Engineering and Technology Journal (Dec 2023)
Integrating Grey Relation Analysis and Artificial Neural Networks for Optimal Machining of Tungsten Carbide Composite Using Hybrid Electrochemical Discharge
Abstract
Hybrid Electrochemical Discharge Machining (ECDM) streamlines the manufacturing process for challenging materials. Tungsten carbide (WC) is widely recognized as a formidable material due to its exceptional hardness and its ability to maintain hardness even at elevated temperatures. This study has conducted a comprehensive investigation of the multi-response optimization of ECDM process parameters to enhance the machining of tungsten carbides, utilizing Grey Relation Analysis (GRA) and Artificial Neural Network (ANN) methods. This optimization's primary objective is to achieve the maximum Material Removal Rate (MRR) and machining depth. The study involved a systematically designed experiment based on the Taguchi design method. Scanning Electron Microscopy (SEM) analysis reveals shallow craters, minimal microcracks, and small melt re-deposits on the machined surfaces, elucidating the smooth surface achieved after ECD machining. The average surface roughness achieved in this study, utilizing Electrochemical Discharge Machining (ECDM) for tungsten, measured at 0.9275 µm. Optimal parameters were determined, including a current of 80 A, a stand-off distance of 0.1 mm, a 30 mm gap, and an electrolyte composed of KCl + KOH for machining tungsten carbide. The results of the Analysis of Variance (ANOVA) indicate that electrolyte concentration has the most significant impact on machining depth and material removal rate (50.55%), followed by the current value (31.32%). Additionally, the ANN results aligned closely with those obtained through GRA. Compositional analysis of the surface using Energy-Dispersive X-ray Spectroscopy (EDS) mapping confirms the presence of oxides and carbon on the machined surface.
Keywords
