f3uM9hO4pWVEi-ZNYEcYKmqsLtKBC0ExJKi_RghCdZyznX9foJqUDIUwrVSzQ92eEyrvRhx6HGne26WEMcQ-hDY13tsVNBJsAu9ANIfkZTHhKvm8w_I4ROsAt2NjPRmfd3veAOxj3oUq36Kq2bYK7sy7R7vVlt37Lth-b9_XzNhskVxnVjOe0qkHWhFupGThdK-dkYQlTymlXkgq0tLzQDmhV6DJ3vCyPmOB1WfElejjFDjH8TJBGcwhT7I-NhlNKmSaiEEfq8UQl50c7zzBD9J2Nf4YSM39nhDl_x_8BUTNjKg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>3111290585</pqid></control><display><type>conference_proceeding</type><title>Prediction of magnetorheological grease compositions using extreme learning machine methods</title><source>AIP Journals Complete</source><creator>Bahiuddin, Irfan ; Pratama, Nico ; Imaduddin, Fitrian ; Mazlan, Saiful Amri ; Ubaidillah ; Mohamad, Norzilawati</creator><contributor>Prabowo, Aditya Rio ; Tjahjana, Dominicus Danardono Dwi Prija ; Imaddudin, Fitrian ; Ubaidillah ; Yaningsih, Indri</contributor><creatorcontrib>Bahiuddin, Irfan ; Pratama, Nico ; Imaduddin, Fitrian ; Mazlan, Saiful Amri ; Ubaidillah ; Mohamad, Norzilawati ; Prabowo, Aditya Rio ; Tjahjana, Dominicus Danardono Dwi Prija ; Imaddudin, Fitrian ; Ubaidillah ; Yaningsih, Indri</creatorcontrib><description>This paper presents a data-driven model to predict magnetorheological (MR) grease composition as a function of its rheological properties using several machine learning methods. The methods are Single Hidden Layer Feedforward Neural Networks (SLFNs) and Kernel Based-Extreme Learning Ma-chine (KELM). The approach provides high accuracy prediction and the easiness of changing the inputs or outputs as long as the data is available. While the model output is carbonyl iron particles weight percentage, the model in-puts are the slope of the magnetic field density-dependent-yield stress change over the magnetic fields and the off-state yield stress. The kernel functions are varied from radial basis function, wavelet, linear, and polynomial functions. The simulation results of KELM show that R-squared values are more than 90% for both training and testing data. The root mean square errors also show relatively small values. With a relatively lower number of parameters than SLFNs-ELM, KELM can show comparable performance with SLFNs-ELM and Back Propagation neural networks.</description><identifier>ISSN: 0094-243X</identifier><identifier>EISSN: 1551-7616</identifier><identifier>DOI: 10.1063/5.0228147</identifier><identifier>CODEN: APCPCS</identifier><language>eng</language><publisher>Melville: American Institute of Physics</publisher><subject>Artificial neural networks ; Back propagation networks ; Carbonyls ; Composition ; Greases ; Kernel functions ; Machine learning ; Magnetic fields ; Magnetic properties ; Neural networks ; Polynomials ; Radial basis function ; Rheological properties ; Yield strength ; Yield stress</subject><ispartof>AIP Conference Proceedings, 2024, Vol.3124 (1)</ispartof><rights>Author(s)</rights><rights>2024 Author(s). Published under an exclusive license by AIP Publishing.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://pubs.aip.org/acp/article-lookup/doi/10.1063/5.0228147$$EHTML$$P50$$Gscitation$$H</linktohtml><link.rule.ids>310,311,315,782,786,791,792,796,4514,23937,23938,25147,27931,27932,76392</link.rule.ids></links><search><contributor>Prabowo, Aditya Rio</contributor><contributor>Tjahjana, Dominicus Danardono Dwi Prija</contributor><contributor>Imaddudin, Fitrian</contributor><contributor>Ubaidillah</contributor><contributor>Yaningsih, Indri</contributor><creatorcontrib>Bahiuddin, Irfan</creatorcontrib><creatorcontrib>Pratama, Nico</creatorcontrib><creatorcontrib>Imaduddin, Fitrian</creatorcontrib><creatorcontrib>Mazlan, Saiful Amri</creatorcontrib><creatorcontrib>Ubaidillah</creatorcontrib><creatorcontrib>Mohamad, Norzilawati</creatorcontrib><title>Prediction of magnetorheological grease compositions using extreme learning machine methods</title><title>AIP Conference Proceedings</title><description>This paper presents a data-driven model to predict magnetorheological (MR) grease composition as a function of its rheological properties using several machine learning methods. The methods are Single Hidden Layer Feedforward Neural Networks (SLFNs) and Kernel Based-Extreme Learning Ma-chine (KELM). The approach provides high accuracy prediction and the easiness of changing the inputs or outputs as long as the data is available. While the model output is carbonyl iron particles weight percentage, the model in-puts are the slope of the magnetic field density-dependent-yield stress change over the magnetic fields and the off-state yield stress. The kernel functions are varied from radial basis function, wavelet, linear, and polynomial functions. The simulation results of KELM show that R-squared values are more than 90% for both training and testing data. The root mean square errors also show relatively small values. With a relatively lower number of parameters than SLFNs-ELM, KELM can show comparable performance with SLFNs-ELM and Back Propagation neural networks.