Hybrid Artificial Intelligence Models with Multi Objective Optimization for Prediction of Tribological Behavior of Polytetrafluoroethylene Matrix Composites
This study presents multi-response optimization and prediction tribological behaviors polytetrafluoroethylene (PTFE) matrix composites. For multi-response optimization, the Taguchi model was hybridized with grey relational analysis to produce grey relational grades (GRG). A support vector regression...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/17/8671 |
| _version_ | 1797496300892061696 |
|---|---|
| author | Musa Alhaji Ibrahim Hüseyin Çamur Mahmut A. Savaş Alhassan Kawu Sabo Mamunu Mustapha Sani I. Abba |
| author_facet | Musa Alhaji Ibrahim Hüseyin Çamur Mahmut A. Savaş Alhassan Kawu Sabo Mamunu Mustapha Sani I. Abba |
| author_sort | Musa Alhaji Ibrahim |
| collection | DOAJ |
| description | This study presents multi-response optimization and prediction tribological behaviors polytetrafluoroethylene (PTFE) matrix composites. For multi-response optimization, the Taguchi model was hybridized with grey relational analysis to produce grey relational grades (GRG). A support vector regression (SVR) model was combined with novel Harris Hawks’ optimization (HHO) and swarm particle optimization (PSO) models to form hybrid SVR–HHO and SVR–PSO models to predict the GRG. The prediction ability of the models was appraised using the coefficient of determination (R<sup>2</sup>), correlation coefficient (R), mean square error (MSE), root mean square (RMSE), and mean absolute percentage error (MAPE). The results of the multi-response optimization revealed that the optimal combination of parametric values of GRG for minimum tribological rate was 9 N-1000 mesh-0.14 ms<sup>−1</sup>-55 m (L3G1SD3SS3). An analysis of variance of the GRG showed that a grit size of 94.56% was the most significant parameter influencing the tribological behavior of PTFE matrix composites. The validation results revealed that an improvement of 52% in GRG was achieved. The prediction results of all models showed that the SVR–PSO and SVR–HHO models were superior to the SVR model. Furthermore, the SVR–HHO model produced superior prediction error and the best goodness of fit over the SVR–PSO model. These findings concluded that hybrids models are promising tools in the multi-response optimization and prediction of tribological behaviors of PTFE matrix composites. They can serve as a guide in the design and development of tribological materials. |
| first_indexed | 2024-03-10T03:01:44Z |
| format | Article |
| id | doaj.art-64c02c72633148ceaac93260f4c38be5 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T03:01:44Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-64c02c72633148ceaac93260f4c38be52023-11-23T12:44:38ZengMDPI AGApplied Sciences2076-34172022-08-011217867110.3390/app12178671Hybrid Artificial Intelligence Models with Multi Objective Optimization for Prediction of Tribological Behavior of Polytetrafluoroethylene Matrix CompositesMusa Alhaji Ibrahim0Hüseyin Çamur1Mahmut A. Savaş2Alhassan Kawu Sabo3Mamunu Mustapha4Sani I. Abba5Department of Mechanical Engineering, Faculty of Engineering, Kano University of Science and Technology, Wudil P.M.B. 3244, Kano 713101, NigeriaDepartment of Mechanical Engineering, Faculty of Engineering, Near East University, via Mersin 10, Nicosia 99138, TurkeyDepartment of Mechanical Engineering, Faculty of Engineering, Near East University, via Mersin 10, Nicosia 99138, TurkeyPhysical Planning and Development Unit, Kano University of Science and Technology, Wudil P.M.B. 3244, Kano 713101, NigeriaDepartment of Electrical Engineering, Faculty of Engineering, Kano University of Science and Technology, Wudil P.M.B. 3244, Kano 713101, NigeriaInterdisciplinary Research Center for Membrane and Water Security, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi ArabiaThis study presents multi-response optimization and prediction tribological behaviors polytetrafluoroethylene (PTFE) matrix composites. For multi-response optimization, the Taguchi model was