Abstract
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.
Highlights
Published: 7 June 2021Micro Electro Discharge Machining is a non-conventional process able to remove material from the workpiece by means of the thermal energy generated by rapid electric sparks, occurring between electrode and workpiece in a dielectric medium that separates the two elements
All the solutions reported in these works show that, whatever optimization algorithm is applied to the artificial neural network (ANN), it is possible to obtain effective optimization and predictive techniques
The model resulted to be able to reproduce with accuracy the geometry and it resulted to be comparable to the real process in terms of Material Removal Rate (MRR) and machining time (t) [21]
Summary
Micro Electro Discharge Machining (micro-EDM) is a non-conventional process able to remove material from the workpiece by means of the thermal energy generated by rapid electric sparks, occurring between electrode and workpiece in a dielectric medium that separates the two elements. An integrated method using artificial neural network (ANN) and genetic algorithm (GA) was used for analyzing the material removal rate (MRR) and for optimizing the process parameters, showing errors within acceptable limits and determining optimum process parameters for the desired output value through the GA [6]. The artificial neural network (ANN) was used in the development of a predictive model of the material removal rate (MRR) in EDM using an input-output pattern of raw data coming from process experiments for copper-electrode and steel-workpiece [8]. A FEM model, developed by the authors in previous work [21], was considered for simulating the material removal process by means of a damage routine This latter model deletes the mesh elements that reach the melting temperature of the material due to the flow of heat transmitted through continuous electrical discharges. The prediction accuracy of both the forecast methodologies was compared based on main process indicators, such as the Material Removal Rate (MRR), machining time, and dimensional deviation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
