This paper presents an experimental study on rough cut, trim cut using distilled water as a dielectric fluid and Al & Si metal powders in dielectric fluid for WEDM of Nimonic-90. First, the influence of discharge energy (DE) in rough cut is evaluated for machining rate (MR) and surface roughness (SR) and compared with trim cut without any metal powder additives in dielectric fluid. The effect of Al and Si metal powders (varying concentration of 1g/L, 2g/L and 3g/L) in dielectric fluid is studied separately and comparison is also made for MR, SR, recast layer and micro hardness of machined Nimonic-90. From the results it is observed that using trim cut, a fine and uniform surface texture is obtained irrespective of the high discharge energy of rough cut. Al and Si powders additives show a significant reduction in MR for trim cutting operation whereas a remarkable modification is obtained in surface textures after trim cut using metals powder mixed dielectric. SR improves with a concentration of 1g/L and shows a little increase with high concentration of both metals powder. Using metals powder in dielectric fluid, the recast layer becomes smooth and denser and thus, micro hardness increases.

Suitable selection of various machining parameters for wire electrical discharge machining (WEDM) process heavily relies on the operator’s experience and manufacturer’s technologies because of their numerous and diverse operating ranges. Artificial neural networks have been introduced as an effective tool to predict values of responses and input parameters of different machining processes through forward and reverse modeling approaches respectively. This paper mainly focuses on predicting values of some machining responses, like machining rate, surface roughness, dimensional deviation and wire wear ratio using feed forward back propagation artificial neural network based on six WEDM process parameters, such as pulse on time, pulse off time, peak current, spark gap voltage, wire feed and wire tension. The corresponding reverse model is also developed to recommend the optimal settings of WEDM process parameters for achieving the desired responses according to the requirements of the end users. These modeling approaches are quite efficient to predict the values of machining responses as well as process parameter settings with reduced time and effort which otherwise have to be determined experimentally based on trial and error method. The predicted results are found to be in well congruence with the previously obtained experimental observations.

WEDM has evolved as a well admired technique for machining of difficult to cut materials such as superalloys. WEDM produces intricate shape and profiles of superalloys by thermoelectric erosion process. But as the process is carried out at very high temperature, the formation of heat affected zone, microcracks, recast layer, porosity etc. resulted in decreased surface integrity of machined specimen and becomes a big problem in WEDM. Discharge energy is the most influencing param-eters that affect the surface integrity of WEDmed samples. In this study, Inconel 825, widely used in aerospace industry for making of combustor casing and turbine blades, was machined with WEDM under different discharge energy. The surface topography of the WEDMed specimen was carried cut by using SEM, XRD and EDX techniques. It was observed from the SEM micrograph that the machined surface includes cracks, pockmarks, craters, and pulled out material. The density and sice of craters increase with increase in discharge energy. Surface crack density of 0.0138 μm/μm2 and recast layer thickness of 34.62μm was obtained for the machined sample at high value of discharge energy while at low value surface crack density of 0.0016 μm/μm2 and recast layer thickness of 20.99μm was observed. EDX and XRD analysis of the specimen showed that an ap-preciable amount of elements viz. Fe (Ferrous), Cr (Chromium), Cu (Copper), Ni (Nickel) are mi-grated to the surface of the workpiece at high value of pulse on time.