Machining Characteristics Estimation in WEDM Process While Machining Titanium Grade-2 Material Using ANN

Wire Electrical Discharge Machining (WEDM) provides an effective solution for machining hard materials with intricate shapes. WEDM is a specialized thermal machining process is capable to accurately machining parts of hard materials with complex shapes. The workpiece and wire are continuously flushed with a dielectric (electrically non-conducting) fluid, usually deionized water, which also acts as a coolant and flushes the debris away. In WEDM, there is no direct contact between workpiece and tool (wire) as in conventional machining process therefore materials of any hardness can be machined and minimum clamping pressure is required to hold the workpiece. Parts having sharp edges that pose difficulties to be machined by the main stream machining processes can be easily machined by WEDM process. However, selection of process parameters for obtaining higher machining efficiency or accuracy in wire EDM is still not fully solved, even with the most up-to-date CNC WED machine. The study presents the machining Titanium grade 2 material using L₁₆ Orthogonal Array (OA). The process parameters considered for the present work are pulse on time, pulse off time, current, bed speed, voltage and flush rate. Among these process parameters voltage and flush rate were kept constant and the other four parameters were varied for the machining of titanium material. Molybdenum wire of 0.18mm is used as the electrode material. Titanium is used in engine applications such as rotors, compressor blades, hydraulic system components and nacelles. Its application can also be found in critical jet engine rotating and airframes components in aircraft industries. Firstly optimization of the process parameters was done to know the effect of most influencing parameters on machining characteristics viz., Surface Roughness (SR) and Electrode Wear (EW). It was found that current and pulse on time was the most effecting parameters for machining characteristics. It was also found that the pulse off time and bedspeed has insignificant effect on the machining characteristics. Then the simpler functional relationship plots were established between the parameters to know the possible information about the SR and EW. This simpler method of analysis does not provide the information on the status of the material and electrode. Hence more sophisticated method of analysis was used viz., Artificial Neural Network (ANN) for the estimation of the experimental values. SR and EW parameters prediction was carried out successfully for 50%, 60% and 70% of the training set for titanium material using ANN. Among the selected percentage data, at 70% training set showed remarkable similarities with the measured value then at 50% and 60%.

Keywords: WEDM, Surface Roughness, Electrode Wear, ANN