Prediction of wear performance of ZK60 / CeO2 composites using machine learning models

Aydın, Fatih; Durgut, Rafet; Mustu, Mustafa; Demir, Bilge

doi:10.1016/j.triboint.2022.107945

Cited by 46 publications

(14 citation statements)

References 90 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RandomForestRegressor class from the scikit-learn library was used for this model. It was previously used for the prediction of the wear rate and COF of graphene-reinforced AMMCs [ 14 ] and for the prediction of the volume loss of ZK60/CeO 2 composites [ 21 ]. k-nearest neighbors (KNN): A non-parametric method that predicts the output of a new instance based on the k-nearest neighbors in the training set [ 40 ].…”

Section: Methodsmentioning

confidence: 99%

“…The DecisionTreeRegressor class from the scikit-learn library was used for this model. DT was previously employed for the prediction of the volume loss of ZK60-CeO 2 composites [ 21 ]. Adaptive boosting (Adaboost): A boosting method that combines multiple weak learners (such as decision trees) into a strong learner by iteratively adjusting the weights of the training instances according to the errors of the previous learners [ 42 ].…”

Section: Methodsmentioning

confidence: 99%

“…The study in [ 19 ] relates the use of machine learning (ML) algorithms to optimizing the wear behavior of ball bearings by reducing the severe vibrations caused by defects. Fatih Aydin et al [ 21 ] fabricated ZK60/CeO 2 with different contents of reinforcement materials (0–1 wt.%) and tested their wear behaviors under different loads (5–30 N). The study also used five ML algorithms to predict the wear behavior based on a limited dataset and compared their performance using statistical measures.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Open-Cell AlSn6Cu-SiC Composites: Fabrication, Dry-Sliding Wear Behavior, and Machine Learning Methods for Wear Prediction

Kolev,

Drenchev,

Petkov

et al. 2023

Materials

View full text Add to dashboard Cite

Open-cell AMMCs are high-strength and lightweight materials with applications in different types of industries. However, one of the main goals in using these materials is to enhance their tribological behavior, which improves their durability and performance under frictional conditions. This study presents an approach for fabricating and predicting the wear behavior of open-cell AlSn6Cu-SiC composites, which are a type of porous AMMCs with improved tribological properties. The composites were fabricated using liquid-state processing, and their tribological properties are investigated by the pin-on-disk method under different loads (50 N and 100 N) and with dry-sliding friction. The microstructure and phase composition of the composites were investigated by scanning electron microscopy, energy-dispersive X-ray spectroscopy, and X-ray diffraction. The mass wear and coefficient of friction (COF) of the materials were measured as quantitative indicators of their tribological behavior. The results showed that the open-cell AlSn6Cu-SiC composite had an enhanced tribological behavior compared to the open-cell AlSn6Cu material in terms of mass wear (38% decrease at 50 N and 31% decrease at 100 N) while maintaining the COF at the same level. The COF of the composites was predicted by six different machine learning methods based on the experimental data. The performance of these models was evaluated by various metrics (R2, MSE, RMSE, and MAE) on the validation and test sets. Based on the results, the open-cell AlSn6Cu-SiC composite outperformed the open-cell AlSn6Cu material in terms of mass loss under different loads with similar COF values. The ML models that were used can predict the COF accurately and reliably based on features, but they are affected by data quality and quantity, overfitting or underfitting, and load change.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Open-Cell AlSn6Cu-SiC Composites: Fabrication, Dry-Sliding Wear Behavior, and Machine Learning Methods for Wear Prediction

Kolev,

Drenchev,

Petkov

et al. 2023

Materials

View full text Add to dashboard Cite

show abstract

“…As a result, the COF increases [103]. Another reason for the rise in the COF with increasing load is the higher plastic deformation on the sample surface [104]. It was reported that the COF of the alloy was higher than that of the composites.…”

Section: Analysis Of Cofmentioning

confidence: 99%

Tribological aspects of magnesium matrix composites: A review of recent experimental studies

Aydın

2023

Tribology - Materials, Surfaces & Interfaces

View full text Add to dashboard Cite

The demand for magnesium (Mg) alloys is increasing in many industries, such as automotive and aerospace, thanks to their low density and high specific strength. However, the poor tribological performance of Mg alloys is one of the most important disadvantages that limit their widespread use. Researchers have developed different approaches to improve the wear performance of Mg alloys, such as alloying, coatings, surface modifications and composite production. Wear performance of systems with sliding parts are crucial for a lifetime and energy efficiency. The development of Mg matrix composites can significantly reduce energy loss by reducing damage from friction and wear. For this reason, it is crucial to understand the wear behaviour of recent Mg matrix composites. The effect of different parameters such as load, sliding speed, reinforcement content, reinforcement type and temperature on the wear performance of Mg matrix composites were investigated.

show abstract

“…Reinforced Mg-based materials are known as Mg matrix composites. [10][11][12][13] Researchers produced Mg matrix composites using reinforcement elements of different sizes (i.e., micron, submicron, nano) via stir casting (SC), disintegrated melt deposition (DMD), friction stir processing (FSP) and powder metallurgy (PM). [14][15][16] For the production of Mg matrix composites, reinforcements such as particles, fibres and whiskers are commonly used.…”

Section: Introductionmentioning

confidence: 99%

Recent advances in mechanical properties of Mg matrix composites: a review

Aydın

2024

Materials Science and Technology

View full text Add to dashboard Cite

Magnesium (Mg), with a density of two-thirds of aluminium (Al) and one-fourth of steel, has become one of the most attractive materials for automotive and aerospace industries owing to the obligation to reduce fuel consumption and gas emissions. However, the poor mechanical property of Mg is one of the most significant barriers to its widespread use. The most widely used method to increase the use potential of Mg is the development of Mg matrix composites. This review focuses on the mechanical properties of recent Mg matrix composites. The effect of different reinforcement materials on the mechanical behaviour and failure mechanisms of Mg matrix composites was evaluated in detail.

show abstract

Prediction of wear performance of ZK60 / CeO2 composites using machine learning models

Cited by 46 publications

References 90 publications

Open-Cell AlSn6Cu-SiC Composites: Fabrication, Dry-Sliding Wear Behavior, and Machine Learning Methods for Wear Prediction

Open-Cell AlSn6Cu-SiC Composites: Fabrication, Dry-Sliding Wear Behavior, and Machine Learning Methods for Wear Prediction

Tribological aspects of magnesium matrix composites: A review of recent experimental studies

Recent advances in mechanical properties of Mg matrix composites: a review

Contact Info

Product

Resources

About