hybridized with grey relational analysis to produce grey relational grades (GRG). A support vector regression (SVR) model was combined with novel Harris Hawks’ optimization (HHO) and swarm particle optimization (PSO) models to form hybrid SVR–HHO and SVR–PSO models to predict the GRG. The prediction ability of the models was appraised using the coefficient of determination (R<sup>2</sup>), correlation coefficient (R), mean square error (MSE), root mean square (RMSE), and mean absolute percentage error (MAPE). The results of the multi-response optimization revealed that the optimal combination of parametric values of GRG for minimum tribological rate was 9 N-1000 mesh-0.14 ms<sup>−1</sup>-55 m (L3G1SD3SS3). An analysis of variance of the GRG showed that a grit size of 94.56% was the most significant parameter influencing the tribological behavior of PTFE matrix composites. The validation results revealed that an improvement of 52% in GRG was achieved. The prediction results of all models showed that the SVR–PSO and SVR–HHO models were superior to the SVR model. Furthermore, the SVR–HHO model produced superior prediction error and the best goodness of fit over the SVR–PSO model. These findings concluded that hybrids models are promising tools in the multi-response optimization and prediction of tribological behaviors of PTFE matrix composites. They can serve as a guide in the design and development of tribological materials.https://www.mdpi.com/2076-3417/12/17/8671PTFEbronzecarbontribological behaviorsTaguchigrey relational analysis |
| spellingShingle | Musa Alhaji Ibrahim Hüseyin Çamur Mahmut A. Savaş Alhassan Kawu Sabo Mamunu Mustapha Sani I. Abba Hybrid Artificial Intelligence Models with Multi Objective Optimization for Prediction of Tribological Behavior of Polytetrafluoroethylene Matrix Composites Applied Sciences PTFE bronze carbon tribological behaviors Taguchi grey relational analysis |
| title | Hybrid Artificial Intelligence Models with Multi Objective Optimization for Prediction of Tribological Behavior of Polytetrafluoroethylene Matrix Composites |
| title_full | Hybrid Artificial Intelligence Models with Multi Objective Optimization for Prediction of Tribological Behavior of Polytetrafluoroethylene Matrix Composites |
| title_fullStr | Hybrid Artificial Intelligence Models with Multi Objective Optimization for Prediction of Tribological Behavior of Polytetrafluoroethylene Matrix Composites |
| title_full_unstemmed | Hybrid Artificial Intelligence Models with Multi Objective Optimization for Prediction of Tribological Behavior of Polytetrafluoroethylene Matrix Composites |
| title_short | Hybrid Artificial Intelligence Models with Multi Objective Optimization for Prediction of Tribological Behavior of Polytetrafluoroethylene Matrix Composites |
| title_sort | hybrid artificial intelligence models with multi objective optimization for prediction of tribological behavior of polytetrafluoroethylene matrix composites |
| topic | PTFE bronze carbon tribological behaviors Taguchi grey relational analysis |
| url | https://www.mdpi.com/2076-3417/12/17/8671 |
| work_keys_str_mv | AT musaalhajiibrahim hybridartificialintelligencemodelswithmultiobjectiveoptimizationforpredictionoftribologicalbehaviorofpolytetrafluoroethylenematrixcomposites AT huseyincamur hybridartificialintelligencemodelswithmultiobjectiveoptimizationforpredictionoftribologicalbehaviorofpolytetrafluoroethylenematrixcomposites AT mahmutasavas hybridartificialintelligencemodelswithmultiobjectiveoptimizationforpredictionoftribologicalbehaviorofpolytetrafluoroethylenematrixcomposites AT alhassankawusabo hybridartificialintelligencemodelswithmultiobjectiveoptimizationforpredictionoftribologicalbehaviorofpolytetrafluoroethylenematrixcomposites AT mamunumustapha hybridartificialintelligencemodelswithmultiobjectiveoptimizationforpredictionoftribologicalbehaviorofpolytetrafluoroethylenematrixcomposites AT saniiabba hybridartificialintelligencemodelswithmultiobjectiveoptimizationforpredictionoftribologicalbehaviorofpolytetrafluoroethylenematrixcomposites |