Title: Prediction and comparison of surface roughness in CNC-turning process by machine vision system using ANN-BP and ANFIS and ANN-DEA models
Authors: U. Natarajan; S. Palani; B. Anandampillai; M. Chellamalai
Addresses: Department of Mechanical Engineering, A.C. College of Engineering and Technology, Karaikkudi-630004, Tamilnadu, India. ' Department of Mechanical Engineering, Mount Zion College of Engineering and Technology, Pudukkottai-622507, Tamilnadu, India. ' Mount Zion College of Engineering and Technology, Pudukkottai-622507, Tamilnadu, India. ' Department of Micro and Precision Machining, Central Manufacturing Technology Institute, Bangalore-560022, India
Abstract: Machine vision methods of roughness measurement are being developed worldwide due to their inherent advantages including non-contact and rapid surface measurement capability. In this work, a back propagation (BP) and a differential evolution algorithm (DEA) based on artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) model have been used for the prediction of surface roughness in turning operations. Cutting speed, feed rate, depth of cut and average grey level of the surface image of work-piece, acquired by computer vision were taken as the input parameters and surface roughness as the output parameter. The results obtained from the ANN-BP, ANFIS and ANN-DEA models were compared with observed values. It is found that the predicted values are in good agreement with the experimental values. It is also found that the error percentage is minimal and it is also observed that the convergence speed for the ANN-DEA model is higher than the ANN-BP and ANFIS.
Keywords: CNC turning; machine vision; ANNs; artificial neural networks; adaptive neuro-fuzzy inference system; ANFIS; differential evolution; surface roughness; non-contact prediction; surface quality; cutting speed; feed rate; depth of cut; average grey level.
International Journal of Machining and Machinability of Materials, 2012 Vol.12 No.1/2, pp.154 - 177
Received: 20 Sep 2011
Accepted: 26 Dec 2011
Published online: 16 Aug 2012 *