Home > Published Issues > 2018 > Volume 7, No. 1, January 2018 >

Experimental Investigation of Machine Tool Condition during Machining of Ferrous Components

Lokesha, P. B.Nagaraj, and P. Dinesh
Department of Mechanical Engineering,M. S. Ramaiah Institute of Technology,Bangalore, India

Abstract—In an engineering manufacturing industry, the machine tool and its productivity is always considered as one of the main resources for manufacturing process to satisfy and meet the required demand on time. Keeping this as main focus of manufacturing system, it is desirable to operate the machine tool with an optimum combination of process parameters such as cutting speed, depth of cut, feed rate to maintain good operating condition and thereby enhancing its productivity. In the present study, an effort has been made to analyze the turning process with different combinations of process parameters and their influence on machine tool condition in terms of quality of surface finish and vibrations induced in the machine tool. Surface roughness of turned part and machine tool vibrations at a predetermined location were measured using Mitutoyo SJ-201 Talysurf and tri-axial accelerometers. After acquiring the experimental data, the analysis of variance was carried out to find the effect of process parameters on surface roughness and machine tool vibration. A multiple regression prediction model was built and predicted values of surface roughness and vibrations were compared with the experimental values, which were found to be in good agreement. Further, an artificial neural network (ANN) prediction model was developed to predict the surface roughness and machine tool vibration for given process parameters which predicted with good accuracy.

Index Terms—productivity, vibration, analysis of variance, multiple regression, artificial neural network

Cite: Lokesha, P. B. Nagaraj, and P. Dinesh, "Experimental Investigation of Machine Tool Condition during Machining of Ferrous Components," International Journal of Mechanical Engineering and Robotics Research, Vol. 7, No. 1, pp. 72-77, January 2018. DOI: 10.18178/ijmerr.7.1.72-77