The encoding of thrust force signals of microdrilling operations with wavelet transformations and the classification of the estimated coefficients with Adaptive Resonance Theory ART2-type neural networks are proposed for detection of severe tool damage just before complete tip breakage occurs. More than 90% accuracy was observed in the sixty-one cases studied. The proposed combination was found to be a powerful signal classification tool because of its fast algorithms, self-learning capability, and extremely high computational speed on the parallel processing hardware.
