1.School of Electrical and Electronic Engineering, Nanjing Normal University, Nanjing 210042, China; 2.School of Physical Science and Technology, Nanjing Normal University, Nanjing 210097, China
With the Kohonen network clustering in neural network employed , the degree of relationship of the universal joint axle of the rolling mill was input to Kohonen network as the training sample , studied and clustered by the network to generate different clustering centers according to the different depth and different degree of relationship among the cracks. Based on the clustering centers and simulating , the cracks in the universal joint axle can be diagnosed.