| 基于无监督神经网络的故障模式识别 |
| |
| 引用本文： | 李伟,钟飞,何涛,史铁林. 基于无监督神经网络的故障模式识别[J]. 计算机测量与控制, 2006, 14(6): 742-744,764 |
| |
| 作者姓名： | 李伟 钟飞 何涛 史铁林 |
| |
| 作者单位： | 湖北工业大学,机械学院,湖北,武汉,430068;湖北工业大学,机械学院,湖北,武汉,430068;现代制造质量工程重点实验室,湖北,武汉,430068 |
| |
| 基金项目： | 中国科学院资助项目;湖北省教育厅科研项目;湖北省自然科学基金 |
| |
| 摘 要： | 无监督学习的竞争式神经网络是一种数据聚类方法,能保持输入空间的拓扑关系不变,借助于一维或二维输出平面的一组有序的向量,实现高维数据的聚类和可视化;探讨了一种无监督神经网络--SOFM网络原理、思想和算法步骤,研究了无监督网络在模式识别中的应用,提出了基于SOFM网络的故障模式识别和状态监测方法;通过实例研究了SOFM网络在机械设备故障模式识别和状态监测中的应用.
|
| 关 键 词： | 无监督神经网络 模式识别 故障诊断 |
| 文章编号： | 1671-4598（2006）06-0742-03 |
| 收稿时间： | 2006-03-01 |
| 修稿时间： | 2006-03-012006-04-04 |
Fault Pattern Recognition Based on Unsupervised Neural Network |
| |
| Lei Wei,Zhong Fei,He Tao,Shi Tielin. Fault Pattern Recognition Based on Unsupervised Neural Network[J]. Computer Measurement & Control, 2006, 14(6): 742-744,764 |
| |
| Authors: | Lei Wei Zhong Fei He Tao Shi Tielin |
| |
| Abstract: | The unsupervised learning network is a data cluster method, it can transform an incoming signal pattern of arbitrary dimension into a one-or two-dimensional discrete map, and perform this transformation adaptively in a topologically ordered fashion. The prin- ciple and algorithm of a unsupervised neural network--SOFM is be discussed, the unsupervised network is applied to pattern recognition of the bearing fault, the new pattern recognition technique has been introduced, the high--dimensional input vectors are projected into a two-dimensional space. Numeric experimentation results show reasonable agreements to that the proposed method could recognize the fault pattern clearly and distinctly than common visualization method. |
| |
| Keywords: | unsupervised neural network pattern recognition fault diagnosis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
