| 基于概率神经网络的自适应报警技术研究 |
| |
| 引用本文： | 张遂强,郝伟,李志农. 基于概率神经网络的自适应报警技术研究[J]. 汽轮机技术, 2006, 48(2): 133-135,137 |
| |
| 作者姓名： | 张遂强 郝伟 李志农 |
| |
| 作者单位： | 郑州大学振动工程研究所,郑州,450002;郑州大学振动工程研究所,郑州,450002;郑州大学振动工程研究所,郑州,450002 |
| |
| 基金项目： | 河南省杰出人才创新基金项目(编号:0621000500) |
| |
| 摘 要： | 为了解决目前设备状态报警线设置所存在的缺点,即报警线的设置与设备运行情况变化无关,提出了用概率神经网络构建设备运行状态模型,根据历史数据确定报警值并设置报警线的方法。实验表明,该方法是可行而有效的,用该方法设置的设备状态报警线能够随设备运行而做自适应调整,对指导工业现场的设备监测具有现实意义。
|
| 关 键 词： | 故障诊断 概率神经网络 自适应报警线 状态监测 |
| 文章编号： | 1001-5884（2006）02-0133-03 |
| 收稿时间： | 2005-08-24 |
| 修稿时间： | 2005-08-24 |
Adaptive Alarm Technique Based on Probabilistic Neural Network |
| |
| ZHANG Sui-qiang,HAO Wei,LI Zhi-nong. Adaptive Alarm Technique Based on Probabilistic Neural Network[J]. Turbine Technology, 2006, 48(2): 133-135,137 |
| |
| Authors: | ZHANG Sui-qiang HAO Wei LI Zhi-nong |
| |
| Affiliation: | Research Institute of Vibration Engineering, Zhengzhou University, Zhengzhou 450002, China |
| |
| Abstract: | Based on the deficiency in the setting of the alarm parameters in the machine fault monitoring,i.e.alarm parameters are nearly independent of the various running condition,an method of constructing real running condition based on probabilistic neural network model is proposed.The method is that the alarm line is determined according to history data from the running machine.The experiment results show that this method is feasible and effective.This method can adaptively adjust alarm parameters of the various machine conditions.The proposed method has a practical significance to the instruction for monitoring of machine condition in the industry field. |
| |
| Keywords: | fault diagnosis probabilistic neural network adaptive alarm condition monitoring |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
