Ann Modeling and Investigation on The Surface Roughness and Taper Error While Machining The Inconel 825 Alloy Material Using Wire-Cut Edm Process

Inconel 825 alloy is difficult to machine using conventional processes due to its superior mechanical and thermal properties. Wire Electrical Discharge Machining (WEDM) offers a viable alternative, yet optimizing taper cutting accuracy and surface quality remains underexplored, particularly for complex profiles. This study investigates the effects of pulse-on time, pulse-off time, wire tension, and taper angle on surface roughness (SR) and taper error (TE) during WEDM of Inconel 825 using Central Composite Design (CCD). Response Surface Methodology (RSM) and Artificial Neural Network (ANN) models were developed to predict responses, with ANN demonstrating superior accuracy (R 2 up to 0.9999). ANOVA revealed pulse-on time as the most significant parameter affecting SR, while pulse-off time most influenced TE. Multi-objective optimization using the desirability approach yielded optimal parameters: T on = 0.6 μs, T off = 40 μs, WT = 12 N, TA = 3°, achieving a desirability value of 1.00, with SR = 0.44 μm and TE = 0.07°. SEM analysis confirmed minimal surface defects under optimized conditions. The study provides reliable predictive models and optimal settings for high-precision taper cutting of Inconel 825, bridging a critical research gap in non-traditional machining of high-performance alloys.