Prediction of surface roughness in turning using orthogonal matrix experiment and neural networks

Abstract

A neural network modeling approach is presented for the prediction of surface texture parameters during turning of a copper alloy (GC-CuSnl2). Test specimens in the form of near-to-net-shape bars and a titanium nitride coated cemented carbide (T30) cutting tool were used. The independent variables considered were the cutting speed, feed rate, cutting depth and tool nose radius. The corresponding surface texture parameters that have been studied are the Ra, Rq, and Rt. A feed forward back propagation neural network was developed using experimental data which were conducted on a CNC lathe according to the principles of Taguchi design of experiments method. It was found that NN approach can be applied in an easy way on designed experiments and predictions can be achieved, fast and quite accurate. The developed NN is constrained by the experimental region in which the designed experiment is conducted. Thus, it is very important to select parameters' levels as well as the limits of the experimental region and the structure of the orthogonal experiment. This methodology could be easily applied to different materials and initial conditions for optimization of other manufacturing processes.