4.7 Article

Analysis of friction and wear of aluminium AA 5083/WC composites for building applications using advanced machine learning models

Journal

AIN SHAMS ENGINEERING JOURNAL
Volume 14, Issue 9, Pages -

Publisher

ELSEVIER
DOI: 10.1016/j.asej.2022.1020902090-4479

Keywords

Aluminium AA 5083; Fly Ash; Inoculants; ASTM G99; Adhesive; Wear

Ask authors/readers for more resources

This study investigates the influence of fly ash inoculants on the distribution of reinforcements and the tribological characteristics of aluminium composites. The composite specimens are produced by reinforcing tungsten carbide and fly ash in an aluminium matrix. The results show that the addition of fly ash up to a certain threshold improves the wear behavior of the composites.
The aluminium composites have gained greater attention, especially in wear resistant applications. However, reinforcing the ceramic particulates in the aluminium matrix is a major factor influencing the tribological characteristics. In this regard, the influence of Fly Ash inoculants on the uniform distribution of reinforcements and the subsequent tribological characteristics are studied. The composite specimens are produced by reinforcing different wt.% (in the range of 3 to 9 wt%) of Tungsten Carbide (WC) and the Fly Ash (FA) in Aluminium AA 5083 matrix by ultrasonic assisted stir casting in a controlled environment. The wt.% of the reinforcements are chosen based on initial trials and related literature reviews. The stir cast aluminium composites are machined in accordance with the specimen standards to accomplish the pin on disc - adhesive wear following the ASTM G99 standards. The results of the wear test clearly depicts that the increase in the wt.% of fly ash upto a threshold limit (6 wt%) improves the wear behaviour of the composites. This is majorly due to the homogeneity brought about by the fly ash inoculants in dispersing the ceramic reinforcements of WC uniformly in the matrix phase. The experimental findings are also ascertained by the statistical validations and correlated. The results of the experiments and the statistical validations and the outcomes of the optimization will be a base for the use of the composites for wear resistant applications, since the wear of the aluminium composite castings are of prime concern for advanced industrial uses. Further, Artificial Neural Network (ANN) and Machine Learning (ML) models are evolved to predict the tribological characteristics of the composite specimens. The predictions of these models are found to be in clore correlation to the experimental outcomes. (c) 2022 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engineering, Ain Shams University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/ by-nc-nd/4.0/).

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available