Non-parametric multiple inputs prediction model for magnetic field dependent complex modulus of magnetorheological elastomer
This study introduces a novel platform to predict complex modulus variables as a function of the applied magnetic field and other imperative variables using machine learning. The complex modulus prediction of magnetorheological (MR) elastomers is a challenging process, attributable to the material’s...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Research
2022
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/103975/1/MohdHattaMohammad2022_NonParametricMultipleInputsPrediction.pdf |
| _version_ | 1796867566328610816 |
|---|---|
| author | Saharuddin, Kasma Diana Mohammed Ariff, Mohd. Hatta Bahiuddin, Irfan Ubaidillah, Ubaidillah Mazlan, Saiful Amri Abdul Aziz, Siti Aishah Nazmi, Nurhazimah Abdul Fatah, Abdul Yasser Shapiai, Mohd. Ibrahim |
| author_facet | Saharuddin, Kasma Diana Mohammed Ariff, Mohd. Hatta Bahiuddin, Irfan Ubaidillah, Ubaidillah Mazlan, Saiful Amri Abdul Aziz, Siti Aishah Nazmi, Nurhazimah Abdul Fatah, Abdul Yasser Shapiai, Mohd. Ibrahim |
| author_sort | Saharuddin, Kasma Diana |
| collection | ePrints |
| description | This study introduces a novel platform to predict complex modulus variables as a function of the applied magnetic field and other imperative variables using machine learning. The complex modulus prediction of magnetorheological (MR) elastomers is a challenging process, attributable to the material’s highly nonlinear nature. This problem becomes apparent when considering various possible fabrication parameters. Furthermore, traditional parametric modeling methods are limited when applied to solve larger-scale cases involving large databases. Consequently, the application of non-parametric modeling such as machine learning has gained increasing attraction in recent years. Therefore, this work proposes a data-driven approach for predicting multiple input-dependent complex moduli using feedforward neural networks. Besides excitation frequency and magnetic flux density as operating conditions, the inputs consider compositions and curing conditions represented by magnetic particle weight percentage and the curing magnetic field, respectively. Extreme learning machines and artificial neural networks were used to train the models. The simulation results obtained at various curing conditions and other inputs confirm that the predicted complex modulus has high accuracy with an R2 of about 0.997, as compared to the experimental results. Furthermore, the predicted complex modulus pattern and magnetorheological effect agree with the experimental data using both the learned and unlearned data. |
| first_indexed | 2024-03-05T21:29:11Z |
| format | Article |
| id | utm.eprints-103975 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T21:29:11Z |
| publishDate | 2022 |
| publisher | Nature Research |
| record_format | dspace |
| spelling | utm.eprints-1039752023-12-11T01:48:31Z http://eprints.utm.my/103975/ Non-parametric multiple inputs prediction model for magnetic field dependent complex modulus of magnetorheological elastomer Saharuddin, Kasma Diana Mohammed Ariff, Mohd. Hatta Bahiuddin, Irfan Ubaidillah, Ubaidillah Mazlan, Saiful Amri Abdul Aziz, Siti Aishah Nazmi, Nurhazimah Abdul Fatah, Abdul Yasser Shapiai, Mohd. Ibrahim TJ Mechanical engineering and machinery This study introduces a novel platform to predict complex modulus variables as a function of the applied magnetic field and other imperative variables using machine learning. The complex modulus prediction of magnetorheological (MR) elastomers is a challenging process, attributable to the material’s highly nonlinear nature. This problem becomes apparent when considering various possible fabrication parameters. Furthermore, traditional parametric modeling methods are limited when applied to solve larger-scale cases involving large databases. Consequently, the application of non-parametric modeling such as machine learning has gained increasing attraction in recent years. Therefore, this work proposes a data-driven approach for predicting multiple input-dependent complex moduli using feedforward neural networks. Besides excitation frequency and magnetic flux density as operating conditions, the inputs consider compositions and curing conditions represented by magnetic particle weight percentage and the curing magnetic field, respectively. Extreme learning machines and artificial neural networks were used to train the models. The simulation results obtained at various curing conditions and other inputs confirm that the predicted complex modulus has high accuracy with an R2 of about 0.997, as compared to the experimental results. Furthermore, the predicted complex modulus pattern and magnetorheological effect agree with the experimental data using both the learned and unlearned data. Nature Research 2022-12 Article PeerReviewed application/pdf en http://eprints.utm.my/103975/1/MohdHattaMohammad2022_NonParametricMultipleInputsPrediction.pdf Saharuddin, Kasma Diana and Mohammed Ariff, Mohd. Hatta and Bahiuddin, Irfan and Ubaidillah, Ubaidillah and Mazlan, Saiful Amri and Abdul Aziz, Siti Aishah and Nazmi, Nurhazimah and Abdul Fatah, Abdul Yasser and Shapiai, Mohd. Ibrahim (2022) Non-parametric multiple inputs prediction model for magnetic field dependent complex modulus of magnetorheological elastomer. Scientific Reports, 12 (1). pp. 1-19. ISSN 2045-2322 http://dx.doi.org/10.1038/s41598-022-06643-4 DOI:10.1038/s41598-022-06643-4 |
| spellingShingle | TJ Mechanical engineering and machinery Saharuddin, Kasma Diana Mohammed Ariff, Mohd. Hatta Bahiuddin, Irfan Ubaidillah, Ubaidillah Mazlan, Saiful Amri Abdul Aziz, Siti Aishah Nazmi, Nurhazimah Abdul Fatah, Abdul Yasser Shapiai, Mohd. Ibrahim Non-parametric multiple inputs prediction model for magnetic field dependent complex modulus of magnetorheological elastomer |
| title | Non-parametric multiple inputs prediction model for magnetic field dependent complex modulus of magnetorheological elastomer |
| title_full | Non-parametric multiple inputs prediction model for magnetic field dependent complex modulus of magnetorheological elastomer |
| title_fullStr | Non-parametric multiple inputs prediction model for magnetic field dependent complex modulus of magnetorheological elastomer |
| title_full_unstemmed | Non-parametric multiple inputs prediction model for magnetic field dependent complex modulus of magnetorheological elastomer |
| title_short | Non-parametric multiple inputs prediction model for magnetic field dependent complex modulus of magnetorheological elastomer |
| title_sort | non parametric multiple inputs prediction model for magnetic field dependent complex modulus of magnetorheological elastomer |
| topic | TJ Mechanical engineering and machinery |
| url | http://eprints.utm.my/103975/1/MohdHattaMohammad2022_NonParametricMultipleInputsPrediction.pdf |
| work_keys_str_mv | AT saharuddinkasmadiana nonparametricmultipleinputspredictionmodelformagneticfielddependentcomplexmodulusofmagnetorheologicalelastomer AT mohammedariffmohdhatta nonparametricmultipleinputspredictionmodelformagneticfielddependentcomplexmodulusofmagnetorheologicalelastomer AT bahiuddinirfan nonparametricmultipleinputspredictionmodelformagneticfielddependentcomplexmodulusofmagnetorheologicalelastomer AT ubaidillahubaidillah nonparametricmultipleinputspredictionmodelformagneticfielddependentcomplexmodulusofmagnetorheologicalelastomer AT mazlansaifulamri nonparametricmultipleinputspredictionmodelformagneticfielddependentcomplexmodulusofmagnetorheologicalelastomer AT abdulazizsitiaishah nonparametricmultipleinputspredictionmodelformagneticfielddependentcomplexmodulusofmagnetorheologicalelastomer AT nazminurhazimah nonparametricmultipleinputspredictionmodelformagneticfielddependentcomplexmodulusofmagnetorheologicalelastomer AT abdulfatahabdulyasser nonparametricmultipleinputspredictionmodelformagneticfielddependentcomplexmodulusofmagnetorheologicalelastomer AT shapiaimohdibrahim nonparametricmultipleinputspredictionmodelformagneticfielddependentcomplexmodulusofmagnetorheologicalelastomer |