This paper proposed a hybrid intelligent process model, based on finite-element method (FEM) and Gaussian process regression (GPR), for electrical discharge machining (EDM) process. A model of single-spark EDM process has been constructed based on FEM method, considering the latent heat, variable heat distribution coefficient of cathode (f c ), and plasma flushing efficiency (PFE), to predict material removal rate (MRR) and surface roughness (Ra). This model was validated using reported analytical and experimental results. Then, a GPR model was proposed to establish relationship between input process parameters (pulse current, pulse duration, and discharge voltage) and the process responses (MRR and Ra) for EDM process. The GPR model was trained, tested, and tuned using the
This study mainly investigates the effect and optimization of process parameters on surface integrity including white layer thickness and crack density in wire electrical discharge machining (WEDM) of tungsten tool YG15 which is one of the most important hardened stainless steel alloys used in the mold industries. In this paper, four input process parameters including pulse-on time, pulse current, water pressure, and feed rate were set during WEDM experiment, and three output characteristics including surface roughness (SR), white layer thickness (WLT), and surface crack density (SCD) were taken as the performance criteria of surface integrity. Then an experiment for central composite design (CCD) of processing the tungsten tool YG15 has been conducted according to response surface methodology (RSM). After analyzing the experimental results and optimizing the WEDM process using two different methods namely backpropagation neural network combined with genetic algorithm (BPNN-GA) and Non-dominated Sorting Genetic Algorithm-II (NSGA-II), the optimal solution can be obtained. The analysis results manifest that the pulseon time and pulse current have a significant effect on the SR, WLT, and SCD. Moreover, several confirmation tests were carried out to verify the efficiency of the optimization methods, and then the more appropriate method was demonstrated by the comparison of optimization results. According to analysis and discussion of results, the most suitable process parameter combinations can be obtained to guide the actual machine, which contribute to increase the surface integrity and accuracy of WEDM and simultaneously reduce the ratio of disqualification for industrial application.
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.