Development and investigation of the surface roughness prediction model using ANN in terms of Machining Parameters during the turning of AISI 1040 steel.

Abstract

Nowadays, surface finish of machined parts plays an important role in manufacturing industry. Poor surface finish invites organization problem seeking identification of the best process condition for the manufacturing process. Surface roughness is the one of the critical performance parameter that has an appreciable effect on several mechanical properties of machined parts such as fatigue behavior, corrosion resistance, creep life, etc. In this present research, an experimental investigation on surface roughness in turning of AISI 1040 steel with coated carbide inserts was carried out. Prediction model for surface roughness in terms of speed, feed and depth of cut is developed using artificial neural network based on gradient descent back-propagation with adaptive learning rate procedure. The predicted values of surface roughness using proposed ANN model have been found to be in close agreement with the experimental data. The correlation coefficient for the entire data set has been found to be 0.982.