Accomplishment of high machining rates along with good surface quality is a major concern in electric discharge machining process. Powder-mixed electric discharge machining in which suitable powder particles are impregnated in dielectric has gone forth as a potential solution to this problem. Nevertheless, challenges such as dielectric circulation, homogeneous blending of the powder particles in the dielectric, debris removal and quantity of the powder material required have to be addressed carefully before implementing this process on a large scale in the manufacturing industry. Extensive research in the field of electric discharge machining using powder-suspended dielectrics has started only in the recent years. In this article, a comprehensive review of the research going on in the field of powder-mixed electric discharge machining is presented. The emphasis is given on powder-mixed electric discharge machining mechanism, influence of powder characteristics and machining parameters on various responses. Some of the major application areas, variants of the basic powder-mixed electric discharge machining process and possibilities of further improvement are also discussed.
Keywords:AISI P20 tool steel Grey-fuzzy logic Multi-response optimization Surface integrity Electric discharge machining a b s t r a c t Surface integrity remains one of the major areas of concern in electric discharge machining (EDM). During the current study, grey-fuzzy logic-based hybrid optimization technique is utilized to determine the optimal settings of EDM process parameters with an aim to improve surface integrity aspects after EDM of AISI P20 tool steel. The experiment is designed using response surface methodology (RSM) considering discharge current (Ip), pulse-on time (T on ), tool-work time (T w ) and tool-lift time (T up ) as process parameters. Various surface integrity characteristics such as white layer thickness (WLT), surface crack density (SCD) and surface roughness (SR) are considered during the current research work. Grey relational analysis (GRA) combined with fuzzy-logic is used to determine grey fuzzy reasoning grade (GFRG). The optimal solution based on this analysis is found to be Ip ¼ 1 A, T on ¼ 10 ms, T w ¼ 0.2 s, and T up ¼ 0.0 s. Analysis of variance (ANOVA) results clearly indicate that T on is the most contributing parameter followed by Ip, for multiple performance characteristics of surface integrity.
In this work, two different artificial neural network (ANN) models -back-propagation neural network (BPN) and radial basis function neural network (RBFN) -are presented for the prediction of surface roughness in die sinking electrical discharge machining (EDM). The pulse current (Ip), the pulse duration (Ton), and duty cycle (t) are chosen as input variables with a constant voltage of 50 volt, and surface roughness is the output parameters of the model. A widespread series of EDM experiments was conducted on AISI D2 steel to acquire the data for training and testing and it was found that the neural models could predict the process performance with reasonable accuracy, under varying machining conditions. However, RBFN is faster than the BPNs and the BPN is reasonably more accurate. Moreover, they can be considered as valuable tools for EDM, by giving reliable predictions and provide a possible way to avoid timeand money-consuming experiments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.