| 基于概率神经网络的滚动轴承故障诊断 |
| |
| 引用本文： | 王敬涛,邓东花.基于概率神经网络的滚动轴承故障诊断[J].现代电子技术,2010,33(20):147-149. |
| |
| 作者姓名： | 王敬涛 邓东花 |
| |
| 作者单位： | [1]广西石化公司机电仪中心,广西钦州535008 [2]中国石油天然气管道工程有限公司仪表自动化室,河北廊坊065000 |
| |
| 摘 要： | 针对滚动轴承故障征兆与故障模式映射的复杂性，以及BP网络容易陷入局部极小、收敛速度慢等缺点，提出了基于概率神经网络（PNN）的滚动轴承故障诊断方法。采用11个时域统计特征作为样本特征，利用PNN实现样本分类，并与反向传播（BP）网络进行滚动轴承故障诊断的方法进行了对比。结果表明，PNN网络可以实现滚动轴承不同类型的故障识别，其分类结果比BP网络具有更高的准确性，并在避免局部极小和节约训练时间方面有较好的实用性。
|
| 关 键 词： | PNN网络 BP神经网络 故障诊断 滚动轴承 |
Fault Diagnosis of Rolling Bearing Based on PNN |
| |
| WANG Jing-tao,DENG Dong-hua.Fault Diagnosis of Rolling Bearing Based on PNN[J].Modern Electronic Technique,2010,33(20):147-149. |
| |
| Authors: | WANG Jing-tao DENG Dong-hua |
| |
| Institution: | 1. Guangxi Branch, China National Petroleum Corporation, Qinzhou 535008, China; 2. China Petroleum Pipeline Engineering Corporation, Langfang 065000, China) |
| |
| Abstract: | Aiming at the mapping complexity between fault symptoms and fault patterns of roiling bearing, and the problems of falling easily into part minimums and low velocity of convergence in BP neural network, PNN is put forward to diagnose rolling hearing. 11 static features of time signals are adopted as the sample symptoms, PNN is trained to diagnose rolling bearings. The results show that PNN can achieve different fault diagnosis of ball hearing in proving accuracy, repressing the network to sink local minimum, and shortening the study time. |
| |
| Keywords: | PNN BP neural network fault diagnosis rolling bearing |
| 本文献已被 维普 万方数据 等数据库收录！ |
