Summary

In this paper the fuzzy mathematics was applied to the pattern recognition of the metal cutting states successfully. The methods used are clustering analysis of the fuzzy equivalent matrix and the fuzzy ISODATA (Iteractive Self-Organizing Data). The feature selections in the pattern recognition, viz, filtering of the irrelative and derived features were discussed. Also, the weight for individual feature has been found by the method named as “feature even degree function”, so that it provides a scientific basis for determining weights of features. The selection rule of the initial matrix Ufo for the fuzzy ISODATA method was presented.

Finally the pattern recognition calculations of cutting states were carried out by two methods. Both of them were analyzed and compared in this paper. It has been proved that the accuracy of the results by fuzzy pattern recognition is satisfactory. The method of calculation has been simplified, so that it will be advantageous to the realization of real time recognition and self-adaptive control of the metal cutting states in the future.