The Neural-fuzzy Modeling and Genetic Optimization in WEDM

Considering the needs for getting more precise parameters and at the same time to get faster cutting speed and better surface roughness in Wire Electrical Discharge Machining (WEDM), the authors established a model of WEDM, which has higher forecast precision and generalization ability and could help us in getting better understanding of the basic principles of WEDM. The model combined modeling function of fuzzy inference with the learning ability of artificial neural network; and a set of rules has been generated directly from the experimental data. Integrated with the genetic optimization procedure, the fuzzy inference systems are used to optimize the wire electrical discharge model of WEDM and the optimum results of the model have proved the feasibility and practicability of the system in WEDM.