ANFIS based model to forecast the Wire-EDM parameters for machining an Ultra High Temperature Ceramic composite

In this work, a ZrB₂ based ceramic composites with 25 wt. % B₄C sintered in spark plasma sintering furnace at 2000°C for 10 min under 50 MPa pressure has been machined with Wire electrical discharge machine (WEDM) and can readily be cut to intricate shapes to meet the requirements of industry. The adaptive neuro fuzzy inference systems (ANFIS) has been used to generate mapping relation between input parameters and output responses. ANFIS is a neuro fuzzy technique where the fusion is made between the neural network and the fuzzy inference system. Also the ANFIS models have been tested by a confirmative test and the results shows minimum root mean square error (RMSE) as 0.0416 for kerf width and 0.9605 for machining speed. This verification indicates that ANFIS modeling can be used to forecast the responses. (paper)