ANFIS-based surface roughness prediction model for EDM of aluminium-based composite material

Abstract

Surface roughness plays a major role in determining how an original component will interact with its environment. For getting a good surface finish, industries spent huge cost for introducing new technologies. The use of advanced engineering ceramics and composites in the aerospace and defence industries is continuous and increases day by day. Prediction of surface roughness plays a vital role in improving the surface finish in the industries. The present work deals with predicting the surface roughness (SR) of aluminium LM25 SiC 10% composite material in electrical discharge machining (EDM) using adaptive neuro-fuzzy inference system (ANFIS). The discharge voltage, discharge current, pulse on time, pulse off time, gap between tool and work piece and oil pressure are taken as the input parameters, whereas surface roughness is the output machining parameter. Design of experiment is based on Response Surface Methodology (RSM). ANFIS model has been constructed using Gaussian membership function (gaussmf) with two membership functions for each input variables and linear membership function for output. This paper uses the hybrid method for membership function parameter training. Based on the conclusion of ANFIS with hybrid method of membership function parameter training, it provides accurate results.