A hybrid process model for EDM based on finite-element method and Gaussian process regression

Abstract

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

Review of research work in die sinking EDM for machining curved hole

“…As it contributes to improve the process parameters and efficiency of the machine, ultrasonic machining and electrical discharge machining are combined together [17]. The use of hybrid intelligent process model based on finite element modeling and Gaussian process regression has been carried out on EDM [18]. New application areas involve electrical discharge texturing used for texturing of aluminum sheet [19].…”

A Review on Modelling Techniques of Electrical Discharge Machining Process

“…Similarly, the surface convection affects the faster decrease in temperature at spark off time. Ming et al [2] developed a hybrid intelligent model for latent heat, heat distribution coefficient of cathode, Plasma Flushing efficiency (PFE) to calculate the MRR and surface roughness using FEM and the relationship between the input parameters and the output performance have been established using GPR model. Sanchez et al [11] constructed an inversion model based on least squares theory to estimate the values of EDM input parameters to fulfill the MRR, SR, EWR.…”

Effect of Discharge Location on Temperature Distribution during Electrical Discharge Machining

“…Energy distribution factor  is another important factor in the model, governing the percentage of the total heat input from the plasma discharge channel. The different values of energy distribution factor were proposed by many researchers [2,5,7,11], ranging from 0.18-0.45. Comparing the experimental and analytical results, the constant value of  (0.3) has been adopted to estimate the temperature distribution in the model.…”

“…Shabgard [4] simulated the temperature distribution on the surface of workpiece during a single discharge and assessed the effects of discharge parameters on machining efficiency and the recast layer thickness. Ming [5] proposed a hybrid intelligent process model based on finite-element method and Gaussian process regression to predict material removal rate and surface roughness. Weingartner [6] evaluated that the influence of high-speed rotating workpieces on tool wear in WEDM.…”