Please use this identifier to cite or link to this item: http://nopr.niscair.res.in/handle/123456789/53503
Title: Estimation of surface roughness on Ti-6Al-4V in high speed micro end milling by ANFIS model
Authors: Bandapalli, Chakradhar
Sutaria, Bharatkumar Mohanbhai
Bhatt, Dhananjay Vishnuprasad
Keywords: Micro end milling;ANFIS;Ti-6Al-4V;Surface roughness
Issue Date: Oct-2019
Publisher: NISCAIR-CSIR, India
Abstract: Titanium and its alloys are a few of the most suitable materials in medical applications due to their biocompatibility, anticorrosion and desirable mechanical properties compared to other materials like commercially pure Nb & Ta, Cr-Co alloys and stainless steels. High speed micro end milling is one of the favorable methods for accomplishing micro features on hard metals/alloys with better quality products delivering efficiently in shorter lead and production times. In this paper, experimental investigation of machining parameters influence on surface roughness in high speed micro end milling of Ti-6Al-4V using uncoated tungsten carbide tools under dry cutting conditions and prediction of surface roughness using adaptive neuro- fuzzy inference system (ANFIS) methodology has been presented. Using MATLAB tool box - ANFIS approach four membership functions - triangular, trapezoidal, gbell, gauss has been chosen during the training process in order to evaluate the prediction accuracy of surface roughness. The model’s predictions have been compared with experimental data for verifying the approach. From the comparison of four membership functions, the prediction accuracy of ANFIS has been reached 99.96% using general bell membership function. The most influential factor which influences the surface roughness has the feed rate followed by depth of cut.
Page(s): 379-389
URI: http://nopr.niscair.res.in/handle/123456789/53503
ISSN: 0975-1017 (Online); 0971-4588 (Print)
Appears in Collections:IJEMS Vol.26(5&6) [October & December 2019]

Files in This Item:
File Description SizeFormat 
IJEMS 26(5&6) 379-389.pdf2.65 MBAdobe PDFView/Open


Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.