Title: Prediction and comparison of thrust force and torque in drilling of natural fibre hybrid composite using regression and artificial neural network modelling
Authors: A. Athijayamani, U. Natarajan, M. Thiruchitrambalam
Addresses: Department of Mechanical Engineering, A. C. College of Engineering and Technology, Karaikudi-4, Tamilnadu, India. ' Department of Mechanical Engineering, A. C. College of Engineering and Technology, Karaikudi-4, Tamilnadu, India. ' Department of Mechanical Engineering, Dr. Mahalingam College of Engineering and Technology, Pollachi, Tamil Nadu, India
Abstract: In this paper, the prediction and comparison of thrust force and torque in drilling of roselle/sisal hybrid composite material were presented. This new approach for natural fibre hybrid composite materials is based on artificial neural network (ANN) and regression models (RM). The series of drilling experiments using HSS-twist drill bits were conducted on composite specimen using MAXMILL CNC machining centre. Drill tool dynamometer has been used to measure thrust force and torque during the drilling processes. Thrust force and torque were taken as response variables and feed rate, cutting speed and drill diameter were taken as input variables. The response variables were predicted with the help of empirical relation using RM and ANN models. The predicted values of the responses by both ANN and RM were compared with the experimental values and their closeness with the experimental values was determined. The results indicate that the ANN model is more effective than RM model in prediction of thrust force and torque in drilling of natural fibre hybrid composite materials.
Keywords: drilling; natural fibre hybrid composites; composite materials; artificial neural networks; ANNs; thrust force; torque; regression modelling; CNC machining; feed rate; cutting speed; drill diameters.
International Journal of Machining and Machinability of Materials, 2010 Vol.8 No.1/2, pp.131 - 145
Published online: 05 Aug 2010 *Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article