Application of ANFIS for modeling and predicting the EDM surface roughness

摘要

Machining quality is very important performance characteristics of electrical discharge machining (EDM). This paper presents the development and application of an adaptive neuro-fuzzy inference system (ANFIS) in the EDM process for prediction of quality parameters. In this ANFIS architecture, discharge current and pulse duration are input variables and output variable is surface roughness. The proposed ANFIS approach in this study provides a more precise selection of the input parameters in electrical discharge machining, which leads to better productivity and product quality.