An analysis to enhance the machining performance of micro-EDM for drilling of blind micro-hole using ANN

Abstract

Abstract The high demand for compact and multitasking devices in the market has been a driving force behind the growing interest in microfabrication techniques. These techniques have wide-ranging applications in many industries, including aerospace, automobile, electronics, and defense. Micro electrical discharge machining (µEDM) techniques have the unique ability to produce highly precise and intricate features on small components, which has further fueled the demand for such products. However, with the increasing demand for micro-featured products, there is a pressing need to enhance the process capability of µEDM process. This work aims to address this need by focusing on enhancing the performance of µEDM by varied process parameters and materials such as copper, brass, and tungsten carbide for the drilling of blind micro holes. Surface roughness (SR) and material removal rate (MRR) are the main performance factors taken into account in this investigation. Notably, the minimum SR was achieved on tungsten carbide, while the maximum MRR was achieved using copper electrodes. For SR and MRR, artificial neural network (ANN) models have been constructed that predict with more than 90% accuracy. These findings have significant implications for the future of microfabrication using µEDM.