Wear Behavior Analysis and Gated Recurrent Unit Neural Network Prediction of Coefficient of Friction in Al10Cu-B<sub>4</sub>C Composites

Aluminum-based metal matrix composites reinforced with B<sub>4</sub>C are advanced materials recognized for their exceptional combination of lightweight properties, high hardness, and superior wear resistance. These characteristics make them perfectly suited for applications demanding ex...

Full description

Saved in:
Bibliographic Details
Main Authors: Mihail Kolev, Ludmil Drenchev, Veselin Petkov, Rositza Dimitrova, Krasimir Kolev, Boris Yanachkov
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Lubricants
Subjects:
Online Access:https://www.mdpi.com/2075-4442/13/1/6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832588125083271168
author Mihail Kolev
Ludmil Drenchev
Veselin Petkov
Rositza Dimitrova
Krasimir Kolev
Boris Yanachkov
author_facet Mihail Kolev
Ludmil Drenchev
Veselin Petkov
Rositza Dimitrova
Krasimir Kolev
Boris Yanachkov
author_sort Mihail Kolev
collection DOAJ
description Aluminum-based metal matrix composites reinforced with B<sub>4</sub>C are advanced materials recognized for their exceptional combination of lightweight properties, high hardness, and superior wear resistance. These characteristics make them perfectly suited for applications demanding exceptional performance in extreme mechanical and tribological environments. This study investigates the wear behavior, microstructural characteristics, and predictive modeling of Al10Cu-B<sub>4</sub>C composites fabricated via powder metallurgy with varying B<sub>4</sub>C contents (0, 2.5, 5, and 7.5 wt.%). The addition of B<sub>4</sub>C microparticles to Al10Cu composites significantly influenced their tribological properties with 2.5 wt.% B<sub>4</sub>C achieving a 21.74% reduction in the coefficient of friction (COF) and 7.5 wt.% B<sub>4</sub>C providing a remarkable 65.00% improvement in wear resistance. Microstructural analysis using SEM and EDS was conducted on the unreinforced materials and the reinforced composites both before and after the wear tests. To further analyze and predict the tribological performance, a Gated Recurrent Unit neural network was developed to predict COF values. The need for this model arises from its potential to cost-effectively facilitate the prediction of COF, diminishing the need for extensive experimental testing while being noted for its simplicity and ease of implementation in practical applications. The model achieved excellent accuracy with an R<sup>2</sup> of 0.9965 for the test set and 0.9917 for the validation set. Additionally, feature importance analysis using Random Forest models identified reinforcement-related features as the dominant predictors for both COF and mass wear. These findings demonstrate the potential of Al10Cu-B<sub>4</sub>C composites for emerging industrial applications, where enhanced wear resistance and controlled friction are critical for improving efficiency and durability under rigorous operating conditions. Furthermore, this study highlights the efficacy of neural network models in accurately predicting COF, providing a powerful tool for optimizing the performance of advanced composite materials.
format Article
id doaj-art-4790139ecce04c3ebc199f657ffec346
institution Kabale University
issn 2075-4442
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Lubricants
spelling doaj-art-4790139ecce04c3ebc199f657ffec3462025-01-24T13:38:57ZengMDPI AGLubricants2075-44422024-12-01131610.3390/lubricants13010006Wear Behavior Analysis and Gated Recurrent Unit Neural Network Prediction of Coefficient of Friction in Al10Cu-B<sub>4</sub>C CompositesMihail Kolev0Ludmil Drenchev1Veselin Petkov2Rositza Dimitrova3Krasimir Kolev4Boris Yanachkov5Institute of Metal Science, Equipment and Technologies with Hydro- and Aerodynamics Centre “Acad. A. Balevski”, Bulgarian Academy of Sciences, 1574 Sofia, BulgariaInstitute of Metal Science, Equipment and Technologies with Hydro- and Aerodynamics Centre “Acad. A. Balevski”, Bulgarian Academy of Sciences, 1574 Sofia, BulgariaInstitute of Metal Science, Equipment and Technologies with Hydro- and Aerodynamics Centre “Acad. A. Balevski”, Bulgarian Academy of Sciences, 1574 Sofia, BulgariaInstitute of Metal Science, Equipment and Technologies with Hydro- and Aerodynamics Centre “Acad. A. Balevski”, Bulgarian Academy of Sciences, 1574 Sofia, BulgariaInstitute of Metal Science, Equipment and Technologies with Hydro- and Aerodynamics Centre “Acad. A. Balevski”, Bulgarian Academy of Sciences, 1574 Sofia, BulgariaInstitute of Metal Science, Equipment and Technologies with Hydro- and Aerodynamics Centre “Acad. A. Balevski”, Bulgarian Academy of Sciences, 1574 Sofia, BulgariaAluminum-based metal matrix composites reinforced with B<sub>4</sub>C are advanced materials recognized for their exceptional combination of lightweight properties, high hardness, and superior wear resistance. These characteristics make them perfectly suited for applications demanding exceptional performance in extreme mechanical and tribological environments. This study investigates the wear behavior, microstructural characteristics, and predictive modeling of Al10Cu-B<sub>4</sub>C composites fabricated via powder metallurgy with varying B<sub>4</sub>C contents (0, 2.5, 5, and 7.5 wt.