Comparison of ANN and RSM modeling approaches for WEDM process optimization

In this paper, an effective process optimization approach based on artificial neural networks with a back propagation algorithm and response surface methodology including central composite design is presented for the modeling and prediction of surface roughness in the wire electrical discharge machining process. In the development of predictive models, cutting parameters of pulse duration, open circuit voltage, wire speed and dielectric flushing are considered as model variables. After experiments are carried out, the analysis of variance is implemented to identify the contribution of uncontrollable process parameters effecting surface roughness. Then, a comparative analysis of the proposed approaches is carried out to determine the most efficient one. The performance of the developed artificial neural networks and response surface methodology predictive models is tested for prediction accuracy in terms of the coefficient of determination and root mean square error metrics. The results indicate that an artificial neural networks model provides more accurate prediction than the response surface methodology model.

Surface Quality and Contamination on Si Wafer Surfaces Sliced Using Wire-Electrical Discharge Machining

In the past, studies on wire-electrical discharge machining (EDM) of Si wafers have often focused on the effect of energy-related parameters on various wafer characteristics. However, comprehensive treatment on analyzing the effect of non-energy parameters of the Si wafer slicing process is not available thus far. This work, therefore, presents an extensive experimental work considering the parameters like wire tension (WT), wire feed rate (WF), and dielectric flushing pressure (WaP) on crucial wafer characteristics such as wafer-thickness and its uniformity, thermal damage, wire material contamination on wafer surfaces, and surface quality. A total of 72 experiments were performed at low and high servo voltage (SV) conditions. The sliced wafers were characterized by SEM, EDAX, and ICP-AES techniques. Ultrathin wafers with a uniform thickness of ∼107 µm were sliced at high SV conditions, while a lower thermal damage (∼10 µm) with low wire contamination was observed during low SV conditions. The percentage of contamination was further found to decrease with an increase in WT, WF, and WaP during low SV conditions. The wafer surface etching showed the diffusion of contaminates like Cu/Zn up to a depth of 25–30 µm. The wafer surface roughness in the middle section has always been observed to be poor due to short-circuiting and arcing within that zone.

Optimization of EDM Hole Drilling Parameters in Machining of MoSi2-SiC Intermetallic/Composites for Improving Geometrical Tolerances

Intermetallic/ceramic composites with multiple responses are based on L18 orthogonal array with gray relational analysis (GRA). This paper presents a new approach for the optimization of drilling parameters on drilling MoSi 2– SiC composites. Optimal machining parameters can then be determined by the gray relational grade as the performance index. In this study, the sparking parameters namely current (I), pulse on time (t on ), pulse off time (t off ), spark gap and dielectric flushing pressure (P) are optimized with considerations of multiple performance characteristics including multi responses such as material removal rate (MRR), electrode wear rate (EWR), circularity (CIR), cylindricity (CYL), perpendicularity (PER). A gray relational grade obtained from the GRA is used to solve the electrical discharge machining (EDM) process with the multiple performance characteristics. Based on the gray relational grade, optimum levels of parameters have been identified and significant contribution of parameters is determined by ANOVA. Confirmation test is conducted to validate the test result. Experimental results have shown that the responses in EDM drilling process can be improved effectively through the new approach.

Optimization of Machining Characteristics in EDM of Si3N4-TiN Composites by Taguchi Grey Relational Analysis

In this study, Sparking parameters specifically Current (I), pulse on time (ton), pulse off time (toff), spark gap and dielectric flushing pressure (P) are optimized with the consideration of multi responses such as Material Removal Rate (MRR) and Electrode wear Rate (EWR). The characteristic features of the Spark EDM process are explored through Taguchi L18 orthogonal array design of experimental studies with various process parametric combinations. To optimize the above machining parameter, grey relation techniques are used. Based on the grey relation grade, optimum levels of parameters have been identified and major contribution of parameters is determined by ANOVA. Verification test is conducted to validate the test result.

Multi-Objective Optimization on Electric Discharge Machining Using by Grey Relational Analysis

The present study ,Sparking parameters namely current (I), pulse on time (ton), pulse off time (toff), spark gap and dielectric flushing pressure (P) are optimized with the considerations of multi responses such as Material Removal Rate (MRR), Electrode wear Rate (EWR), of the MoSi2-SiC intermetallic/ceramic composite are investigated by use of the Taguchi L18 orthogonal array (OA) with grey relational grade analysis was reported.

Influence of Workpiece Shape on MRR and EWR in EDM of Steel

Shape of workpiece, electrode orientation and flushing system play important role in electrical discharge machining (EDM) process. Low material removal rate and relatively high electrode wear ratio are some of the disadvantages of EDM process. This can be due to the flushing modes. Workpiece shape has a significant effect in effectiveness of dielectric flushing flow and orientation during EDM process. This research work is conducted to analyze the influence of various workpiece shapes. Square cavity, L shape, flat shape and U shape were machined with same cross-section electrode material. Test parameters are material removal rate (MRR) and electrode wear ratio (EWR). Experiment results show slight difference in MRR and EWR values for different shapes. U shape presents the highest MRR and the lowest EWR occurs in flat shape compared to cavity and L shapes. It can be concluded that flat and U shapes result in good EDM machining quality due to good dielectric flow and flushing conditions in the area of EDM machining.

Study on Single-Pulse Discharges under Special Flushing Conditions

Investigations on the special flushing conditions with an electrical discharge drilling machine were done to analyze single discharges. While flushing speeds in electrical discharge drilling are quiet higher as in electrical discharge sinking, the craters are influenced by the strong flushing. The topography of the craters in terms of depth, length and volume were analyzed. Crater depth and crater length are increasing with higher flushing speeds. Under a dielectric flushing the removed material on the tool electrode is less than on the workpiece. If the volume flow is high enough, the whole plasma channel is pushed in the direction of the flow. A computational fluid dynamics analysis was done to simulate the flow speeds in the narrow gap. Flow speeds above 500 m/s were simulated in the gap.