Experimental investigation on mechanical properties of reinforced Al6061 composites and its prediction using KNN-ALO algorithms
by A. Thirumoorthy; T.V. Arjunan; K.L. Senthil Kumar
International Journal of Rapid Manufacturing (IJRAPIDM), Vol. 8, No. 3, 2019

Abstract: Metal matrix composites (MMCs) are widely practicing material for improving the surface property. Stir casting is one of the most straightforward processes of manufacturing MMC and attains higher advantages on material processing cost, more comfortable handling of material, size, design and excellent stability of matrix structure. In this research work, MMC of Al6061 with blended MgO and Si₃N₄ composite mixtures is produced using stir casting process. One of the factors affecting the material homogeneity in the casted material is the tensile rupture, where the proposed composite material subjected to tensile stress and yielding. The structural property of the material tested under universal testing machine and Brinell hardness tester. This paper proposes a novel hybrid approach to evaluate the tensile property of composites. The prediction of the tensile property of the MMC performed by the K-nearest neighbour (KNN) algorithm and ant lion optimisation (ALO) algorithm, which is numerically modelled and experimented in the running platform of MATLAB and compared with decision tree (DT) classifier algorithm for better performance outcome. Predicted test results show that the proposed KNN-ALO is an efficient method for predicting the tensile and hardness properties of stir cast aluminium composites.

Online publication date: Sat, 29-Jun-2019

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Rapid Manufacturing (IJRAPIDM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com