%). The addition of B<sub>4</sub>C microparticles to Al10Cu composites significantly influenced their tribological properties with 2.5 wt.% B<sub>4</sub>C achieving a 21.74% reduction in the coefficient of friction (COF) and 7.5 wt.% B<sub>4</sub>C providing a remarkable 65.00% improvement in wear resistance. Microstructural analysis using SEM and EDS was conducted on the unreinforced materials and the reinforced composites both before and after the wear tests. To further analyze and predict the tribological performance, a Gated Recurrent Unit neural network was developed to predict COF values. The need for this model arises from its potential to cost-effectively facilitate the prediction of COF, diminishing the need for extensive experimental testing while being noted for its simplicity and ease of implementation in practical applications. The model achieved excellent accuracy with an R<sup>2</sup> of 0.9965 for the test set and 0.9917 for the validation set. Additionally, feature importance analysis using Random Forest models identified reinforcement-related features as the dominant predictors for both COF and mass wear. These findings demonstrate the potential of Al10Cu-B<sub>4</sub>C composites for emerging industrial applications, where enhanced wear resistance and controlled friction are critical for improving efficiency and durability under rigorous operating conditions. Furthermore, this study highlights the efficacy of neural network models in accurately predicting COF, providing a powerful tool for optimizing the performance of advanced composite materials.https://www.mdpi.com/2075-4442/13/1/6Al10Cu-B<sub>4</sub>C compositesmetal matrix compositeswear characteristicsdry-sliding frictiongated recurrent unitneural network
spellingShingle Mihail Kolev
Ludmil Drenchev
Veselin Petkov
Rositza Dimitrova
Krasimir Kolev
Boris Yanachkov
Wear Behavior Analysis and Gated Recurrent Unit Neural Network Prediction of Coefficient of Friction in Al10Cu-B<sub>4</sub>C Composites
Lubricants
Al10Cu-B<sub>4</sub>C composites
metal matrix composites
wear characteristics
dry-sliding friction
gated recurrent unit
neural network
title Wear Behavior Analysis and Gated Recurrent Unit Neural Network Prediction of Coefficient of Friction in Al10Cu-B<sub>4</sub>C Composites
title_full Wear Behavior Analysis and Gated Recurrent Unit Neural Network Prediction of Coefficient of Friction in Al10Cu-B<sub>4</sub>C Composites
title_fullStr Wear Behavior Analysis and Gated Recurrent Unit Neural Network Prediction of Coefficient of Friction in Al10Cu-B<sub>4</sub>C Composites
title_full_unstemmed Wear Behavior Analysis and Gated Recurrent Unit Neural Network Prediction of Coefficient of Friction in Al10Cu-B<sub>4</sub>C Composites
title_short Wear Behavior Analysis and Gated Recurrent Unit Neural Network Prediction of Coefficient of Friction in Al10Cu-B<sub>4</sub>C Composites
title_sort wear behavior analysis and gated recurrent unit neural network prediction of coefficient of friction in al10cu b sub 4 sub c composites
topic Al10Cu-B<sub>4</sub>C composites
metal matrix composites
wear characteristics
dry-sliding friction
gated recurrent unit
neural network
url https://www.mdpi.com/2075-4442/13/1/6
work_keys_str_mv AT mihailkolev wearbehavioranalysisandgatedrecurrentunitneuralnetworkpredictionofcoefficientoffrictioninal10cubsub4subccomposites
AT ludmildrenchev wearbehavioranalysisandgatedrecurrentunitneuralnetworkpredictionofcoefficientoffrictioninal10cubsub4subccomposites
AT veselinpetkov wearbehavioranalysisandgatedrecurrentunitneuralnetworkpredictionofcoefficientoffrictioninal10cubsub4subccomposites
AT rositzadimitrova wearbehavioranalysisandgatedrecurrentunitneuralnetworkpredictionofcoefficientoffrictioninal10cubsub4subccomposites
AT krasimirkolev wearbehavioranalysisandgatedrecurrentunitneuralnetworkpredictionofcoefficientoffrictioninal10cubsub4subccomposites
AT borisyanachkov wearbehavioranalysisandgatedrecurrentunitneuralnetworkpredictionofcoefficientoffrictioninal10cubsub4subccomposites