P Radha, N Selvakumar (2016) Neural Networks for Predicting the Wear Properties of Sintered Ti-6Al-4V Composite Reinforced with Nano B
4
C Particle and Classiication using
Data Mining Tools. Int J Comput Neural Eng. 3(3), 40-48..
40
OPEN ACCESS http://scidoc.org/IJCNE.php
International Journal of Computational & Neural Engineering (IJCNE)
ISSN 2572-7389
Neural Networks for Predicting the Wear Properties of Sintered Ti-6Al-4V Composite Reinforced with
Nano B
4
C Particle and Classiication using Data Mining Tools
Research Article
P Radha
1*
, N Selvakumar
2
1
Associate Professor, Department of Computer Applications, Mepco Schlenk Engineering College, Sivakasi, Tamilnadu, India.
2
Senior Professor, Department of Mechanical Engineering, Mepco Schlenk Engineering College, Sivakasi, Tamilnadu, India.
Introduction
Titanium matrix composites (TMC) are good-looking materials
for structural application in aircraft, automobile and military
industries. TMC has high strength to weight ratio and good wear
resistance. These have stimulated further research to grow their
applications, by additional enhancement in the properties. Ti-6Al-
4V (Grade 5) is one of the supreme extensively used titanium
alloys, because of its high speciic strength and good corrosion
resistance. However, the foremost disadvantages of titanium and
its alloys are low hardness and poor resistance to sliding wear [1-3].
Ceramic particles such as W, TiC, Al
2
O
3
and Boron carbide (B
4
C)
are mostly used for reinforcement of TMC. B
4
C is one of the
supreme promising ceramic materials due to its good properties,
such as high strength, low density, extreme high hardness and
good chemical stability [4-6]. Many techniques have been used
for the fabrication of Ti-6Al-4V-B
4
C composites such as liquid
phase methods and solid-state consolidation [7-10]. However, due
to its poor wetting between Ti-Al-V and B
4
C, liquid phase method
is dificult. Powder metallurgy (P/M) processing is an alternative
method to fabricate of Ti-6Al-4V-B
4
C composites. Moreover in
this process, the problem of non-wettability of B
4
C with molten
TMC does not arise. Mechanical alloying is a good-looking P/M
technique that produces uniform dispersion of the secondary
particles in the matrix.
By considering the above advantages, the P/M Lab uses
composites preform (Ti-6Al-4V) with an addition of (2-10) wt.
% of nano B
4
C using mechanical alloying method to improve
the strength of materials. This strategy mixes the metal powders
such as Ti, Al and V with B
4
C to avoid the dimension loss of
composites due to friction and heat. While measuring the dry
and high temperature wear using pin-on-disk testing machine, the
temperature, load, sliding distance are varied for identifying the
wear resistance of the prepared composites.
Soft Computing models have been studied in recent years, with
an objective of achieving human like performance in many ields
Abstract
This proposed work is to improve the strength and wear resistance of materials by reinforcing the composite preform (Ti-
6Al-4V) with an addition of (2-10) wt. % of nano boron carbide particles. The characterization was performed through
Scanning electron microscope of above composites. While measuring wear using pin-on-disk testing machine, the tempera-
ture, load, sliding distance are varied for identifying the nature of dry and high temperature wear of prepared composite.
The output of this wear experimental work is fed to the soft computing based tool like Artiicial Neural Network for pre-
dicting the wear properties such as speciic wear rate and coeficient of friction. Further, with respect to the temperature
and B
4
C%, the wear properties are analysed using data mining tool like Decision Tree. Moreover, ixing the range of metal
powders for classifying the wear properties of composite preforms can be automated by using Fuzzy logic.
Keywords: Dry and High Temperature Wear; Ti-6Al-4V; Boron Carbide; Neural Networks; Fuzzy Approach;
Data Mining.
*Corresponding Author:
P. Radha,
Associate Professor, Department of Computer Applications, Mepco Schlenk Engineering College, Sivakasi - 626 005, Tamilnadu, India.
Tel: 04562 235453
Fax: 04562 235111
E-mail: pradha@mepcoeng.ac.in
Received: October 17, 2016
Accepted: December 12, 2016
Published: December 14, 2016
Citation: P Radha, N Selvakumar (2016) Neural Networks for Predicting the Wear Properties of Sintered Ti-6Al-4V Composite Reinforced with Nano B
4
C Particle and Classiication
using Data Mining Tools. Int J Comput Neural Eng. 3(3), 40-48. doi: http://dx.doi.org/10.19070/2572-7389-160006
Copyright: P Radha
©
2016. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution and
reproduction in any medium, provided the original author and source are credited.