</description><subject>Artificial neural networks</subject><subject>Back propagation networks</subject><subject>Carbonyls</subject><subject>Composition</subject><subject>Greases</subject><subject>Kernel functions</subject><subject>Machine learning</subject><subject>Magnetic fields</subject><subject>Magnetic properties</subject><subject>Neural networks</subject><subject>Polynomials</subject><subject>Radial basis function</subject><subject>Rheological properties</subject><subject>Yield strength</subject><subject>Yield stress</subject><issn>0094-243X</issn><issn>1551-7616</issn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2024</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNotkM9LwzAcxYMoOKcH_4OAN6EzP5qkOcrQKQz0sIPgIaTpt11G29SkBf3vXdlODx4f3uM9hO4pWVEi-ZNYEcYKmqsLtKBC0ExJKi_RghCdZyznX9foJqUDIUwrVSzQ92eEyrvRhx6HGne26WEMcQ-hDY13tsVNBJsAu9ANIfkZTHhKvm8w_I4ROsAt2NjPRmfd3veAOxj3oUq36Kq2bYK7sy7R7vVlt37Lth-b9_XzNhskVxnVjOe0qkHWhFupGThdK-dkYQlTymlXkgq0tLzQDmhV6DJ3vCyPmOB1WfElejjFDjH8TJBGcwhT7I-NhlNKmSaiEEfq8UQl50c7zzBD9J2Nf4YSM39nhDl_x_8BUTNjKg</recordid><startdate>20240930</startdate><enddate>20240930</enddate><creator>Bahiuddin, Irfan</creator><creator>Pratama, Nico</creator><creator>Imaduddin, Fitrian</creator><creator>Mazlan, Saiful Amri</creator><creator>Ubaidillah</creator><creator>Mohamad, Norzilawati</creator><general>American Institute of Physics</general><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope></search><sort><creationdate>20240930</creationdate><title>Prediction of magnetorheological grease compositions using extreme learning machine methods</title><author>Bahiuddin, Irfan ; Pratama, Nico ; Imaduddin, Fitrian ; Mazlan, Saiful Amri ; Ubaidillah ; Mohamad, Norzilawati</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p637-192341dfe6f03a692ec9f7cc68a0277c9cb0de96a389ce1d89b4c3bbec953fbd3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Artificial neural networks</topic><topic>Back propagation networks</topic><topic>Carbonyls</topic><topic>Composition</topic><topic>Greases</topic><topic>Kernel functions</topic><topic>Machine learning</topic><topic>Magnetic fields</topic><topic>Magnetic properties</topic><topic>Neural networks</topic><topic>Polynomials</topic><topic>Radial basis function</topic><topic>Rheological properties</topic><topic>Yield strength</topic><topic>Yield stress</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Bahiuddin, Irfan</creatorcontrib><creatorcontrib>Pratama, Nico</creatorcontrib><creatorcontrib>Imaduddin, Fitrian</creatorcontrib><creatorcontrib>Mazlan, Saiful Amri</creatorcontrib><creatorcontrib>Ubaidillah</creatorcontrib><creatorcontrib>Mohamad, Norzilawati</creatorcontrib><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Bahiuddin, Irfan</au><au>Pratama, Nico</au><au>Imaduddin, Fitrian</au><au>Mazlan, Saiful Amri</au><au>Ubaidillah</au><au>Mohamad, Norzilawati</au><au>Prabowo, Aditya Rio</au><au>Tjahjana, Dominicus Danardono Dwi Prija</au><au>Imaddudin, Fitrian</au><au>Ubaidillah</au><au>Yaningsih, Indri</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Prediction of magnetorheological grease compositions using extreme learning machine methods</atitle><btitle>AIP Conference Proceedings</btitle><date>2024-09-30</date><risdate>2024</risdate><volume>3124</volume><issue>1</issue><issn>0094-243X</issn><eissn>1551-7616</eissn><coden>APCPCS</coden><abstract>This paper presents a data-driven model to predict magnetorheological (MR) grease composition as a function of its rheological properties using several machine learning methods. The methods are Single Hidden Layer Feedforward Neural Networks (SLFNs) and Kernel Based-Extreme Learning Ma-chine (KELM). The approach provides high accuracy prediction and the easiness of changing the inputs or outputs as long as the data is available. While the model output is carbonyl iron particles weight percentage, the model in-puts are the slope of the magnetic field density-dependent-yield stress change over the magnetic fields and the off-state yield stress. The kernel functions are varied from radial basis function, wavelet, linear, and polynomial functions. The simulation results of KELM show that R-squared values are more than 90% for both training and testing data. The root mean square errors also show relatively small values. With a relatively lower number of parameters than SLFNs-ELM, KELM can show comparable performance with SLFNs-ELM and Back Propagation neural networks.</abstract><cop>Melville</cop><pub>American Institute of Physics</pub><doi>10.1063/5.0228147</doi><tpages>7</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0094-243X
ispartof AIP Conference Proceedings, 2024, Vol.3124 (1)
issn 0094-243X
1551-7616
language eng
recordid cdi_scitation_primary_10_1063_5_0228147
source AIP Journals Complete
subjects Artificial neural networks
Back propagation networks
Carbonyls
Composition
Greases
Kernel functions
Machine learning
Magnetic fields
Magnetic properties
Neural networks
Polynomials
Radial basis function
Rheological properties
Yield strength
Yield stress
title Prediction of magnetorheological grease compositions using extreme learning machine methods
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-06T09%3A33%3A38IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_scita&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Prediction%20of%20magnetorheological%20grease%20compositions%20using%20extreme%20learning%20machine%20methods&rft.btitle=AIP%20Conference%20Proceedings&rft.au=Bahiuddin,%20Irfan&rft.date=2024-09-30&rft.volume=3124&rft.issue=1&rft.issn=0094-243X&rft.eissn=1551-7616&rft.coden=APCPCS&rft_id=info:doi/10.1063/5.0228147&rft_dat=%3Cproquest_scita%3E3111290585%3C/proquest_scita%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3111290585&rft_id=info:pmid/&rfr_iscdi=true