modeling and optimization of the electrical discharge machining process based on a combined artificial neural network and particle swarm optimization algorithm

In this study electrical discharge machining (edm) process, widely used in mold manufacturing, is modeled and optimized using artificial neural network and an optimization heuristic algorithm. material removal rate (mrr), tool wear rate (twr), and surface roughness (sr) are considered as performance characteristics of the edm process. optimization of process parameters in order to find a combination of process parameters to simultaneously minimize twr and sr and maximize mrr is the objective of this study. in order to establish the relations between the input and the output process parameters, back propagation neural network (bpnn) used. in the last section of this research, particle swarm optimization (pso) algorithm has been employed for optimization of the multiple response characteristics. a set of verification tests is also performed to verify the accuracy of optimization procedure in determination of the optimal levels of process parameters. results demonstrate that propose modeling technique (bpnn) can precisely simulate actual edm process with less than 1% error. furthermore less than 4% error for pso algorithm results is quite efficient in optimization procedure.