Paper Title
Optimization and Predictive Modelling on Surface Roughness of Duplex Stainless Steel using Artificial Neural Network
Abstract
In this study, a prediction model was developed for surface roughness of Duplex Stainless Steel (1.4462) by
using Artificial Neural Network (ANN). Machinability tests were carried out under dry conditions at the CNC lathe with the
cutting parameters selected in accordance with ISO 3685. In the experiment, surface roughness depending on cutting
parameters (cutting speed, chip angle and feed rate) were measured. These parameters were used for ANN as input
parameters (training and testing). Output parameters of ANN were surface roughness and temperature values. The accuracy
of ANN performance evaluated by regression analysis with comparing experimental and predicted. ANN model provided
highly accurate and consistent prediction for all output parameters.
Keywords - Duplex Stainless Steel, Neural Network, Surface Roughness