[1]姚志宏,戴　琳.基于Kohonen网络对万向接轴裂纹的诊断[J].南京师范大学学报(工程技术版),2004,04(03):073-75.
　YAO Zhihong,DAI Lin.Crack Diagnosis of Universal Coupling Based on Kohonen Network[J].Journal of Nanjing Normal University(Engineering and Technology),2004,04(03):073-75.
点击复制

基于Kohonen网络对万向接轴裂纹的诊断

分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

作者:: 姚志宏¹ ; 戴　琳²; 1. 南京师范大学电气与电子工程学院,江苏南京210042 ;2. 南京师范大学物理科学与技术学院,江苏南京210097

Author(s):: YAO Zhihong ¹; DAI Lin ²; 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

Keywords:: Kohonen network ; crack ; training sample ; clustering center ; degree of relationship ; universal joint axle

摘要:: 利用神经网络中的Kohonen网络聚类的特点 ,把轧钢机万向接轴裂纹故障不同的关联度作为Kohonen网络的训练样本输入到Kohonen网络 ,并由网络进行学习和聚类 .由于裂纹深度不同 ,裂纹故障的关联度不同 ,于是网络便产生不同的聚类中心点 .根据不同的聚类中心 ,可以很明确地诊断万向接轴裂纹的故障程度

Abstract:: 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.

[1 ] 虞和济,陈长征. 基于神经网络的智能诊断[M] . 北京: 冶金工业出版社,2000. 57- 66.
[2 ] 闻新. MATLAB 神经网络应用设计[M] . 北京: 科学出版社,2000. 165 -182.

备注/Memo:: 作者简介: 姚志宏(1946 - ) ,副教授,主要从事电工电子学及人工神经网络的教学与研究. E-mail :yaozhihong4607 @njnu. edu. cn

更新日期/Last Update: 2013-04-29