| 基于BP算法的液压泵在线状态监测及故障诊断 |
| |
| 引用本文： | 董选明,裘丽华.基于BP算法的液压泵在线状态监测及故障诊断[J].北京航空航天大学学报,1997,23(3):322-327. |
| |
| 作者姓名： | 董选明 裘丽华 |
| |
| 作者单位： | 北京航空航天大学自动控制系 |
| |
| 摘 要： | 以液压泵振动信号的５个时域信息；峰值，峰峰值，均方根值，方差和波形系数作为最小诊断参数组合，用ＢＰ神经网络进行信息融合，提出一液压泵的神经网络在线状态监测及故障诊断系统。
|
| 关 键 词： | 故障诊断 神经网络 液压泵 状态监测 |
ON LINE CONDITION MONITORING AND FAULT DIAGNOSIS FOR HYDRAULIC PUMP BASED ON BP ALGORITHM |
| |
| Dong Xuanming\ Qiu Lihua\ Wang Zhanlin.ON LINE CONDITION MONITORING AND FAULT DIAGNOSIS FOR HYDRAULIC PUMP BASED ON BP ALGORITHM[J].Journal of Beijing University of Aeronautics and Astronautics,1997,23(3):322-327. |
| |
| Authors: | Dong Xuanming\ Qiu Lihua\ Wang Zhanlin |
| |
| Abstract: | This paper considers five time domain features of pump vibration: P,P p ,R rms ,V var and C crest as minimum combination of diagnosic parameters(MCDP), and uses BP neural networks to fuse and synthesize these features. A on line NN based condition monitoring and fault diagnosic system(NNCMFDS) for hydraulic pump is presented. The paper also discusses two modes of data representations which are single node data mapping(SNDM) and spread encoding(SE).The simulation and bench test results demonstrate that NNCMFDS has a high on line monitoring and fault diagnosic success rate, and NNCMFDS in SE mode has a faster learning rate,more sufficient accuracy and stronger noise reduction capacity than that in SNDM mode. |
| |
| Keywords: | fault diagnosis neural networks feature selection vibration signals information fusion condition monitoring |
| 本文献已被 CNKI 维普 等数据库收录！ |
