Response Surface Methodology and Artificial Neural Network-Based Models for Predicting Performance of Wire Electrical Discharge Machining of Inconel 718 Alloy

Abstract

This paper deals with the development and comparison of prediction models established using response surface methodology (RSM) and artificial neural network (ANN) for a wire electrical discharge machining (WEDM) process. The WEDM experiments were designed using central composite design (CCD) for machining of Inconel 718 superalloy. During experimentation, the pulse-on-time (TON), pulse-off-time (TOFF), servo-voltage (SV), peak current (IP), and wire tension (WT) were chosen as control factors, whereas, the kerf width (Kf), surface roughness (Ra), and materials removal rate (MRR) were selected as performance attributes. The analysis of variance tests was performed to identify the control factors that significantly affect the performance attributes. The double hidden layer ANN model was developed using a back-propagation ANN algorithm, trained by the experimental results. The prediction accuracy of the established ANN model was found to be superior to the RSM model. Finally, the Non-Dominated Sorting Genetic Algorithm-II (NSGA- II) was implemented to determine the optimum WEDM conditions from multiple objectives.

Effect of WEDM Process Parameters on Surface Morphology of Nitinol Shape Memory Alloy

“…Poor chip breaking, tool wear, and burr formation have been observed while machining shape memory alloys using conventional machining techniques Wire electrical discharge machining (WEDM) is a type of nonconventional machining method which is more preferable to overcome these defects [10]. The WEDM process is applicable to all conductive materials regardless of material hardness [11][12][13][14]. The WEDM process creates a series of sparks that helps to remove the material from the work surface.…”

Analysis of the Possibility of Using Wavelet Transform to Assess the Condition of the Surface Layer of Elements with Flat-Top Structures

“…Using this algorithm, a combination of machining parameters is obtained, which ensures maximum material removal speed and minimum surface roughness [20]. Neural networks and genetic algorithms are also used to predict machining effects and optimize the input parameters of the process [21].…”

Modelling and Analysis of the Effect of EDM-Drilling Parameters on the Machining Performance of Inconel 718 Using the RSM and ANNs Methods

“…Currently developed models describing the relationships between the input and resulting factors are also used to optimize the machining process parameters [ 20 , 21 ]. The most commonly used mathematical and statistical techniques include multiple regression and design of experiments (DOE) [ 22 ], the analysis of variance (ANOVA) [ 23 ], the response surface methodology (RSM) [ 24 ], Taguchi method [ 25 ], grey relational analysis (GRA) [ 12 ], artificial neural networks (ANNs) [ 26 , 27 ], neuro-fuzzy approach [ 22 ], and also their combinations [ 28 , 29 ]. For analyzing the effects of electrical discharge machining process parameters on performance factors, as well as developing empirical models, the RSM has been the most widely used technique in recent years [ 30 ].…”

“…This approach is more appropriate due to the many factors affecting the process and still unknown phenomena present in the machining gap area. However, [ 29 ] presents a predictive model for wire electrical discharge machining of the Inconel 718 superalloy with the use of the RSM and ANN techniques. The analysis of the results showed that the model obtained by applying an artificial neural network provided more accurate and reliable predicted values of the analyzed resulting factors, compared to the RSM method.…”