多特征信息融合的贝叶斯网络故障诊断方法研究

中国机械工程 ›› 2010, Vol. 21 ›› Issue (8): 940-945,967.

多特征信息融合的贝叶斯网络故障诊断方法研究

姜万录;刘思远

燕山大学,秦皇岛,066004

出版日期:2010-04-25 发布日期:2010-05-05
基金资助:
国家自然科学基金资助项目(50775198)；河北省自然科学基金资助项目(E2008000812)
National Natural Science Foundation of China（No. 50775198）;
Hebei Provincial Natural Science Foundation of China（No. E2008000812）

Fault Diagnosis Approach Study of Bayesian Networks Based on Multi-characteristic Information Fusion

Jiang Wanlu;Liu Siyuan

Yanshan University,Qinhuangdao,Hebei,066004

Online:2010-04-25 Published:2010-05-05
Supported by:

National Natural Science Foundation of China（No. 50775198）;
Hebei Provincial Natural Science Foundation of China（No. E2008000812）

摘要/Abstract

摘要：

针对轴向柱塞泵故障特征的模糊性和不完备性特点,提出一种多特征信息融合与贝叶斯网络相结合的故障诊断方法。该方法从柱塞泵采集的振动信号中提取出频域和幅域的多个故障特征,并将这些特征当作来自多个不同传感器的多源信息。利用贝叶斯参数估计算法进行多特征信息融合。通过构造贝叶斯网络并建立贝叶斯分类器来简化融合后的结果,通过最大后验概率估计值的计算进行故障识别。经过轴向柱塞泵多故障模式的诊断实验,验证了该方法能够有效地实现柱塞泵柱塞松靴和脱靴故障的诊断。

关键词:

柱塞泵, 故障诊断, 多特征信息融合, 贝叶斯网络



Abstract:

Aiming at the fuzzy and incomplete nature of fault characteristics of axial piston pump,a method of Bayesian networks and multi-characteristic information fusion was proposed.Firstly,multi-fault characteristics in the frequency domain and amplitude domain were extracted from vibration signals and regarded,as multi-source informations coming from different sensors.Then,Bayesian parameter estimation algorithm was applied to fuse multi-characteristic information.Next,the fusion result was simplified by constructing a Bayesian network and establishing Bayesian classifier.Finally,through calculating the maximum posterior probability estimation and the fault patterns were identified.The validity of this method was verified through experiments of multi-fault patterns on an axial piston pump.

Key words:

piston pump, fault diagnosis, multi-characteristic information fusion, Bayesian network

中图分类号:

TP206.3

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): 940-945,967.

JIANG Mo-Lu, LIU Sai-Yuan.

Fault Diagnosis Approach Study of Bayesian Networks Based on Multi-characteristic Information Fusion

[J]. China Mechanical Engineering, 2010, 21(8): 940-945,967.

参考文献

[1]Niu Huifeng,Jiang Wanlu, Liu Siyuan. Research on the Hybrid Fault Diagnosis Approach Based on Artificial Immune Algorithm[C]//Proeeedings of 4th International Conference on Natural Computation (ICNC' 2008). Jinan, 2008 : 667-670.
[2]牛慧峰[1],姜万录[1].免疫支持向量机方法在液压泵故障诊断中的应用[J].中国机械工程,2008,19(14):1736-1739.
[3]刘思远[1],姜万录[1].粗糙集在液压泵故障诊断研究中的应用[J].机床与液压,2008,36(10):196-198.
[4]Nilsson N. Artificial Intelligence, a New Synthesis [M]. San Francisco: Morgan Kaufmann Publishers, 1998.
[5]韩崇昭，朱洪艳，段战胜，等．多元信息融合[M]．北京：清华大学出版社,2006：96—112．
[6]李宏坤 [1],马孝江 [2],王珍 [3].基于多征兆信息融合理论的柴油机故障诊断[J].农业机械学报,2004,35(1):121-124.
[7]王少萍[1],苑中魁[1],杨光琴[1].液压泵信息融合故障诊断[J].中国机械工程,2005,16(4):327-331.
[8]姜万录.基于混沌性质和多分辨分析的故障诊断理论及实验研究 [D].燕山大学,2001:
[9]霍利民 [1],朱永利 [2],贾兰英 [3],苏海锋 [3].基于贝叶斯网络的电网故障诊断方法[J].华北电力大学学报,2004,31(3):30-34.
[10]Su Hong Sheng. Multi--source Fuzzy Information Fusion Method Based on Bayesian Optimal Classifier[J]. Acta Automatica Sinica, 2008,34 (3) : 282-287.
[11]王玉珍[1].基于贝叶斯理论的分类模式挖掘方法研究[J].微计算机应用,2007,28(6):664-668.
[12]朱永利[1],吴立增[1],李雪玉[1].贝叶斯分类器与粗糙集相结合的变压器综合故障诊断[J].中国电机工程学报,2005,25(10):159-165.
[13]Liu Siyuan,Jiang Wanlu, Niu Huifeng. Fault Diagnosis of Hydraulic Pump Based on Rough Set and PCA Algorithm[C]//Proceedings of 5th International Conference on Fuzzy Systems and Knowledge Discovery. Jinan, 2008 : 256-260.
[14]Bezdek J C. Pattern Recognition with Fuzzy Objective Function Algorithms[M]. New York: Plenum Press, 1981.
[15]韩捷等编著.旋转机械故障机理及诊断技术[M],1997:241.