| 基于多元统计的电机故障诊断新方法 |
| |
| 引用本文： | 庄哲民,黎伟权,李芬兰. 基于多元统计的电机故障诊断新方法[J]. 测试技术学报, 2007, 21(2): 112-116 |
| |
| 作者姓名： | 庄哲民 黎伟权 李芬兰 |
| |
| 作者单位： | 汕头大学,电子工程系,广东,汕头,515063;汕头大学,电子工程系,广东,汕头,515063;汕头大学,电子工程系,广东,汕头,515063 |
| |
| 摘 要： | 提出了用多元统计过程控制方法(MSPC)对异步电动机进行故障诊断的新方法.利用多个传感器测量的异步电机多维信号参量,构建电机在正常工作和发生故障时的Q统计和T2统计,以实现电机的状态检测;利用Q统计和T2统计值构建电机的状态特征向量,通过比较度量当前电机的特征向量H与电机发生故障时的特征向量HF的几何距离来实现电机故障的定位与分离.实验证明,该方法可以有效地实现故障的诊断与分离.
|
| 关 键 词： | 多元统计 状态监测 故障定位 模式识别 |
| 文章编号： | 1671-7449（2007）02-0112-05 |
| 收稿时间： | 2006-09-17 |
| 修稿时间： | 2006-09-17 |
A Novel Method for the Fault Diagnosis of Asynchronous Motor Based on Multivariate Statistical Analysis |
| |
| ZHUANG Zhe-min,LI Wei-quan,LI Fen-lan. A Novel Method for the Fault Diagnosis of Asynchronous Motor Based on Multivariate Statistical Analysis[J]. Journal of Test and Measurement Techol, 2007, 21(2): 112-116 |
| |
| Authors: | ZHUANG Zhe-min LI Wei-quan LI Fen-lan |
| |
| Abstract: | A new multivariate statistical process control(MSPC) method is presented for the fault diagnosis of asynchronous machine.The multi-dimensional signals measured by sensors with a machine working under normal condition or fault condition,can be used to build Q statistic and T2 statistic respectively to detect the state of the machine.Meanwhile,the feature vector is constructed by the Q value and the T2 value,the geometrical distance between the normal feature vector H and the feature vector HF when the machine goes wrong is used to realize the fault location.The results show that the method is feasible. |
| |
| Keywords: | multivariate statistics condition detect fault location pattern recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
