Neural Network Process Modelling for Turning of Aluminium (6061) using Cemented Carbide Inserts

Abstract

This paper deals with study using soft computing techniques, namely Artificial Neural Networks ANN, in predicting the surface roughness in turning process. Some of machining variables that have a major impact on the surface roughness in turning process such as spindle speed, feed rate and depth of cut were considered as inputs and surface roughness as output. Surface roughness, is the most specified customer requirements in a machining process. For efficient use of machine tools, optimum cutting parameters (speed, feed and depth of cut) are required. Therefore it is necessary to find a suitable optimization method which can find optimum values of cutting parameters for minimizing surface roughness. The turning process parameter optimization is highly constrained and nonlinear. In present work, machining process was carried out on Aluminium (6061) material and surface roughness was measured using Surface Roughness Tester. To predict the surface roughness, neural network model was designed through Multilayer Pereceptron network for the data obtained. The predicted surface roughness values computed from ANN, are compared with experimental data and the results obtained, conclude that neural network model is reliable and accurate for solving the cutting parameter optimization.