Microsoft Word 14 Material Removal

Keywords 
 Artificial neural network (ANN), Sugeno fuzzy, fuzzy logic, material removal rate 
(MRR), automatic tool changer (ATC), Back propagation network (BPN) 
 
 
INTERNATIONAL JOURNAL OF MECHANICAL 
ENGINEERING AND TECHNOLOGY (IJMET) 
 
ISSN 0976 – 6340 (Print) 
ISSN 0976 – 6359 (Online
)
Volume 3, Issue 2, May-August (2012), pp. 128-137 
© IAEME: www.iaeme.com/ijmet.html 
Journal Impact Factor (2011):
1.2083 (Calculated by GISI)
www.jifactor.com 
IJMET 
© I A E M E 

---

International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 
6340(Print), ISSN 0976 – 6359(Online) Volume 3, Issue 2, May-August (2012), © IAEME 
129 
1. INTRODUCTION 
  
In the investigation of drilling of C-SiC, the MRR is considered essential as it influences 
the surface finish and the micro geometry of the finished part. Optimum selection of the 
process conditions is extremely important as it determines the MRR which in turn affects 
the surface finish of the machined parts. Thus in this drilling process an improper 
selection of cutting conditions can lead to surfaces with rough finish. 
The resurgence of interest in expert systems over the past few decades has opened many 
new avenues in various applications. Expert systems lead to greater generality and better 
rapport with reality. It is driven by the need for methods of analysis and design, which 
can come to grips with imprecision to achieve robustness and low cost production 
solution [2]. The use of neural network in machining research has been extensive and 
multifaceted. These networks can be trained to recognize arbitrary relations between sets 
of inputs and output pairs by adjusting weights of the interconnections. Back 
propagation neural network is most commonly used in manufacturing research and 
neural network has been used extensively in the past decade to monitor the progress of 
tool condition. Fuzzy modeling is based on the idea to find a set of local input-output 
relations describing a process. So, the method of fuzzy modeling can express a non-
linear process better than any other ordinary method. As more knowledge about the 
system is accumulated the uncertainty diminishes the need for the fuzzy logic treatment 
and it can revert to a deterministic or statistical one. The aim of this experimental and 
analytical work is to identify suitable parameters, the monitoring of which enable the 
prediction of MRR for drilled holes by two expert systems namely Sugeno-Fuzzy and 
Neural network. Both have their own ability in determining the output which determines 
and maintains the quality of drilled surface. Finally the best expert system has to be 
recommended for this drilling job on carbon silicon carbide composite as per their 
limitations and advantages by carrying out comparative analysis among the expert 
systems within the range of experimental values.