Multi-response optimization of EDM drilling parameters of the Nitinol SMA

The demand for Nitinol (SMA) is increasing rapidly for various applications. With the aim of optimum control parameters of EDM, 46 experiments completed on six specimens of 6.156 mm thickness using Sparkonix EDM drill machine. Current (I), voltage (V), charging-time (TON), discharging-time (TOFF), and dielectric pressure (DP) were taken as input control parameters. Single-indexed optimization of material removal rate (MRR), tool-wear rate (TWR), and degree of tapperness (DoT) are evaluated using gray relational grade (GRG). Individual control-parameter contributions are evaluated using Taguchi and ANOVA. The obtained optimal input control parameters were used for the confirmation experiment, and the obtained result gives good agreement to it. V and TON are found as the most significant parameters. Maximum and minimum values of MRR, TWR, and DoT have been recorded as 0.0277 & 0.0074 g/min, 0.0177 & 0.0033 g/min, and 0.032 & 0.01 radians respectively. MRR, TWR, and DoT improved by 49.1, 4.5, and 43.3 %, respectively.

A Comparison between Finite Element Model (FEM) Simulation and an Integrated Artificial Neural Network (ANN)-Particle Swarm Optimization (PSO) Approach to Forecast Performances of Micro Electro Discharge Machining (Micro-EDM) Drilling

Artificial Neural Network (ANN), together with a Particle Swarm Optimization (PSO) and Finite Element Model (FEM), was used to forecast the process performances for the Micro Electrical Discharge Machining (micro-EDM) drilling process. The integrated ANN-PSO methodology has a double direction functionality, responding to different industrial needs. It allows to optimize the process parameters as a function of the required performances and, at the same time, it allows to forecast the process performances fixing the process parameters. The functionality is strictly related to the input and/or output fixed in the model. The FEM model was based on the capacity of modeling the removal process through the mesh element deletion, simulating electrical discharges through a proper heat-flux. This paper compares these prevision models, relating the expected results with the experimental data. In general, the results show that the integrated ANN-PSO methodology is more accurate in the performance previsions. Furthermore, the ANN-PSO model is faster and easier to apply, but it requires a large amount of historical data for the ANN training. On the contrary, the FEM is more complex to set up, since many physical and thermal characteristics of the materials are necessary, and a great deal of time is required for a single simulation.