A fuzzy pulse discriminating system for electrical discharge machining

In this paper, the use of fuzzy set theory to construct a new pulse discriminator in electrical discharge machining (EDM) is reported. The classification of various discharge pulses in EDM is based on the features of the measured gap voltage and gap current. To obtain optimal classification performance, a machine learning method based on a simulated annealing algorithm is adopted to automatically synthesize the membership functions of the fuzzy pulse discriminator. Experimental results have shown that EDM discharge pulses can be not only correctly but also quickly classified under varying cutting conditions using this approach.