Machine-Learning-Driven Analysis of Wear Loss and Frictional Behavior in Magnesium Hybrid Composites
The wear loss and frictional characteristics of magnesium-based hybrid composites reinforced with boron carbide (B<sub>4</sub>C) particles and graphite filler were the main subjects of the investigation. Key parameters, including reinforcement content (0–10 wt%), applied load (5–30 N), s...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Crystals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4352/15/5/452 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849711768368054272 |
|---|---|
| author | Barun Haldar Hillol Joardar Arpan Kumar Mondal Nashmi H. Alrasheedi Rashid Khan Murugesan P. Papathi |
| author_facet | Barun Haldar Hillol Joardar Arpan Kumar Mondal Nashmi H. Alrasheedi Rashid Khan Murugesan P. Papathi |
| author_sort | Barun Haldar |
| collection | DOAJ |
| description | The wear loss and frictional characteristics of magnesium-based hybrid composites reinforced with boron carbide (B<sub>4</sub>C) particles and graphite filler were the main subjects of the investigation. Key parameters, including reinforcement content (0–10 wt%), applied load (5–30 N), sliding speed (0.5–3 m/s), and sliding distance (500–3000 m), were varied. Data-driven machine learning (ML) algorithms were utilized to identify complex patterns and predict relationships between input variables and output responses. Five distinct machine learning algorithms, Artificial Neural Network (ANN), Random Forest (RF), K-Nearest Neighbor (KNN), Gradient Boosting Machine (GBM), and Support Vector Machine (SVM), were employed to analyze experimental tribological data for predicting wear loss and coefficients of friction (COFs). The performance evaluation showed that ML models effectively predicted friction behavior and wear behavior of magnesium-based hybrid composites using tribological test data. A comparison of model performances revealed that the Gradient Boosting Machine (GBM) provided superior accuracy compared to other machine learning models in predicting both wear loss and the coefficient of friction. Additionally, feature importance analysis indicated that the graphite weight percentage was the most significant influence in predicting the coefficient of friction and wear loss characteristics. |
| format | Article |
| id | doaj-art-32a3e9ed4ff643ff8b998751a17d2a39 |
| institution | DOAJ |
| issn | 2073-4352 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Crystals |
| spelling | doaj-art-32a3e9ed4ff643ff8b998751a17d2a392025-08-20T03:14:32ZengMDPI AGCrystals2073-43522025-05-0115545210.3390/cryst15050452Machine-Learning-Driven Analysis of Wear Loss and Frictional Behavior in Magnesium Hybrid CompositesBarun Haldar0Hillol Joardar1Arpan Kumar Mondal2Nashmi H. Alrasheedi3Rashid Khan4Murugesan P. Papathi5Industrial Engineering Department, College of Engineering, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaDepartment of Mechanical Engineering, C.V. Raman Global University, Bhubaneswar 752054, IndiaDepartment of Mechanical Engineering, National Institute of Technical Teachers Training and Research (NITTTR), Kolkata 700106, IndiaMechanical Engineering Department, College of Engineering, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaMechanical Engineering Department, College of Engineering, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaMechanical Engineering Department, College of Engineering, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaThe wear loss and frictional characteristics of magnesium-based hybrid composites reinforced with boron carbide (B<sub>4</sub>C) particles and graphite filler were the main subjects of the investigation. Key parameters, including reinforcement content (0–10 wt%), applied load (5–30 N), sliding speed (0.5–3 m/s), and sliding distance (500–3000 m), were varied. Data-driven machine learning (ML) algorithms were utilized to identify complex patterns and predict relationships between input variables and output responses. Five distinct machine learning algorithms, Artificial Neural Network (ANN), Random Forest (RF), K-Nearest Neighbor (KNN), Gradient Boosting Machine (GBM), and Support Vector Machine (SVM), were employed to analyze experimental tribological data for predicting wear loss and coefficients of friction (COFs). The performance evaluation showed that ML models effectively predicted friction behavior and wear behavior of magnesium-based hybrid composites using tribological test data. A comparison of model performances revealed that the Gradient Boosting Machine (GBM) provided superior accuracy compared to other machine learning models in predicting both wear loss and the coefficient of friction. Additionally, feature importance analysis indicated that the graphite weight percentage was the most significant influence in predicting the coefficient of friction and wear loss characteristics.https://www.mdpi.com/2073-4352/15/5/452magnesium hybrid compositeswear lossCOFmachine learningsustainable material |
| spellingShingle | Barun Haldar Hillol Joardar Arpan Kumar Mondal Nashmi H. Alrasheedi Rashid Khan Murugesan P. Papathi Machine-Learning-Driven Analysis of Wear Loss and Frictional Behavior in Magnesium Hybrid Composites Crystals magnesium hybrid composites wear loss COF machine learning sustainable material |
| title | Machine-Learning-Driven Analysis of Wear Loss and Frictional Behavior in Magnesium Hybrid Composites |
| title_full | Machine-Learning-Driven Analysis of Wear Loss and Frictional Behavior in Magnesium Hybrid Composites |
| title_fullStr | Machine-Learning-Driven Analysis of Wear Loss and Frictional Behavior in Magnesium Hybrid Composites |
| title_full_unstemmed | Machine-Learning-Driven Analysis of Wear Loss and Frictional Behavior in Magnesium Hybrid Composites |
| title_short | Machine-Learning-Driven Analysis of Wear Loss and Frictional Behavior in Magnesium Hybrid Composites |
| title_sort | machine learning driven analysis of wear loss and frictional behavior in magnesium hybrid composites |
| topic | magnesium hybrid composites wear loss COF machine learning sustainable material |
| url | https://www.mdpi.com/2073-4352/15/5/452 |
| work_keys_str_mv | AT barunhaldar machinelearningdrivenanalysisofwearlossandfrictionalbehaviorinmagnesiumhybridcomposites AT hilloljoardar machinelearningdrivenanalysisofwearlossandfrictionalbehaviorinmagnesiumhybridcomposites AT arpankumarmondal machinelearningdrivenanalysisofwearlossandfrictionalbehaviorinmagnesiumhybridcomposites AT nashmihalrasheedi machinelearningdrivenanalysisofwearlossandfrictionalbehaviorinmagnesiumhybridcomposites AT rashidkhan machinelearningdrivenanalysisofwearlossandfrictionalbehaviorinmagnesiumhybridcomposites AT murugesanppapathi machinelearningdrivenanalysisofwearlossandfrictionalbehaviorinmagnesiumhybridcomposites |