Prediction of surface roughness in ultraprecision turning using fuzzy logic

Ultraprecision turning is a manufacturing process used to generate a high surface roughness in precision components, and its input-output relationships are highly nonlinear. Surface roughness of a turned surface depends on the selection of cutting variables, such as cutting speed, feed and depth of cut. Realizing the fact that fuzzy logic controller (FLC) is a powerful tool for dealing with impression and uncertainty, in this paper two approaches are developed to model the Ultraprecision turning operation using fuzzy logic. In the first approach a combined Genetic-fuzzy (GA-Fuzzy) system is used, where as a Genetic-fuzzy basis function network (GA-FBFN) is utilized in the second approach. The results of these two approaches are compared with those of the empirical expression for making prediction of surface roughness in Ultraprecision turning. It has been found that the performance of the second approach is much better than the previous one. It may happen because, in the GAFuzzy system, the main draw back lies in the fact that it does not keep track on the number of times a particular rule is getting fired during training.