基于Kohonen网络对小型轧机万向接轴裂纹的诊断

利用神经网络中Kohonen网络聚类的特点，把小型轧机万向接轴裂纹故障的不同关联度，作为Kohonen网络的训练样本输入到Kohonen网络中去，并由Kohonen网络学习和聚类产生不同的聚类中心点。由于裂纹深度不同，裂纹故障关联度不同，网络产生的聚类中心点不同。因此可根据不同的聚类中心点准确地诊断万向接轴的裂纹深度。

Prognosis of Crackle on Universal Coupling Based on Kohonen Network

With the characteristics of the Koho nen network clustering in neural network, the degree of relationship of universal joint axis of rolling mill is input to Kohonen network as training sample,and is studied and clustered by the network to generate different clustering centers owing to the different depth and different degree of relationship among severity of crack. Based on the clustering centers and simulating, the degree of severity of crack on universal joint axis can be confirmed and diagnosed.