In this work, the cuttings parameters are varied to analyse the roughness of machined surface statistically during the course of hard turning of AISI 4140 steel when heat treated to 47 HRC. It uses CVD coated Ti(C, N) + Al2O3 carbide as cutting tool. The analysis is done on the basis of Response Surface Methodology (RSM) framed according to the design of experiments. The parameter that has the impact over roughness is measured in terms of analysis of variance. The regression and Artiﬁcial Neural Network (ANN) model to predict roughness in terms of cutting parameters are found out based on experimental data. The optimal cutting conditions to reduce roughness are also found using Response Surface Methodology (RSM). It is found out that feed rate is the most inﬂuencing parameter followed by cutting speed. The ANN model prediction ability is higher when compared to regression model.
Digital Object Identifier (DOI)
Rajeev, D. and Dinakaran, D.
"Statistical Analysis of Surface Roughness in Hard Turning: An Optimization Approach,"
Applied Mathematics & Information Sciences: Vol. 11:
2, Article 27.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol11/iss2/27