A Multivariate Model of Orthogonal Turning Operation on Cutting Tool Dynamics Modeled by Optimum Cutting Parameters using Genetic Algorithm
B. Tulasiramarao1, P. Ramreddy2, K. Srinivas3, A. Raveendra4

1B. Tulasiramarao, Research Scholar JNTU, Hyderabad (Telangana), India.
2Dr. P. Ramreddy, Professor, Deportment of Mechanical Engineering, Former Registar, JNTU, Hyderabad (Telangana), India.
3Dr. K. Srinivas, Professor, Deportment of Mechanical Engineering, RVR & JC College of Engineering, Guntur (A.P), India.
4A. Raveendra, Associate Professor, Department of Mechanical Engineering, Malla Reddy Engineering College (A), Secunderabad (Telangana), India.
Manuscript received on 10 February 2019 | Revised Manuscript received on 23 February 2019 | Manuscript Published on 04 March 2019 | PP: 530-535 | Volume-7 Issue-5S2 January 2019 | Retrieval Number: ES209501751919/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Turning accuracy and high productivity rates have become the key determinants and both accuracy and surface quality plays vital role. In this publication a diversified multivariate model of an orthogonal turning operation has been formulated considering a series of turning experiments. Using the obtained experimental data, the cutting dynamics has been modeled with radial basis function neural network for different work piece materials. In par with basic cutting parameters, tool overhang and tool wear were selected as inputs and static cutting edge forces, average roughness values and critical chatter length on work piece were presented as outputs. For four work materials considered in experiments, four neural networks were trained. Using these neural network models, optimum cutting parameters such as speed, depth of cut, feed and tool-overhang lengths are projected by minimizing total cutting edge force with the help of genetic algorithms.
Keywords: Cutting Parameters, Design Parameters, Neural Network and Genetic Algorithm.
Scope of the Article: Algorithm Engineering