Fuzzy Surface Roughness Modeling of Ultra-Precision Diamond Turning of an Al 6061/ SiCp Metal Matrix Composite

Ultra-precision diamond turning is widely used in the manufacturing of high precision components with a surface roughness of a few nanometers and with a tolerance which is in submicrometer range. Conventionally, the setup parameters for the diamond turning process are usually selected with the aid of trial cutting experiments, which are both time consuming and costly. Moreover, the surface roughness of the product depends on the experience of an operator and the machining environment. There is a need for the development of a simulation system which is capable of predicting the surface roughness of a workpiece and optimizing cutting conditions. In the present work, an attempt has been made to design an optimized fuzzy inference system using genetic aigorithm, so that the surface roughness in ultra-precision diamond turning of metal matrix composite can be modeled for set of input parameters, namely spindle speed, feed rate and depth of cut. As Genetic Algorithm (GA) is computationally expensive, the GA based training is done off-line. Once trained, the GA-tuned Fuzzy Inference System (GAFIS) will be able to predict surface roughness in ultra-precision diamond turning of AI6061/ SiCp Metal Matrix Composite before conducting actual experiment. The surface roughness obtained using proposed GAFIS is compared with the experimental results.