Glassy carbon (GC) has superior properties such as high corrosion resistance, heat resistance, and low adhesion to glass materials in a glass molding process (GMP). In addition, the demand for GC molds is increasing in various industries that require high precision of glass parts. However, GC is a difficult-to-machine material with high hardness and brittleness. Electrical discharge machining (EDM) can machine GC regardless of its strength or hardness. In this study, tungsten carbide (WC-Co) electrode was fabricated by wire electrical discharge grinding (WEDG). Characteristics of EDM of micro holes on GC were then analyzed. As capacitance and voltage increased, material removal rate (MRR) increased while machining time tended to decrease. However, at low voltages, short circuit and secondary discharge occurred, which increased the electrode wear rate (EWR). As a result, a D-shaped electrode that could prevent short circuit and debris accumulation was fabricated and a micro hole array was machined.

CNN is one of the deep learning technologies useful for image-based pattern recognition and classification. For machining processes, this technique can be used to predict machining parameters and surface roughness. In electrical discharge machining (EDM), the machined surface is covered with many craters, the shape of which depends on the workpiece material and pulse parameters. In this study, CNN was applied to predict EDM parameters including capacitor, workpiece material, and surface roughness. After machining three metals (brass, stainless steel, and cemented carbide) with different discharge energies, images of machined surfaces were collected using a scanning electron microscope (SEM) and a digital microscope. Surface roughness of each surface was then measured. The CNN model was used to predict machining parameters and surface roughness.