Fault Diagnosis Approach of Bayesian Networks Based on Multi-sensor Information Fusion and Application
-
摘要: 针对齿轮泵信号具有复杂性和模糊性的特点,提出了一种基于多传感器信息融合的贝叶斯网络故障诊断方法。分析了齿轮泵振动和压力信号特点,以此为基础提取了振动信号的能量特征、分形特征和压力信号的高频压力脉动3种特征属性,构建了多故障贝叶斯网络对特征进行融合,设计了贝叶斯分类器,通过最大后验概率准则识别故障类型。两次融合结果表明:多传感器信息完备了特征空间,提高了诊断正确率,能够有效实现齿轮泵多种故障的诊断,具有较好的应用价值。Abstract: Aiming to the complex and fuzz nature of gear pump signal,a fault diagnosis approach of Bayesian net-works was presented based on multi-sensor information fusion. Firstly,this study analyzed the signal characteristicof vibration and pressure, and extracted energy and fractal characteristis of vibration signal and high frequency pres-sure pulse of pressure signal. Then the multi-fault Bayesian network was built to fuse these characteristics. Finally,Bayesian classifier was designed to identify the fault pattern through the maximum posterior estimation. Twice fusionresults show that multi-sensor information completes the characteristic space,raises the diagnosis exactitude rate.This approach can effectively carry out the gear pump multi-fault diagnosis and have better application value.
-
Key words:
- multi-sensor information fusion /
- bayesian network /
- gear pump /
- fault diagnosis
-
[1] 李弼程,黄洁,高世海等. 信息融合技术及其应用[M]. 北京:国防工业出版社,2010 [2] 李俭川,胡茑庆,秦国军等. 贝叶斯网络理论及其在设备故障诊断中的应用[J]. 中国机械工程,2003,14(10):896～900 [3] 朱伟明. 基于贝叶斯融合的柴油机性能状态评估方法研究[J].内燃机,2010,(2):18～19 [4] 姜万录,刘思远. 多特征信息融合的贝叶斯网络故障诊断方法研究[J]. 中国机械工程,2010,21(8):940～945 [5] 潘伟. 工程机械液压系统状态监测与故障诊断研究[D]. 西安:第二炮兵工程学院,2005 [6] Su H S. Multi-source fuzzy information fusion method based onbayesian optimal classifier[J]. Acta Automatica Sinica,2008,34(3):282～287 [7] 王江萍,孙文莉. 基于小波包能量谱齿轮振动信号的分析与故障诊断[J]. 机械传动,2011,35(1):55～58 [8] 钟明寿,龙源,谢全民等. 基于分形盒维数和多重分形的爆破地震波信号分析[J]. 振动与冲击,2010,29(1):7～11 [9] Bezdek J C. Pattern Recognition with Fuzzy Objective Func-tion Algorithms[M]. New York: Plenum Press,1981 -
点击查看大图
计量
- 文章访问数: 210
- HTML全文浏览量: 40
- PDF下载量: 7
- 被引次数: 0
下载:
