PERMODELAN INVERSI PEREDAM MAGNET-REOLOGI BERBASIS JARINGAN SARAF TIRUAN UNTUK SISTEM KENDALI
The application of artificial neural network (ANN) models in magnet-rheological damper modeling is of great interest in recently challenges. Therefore, this study aims to propose a solution to overcome this problem by conducting inverse modeling using an artificial neural network. This inverse model...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Brawijaya
2022-08-01
|
| Series: | Rekayasa Mesin |
| Subjects: | |
| Online Access: | https://rekayasamesin.ub.ac.id/index.php/rm/article/view/962 |
| _version_ | 1811214541792477184 |
|---|---|
| author | Rafly Asprilla Alwi Irfan Bahiuddin Ryandhi Rofifu Chazim Agustinus Winarno Fitrian Imaduddin |
| author_facet | Rafly Asprilla Alwi Irfan Bahiuddin Ryandhi Rofifu Chazim Agustinus Winarno Fitrian Imaduddin |
| author_sort | Rafly Asprilla Alwi |
| collection | DOAJ |
| description | The application of artificial neural network (ANN) models in magnet-rheological damper modeling is of great interest in recently challenges. Therefore, this study aims to propose a solution to overcome this problem by conducting inverse modeling using an artificial neural network. This inverse model is applied to a meandering magnet-rheological valve damper to predict the current to produce the appropriate damping force. The simulation scheme is selected with current as output and damping force, velocity, and displacement as input. The best model is formulated by varying the architecture of the artificial neural network. The best artificial neural network architecture is obtained after doing these variations. The data is divided into 80% training data, 10% validation data, and 10% test data. The activation function used is a logsig function using three hidden layers with the number of neurons in each layer [30-20-30]. The algorithm used in the chosen architecture is Levenberg-Marquardt. The regression value of 0.991 and the MSE value of 0.001 were obtained from the modeling results. The required damping force is ensured that it can be predicted well using the selected artificial neural network. The test proves that the results of the regression constant are 0.999 and the MSE value is 0.0005 when the current output value is inverted to the damper artificial neural network. |
| first_indexed | 2024-04-12T06:05:25Z |
| format | Article |
| id | doaj.art-cab07fec782f45bc8d78ee88a05180e4 |
| institution | Directory Open Access Journal |
| issn | 2338-1663 2477-6041 |
| language | English |
| last_indexed | 2024-04-12T06:05:25Z |
| publishDate | 2022-08-01 |
| publisher | University of Brawijaya |
| record_format | Article |
| series | Rekayasa Mesin |
| spelling | doaj.art-cab07fec782f45bc8d78ee88a05180e42022-12-22T03:44:53ZengUniversity of BrawijayaRekayasa Mesin2338-16632477-60412022-08-0113235135910.21776/jrm.v13i2.962714PERMODELAN INVERSI PEREDAM MAGNET-REOLOGI BERBASIS JARINGAN SARAF TIRUAN UNTUK SISTEM KENDALIRafly Asprilla Alwi0Irfan Bahiuddin1Ryandhi Rofifu Chazim2Agustinus Winarno3Fitrian Imaduddin4Universitas Gadjah MadaUniversitas Gadjah MadaUniversitas Gadjah MadaUniversitas Gadjah MadaUniversitas Sebelas MaretThe application of artificial neural network (ANN) models in magnet-rheological damper modeling is of great interest in recently challenges. Therefore, this study aims to propose a solution to overcome this problem by conducting inverse modeling using an artificial neural network. This inverse model is applied to a meandering magnet-rheological valve damper to predict the current to produce the appropriate damping force. The simulation scheme is selected with current as output and damping force, velocity, and displacement as input. The best model is formulated by varying the architecture of the artificial neural network. The best artificial neural network architecture is obtained after doing these variations. The data is divided into 80% training data, 10% validation data, and 10% test data. The activation function used is a logsig function using three hidden layers with the number of neurons in each layer [30-20-30]. The algorithm used in the chosen architecture is Levenberg-Marquardt. The regression value of 0.991 and the MSE value of 0.001 were obtained from the modeling results. The required damping force is ensured that it can be predicted well using the selected artificial neural network. The test proves that the results of the regression constant are 0.999 and the MSE value is 0.0005 when the current output value is inverted to the damper artificial neural network.https://rekayasamesin.ub.ac.id/index.php/rm/article/view/962magneto-rheoloical fluidmagneto-rheoloical damperinverse modelartificial neural networks |
| spellingShingle | Rafly Asprilla Alwi Irfan Bahiuddin Ryandhi Rofifu Chazim Agustinus Winarno Fitrian Imaduddin PERMODELAN INVERSI PEREDAM MAGNET-REOLOGI BERBASIS JARINGAN SARAF TIRUAN UNTUK SISTEM KENDALI Rekayasa Mesin magneto-rheoloical fluid magneto-rheoloical damper inverse model artificial neural networks |
| title | PERMODELAN INVERSI PEREDAM MAGNET-REOLOGI BERBASIS JARINGAN SARAF TIRUAN UNTUK SISTEM KENDALI |
| title_full | PERMODELAN INVERSI PEREDAM MAGNET-REOLOGI BERBASIS JARINGAN SARAF TIRUAN UNTUK SISTEM KENDALI |
| title_fullStr | PERMODELAN INVERSI PEREDAM MAGNET-REOLOGI BERBASIS JARINGAN SARAF TIRUAN UNTUK SISTEM KENDALI |
| title_full_unstemmed | PERMODELAN INVERSI PEREDAM MAGNET-REOLOGI BERBASIS JARINGAN SARAF TIRUAN UNTUK SISTEM KENDALI |
| title_short | PERMODELAN INVERSI PEREDAM MAGNET-REOLOGI BERBASIS JARINGAN SARAF TIRUAN UNTUK SISTEM KENDALI |
| title_sort | permodelan inversi peredam magnet reologi berbasis jaringan saraf tiruan untuk sistem kendali |
| topic | magneto-rheoloical fluid magneto-rheoloical damper inverse model artificial neural networks |
| url | https://rekayasamesin.ub.ac.id/index.php/rm/article/view/962 |
| work_keys_str_mv | AT raflyasprillaalwi permodelaninversiperedammagnetreologiberbasisjaringansaraftiruanuntuksistemkendali AT irfanbahiuddin permodelaninversiperedammagnetreologiberbasisjaringansaraftiruanuntuksistemkendali AT ryandhirofifuchazim permodelaninversiperedammagnetreologiberbasisjaringansaraftiruanuntuksistemkendali AT agustinuswinarno permodelaninversiperedammagnetreologiberbasisjaringansaraftiruanuntuksistemkendali AT fitrianimaduddin permodelaninversiperedammagnetreologiberbasisjaringansaraftiruanuntuksistemkendali |