Open AccessStudy of Cutting Forces and Prediction of Surface Quality Analysis Using Neural Network Model, Support Vector Regression Model by Various Textured Tool Condition for Ti-6Al-4V Alloy
Author(s) -
D. Arulkirubakaran,
Rukundo Prince,
Rajneesh Kumar,
S. Aravinthkumar,
C. Andrew Joshva
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/923/1/012008
Subject(s) - artificial neural network , machining , materials science , tungsten carbide , surface roughness , tool wear , backpropagation , surface finish , groove (engineering) , support vector machine , linear regression , mechanical engineering , computer science , composite material , metallurgy , artificial intelligence , machine learning , engineering
To evaluate the performance of the textured tool on surface quality with three different types of the textured pattern using Wire-Cut Electrical Discharge Machining (W-EDM) on tungsten carbide cutting tools with two different groove depth dimensions 100 μm& 200μm respectively and the tools are coated with both TiN and TiAlN using Physical Vapour Deposition (PVD) technique. Surface roughness is predicted using the Support Vector Regression, multilayer Artificial Neural Network model (ANN) model. ANN training is carried out with a pure line transfer function and backpropagation algorithm. Easy off machining and good surface finish are achieved through TiAlN coated tool with linear texture along the perpendicular to chip flow direction than the tools considered for experimental and predicted conditions.