Prediction of Surface Roughness in Longitudinal Turning Process by a Genetic Learning Algorithm

The surface roughness is one of the major parameters for determining the level of machining quality. The cutting parameters and conditions have great importance to achieve the desired values during the turning process. In the present work, a new approach was considered for modelling the effect of various turning process parameters and conditions on surface roughness. The experimental studies about the surface roughness after the turning process documented in the literature were collected and compiled into a model based on a genetic learning algorithm. As input parameters for modeling the work piece alloy type, tool type, tool tip radius, tool coating type, cooling conditions, cutting speed, feed rate, and cut depth were used in the study and were comprehensivly compiled.