考虑父节点的贝叶斯网络故障路径追溯算法

被引:9
作者
王林 [1 ,2 ]
宋蓓 [2 ]
张友卫 [1 ,2 ]
綦小龙 [2 ,3 ]
王皓 [2 ]
机构
[1] 江苏方天电力技术有限公司
[2] 南京大学计算机软件新技术国家重点实验室
[3] 伊犁师范学院电子与信息工程学院
关键词
贝叶斯网络; 故障路径追溯; 概率推理; 最大条件概率;
D O I
暂无
中图分类号
TP301.6 [算法理论];
学科分类号
081202 ;
摘要
基于概率图模型的故障诊断技术常被用于不确定信息的推理。其中贝叶斯网络作为一类具有强大实用性及适用性的概率图模型,得到了广泛应用。为有效识别大数据量工业系统中的故障传播路径,提出了一种考虑父节点影响的贝叶斯网络故障路径追溯算法。在建立贝叶斯网络后,给定父节点所有潜在取值组合,算法利用条件概率分解及二分法估计特定故障子节点的最大条件分布值,然后与真实观测值比较,得到导致此故障发生的最大可能原因。通过逐层推断,最终能够实现对网络中故障传播路径的有效追溯。实验结果表明,该算法具有准确追踪故障路径的能力,同时显示出较高的可用性及较快的追踪速度。
引用
收藏
页码:1796 / 1805
页数:10
相关论文
共 14 条
[1]   一种基于贝叶斯后验的异常值在线检测及置信度评估算法 [J].
孙栓柱 ;
宋蓓 ;
李春岩 ;
王皓 .
中国科学技术大学学报, 2017, 47 (08) :644-652
[2]   Bayesian Networks in Fault Diagnosis [J].
Cai, Baoping ;
Huang, Lei ;
Xie, Min .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2017, 13 (05) :2227-2240
[3]   A Data-Driven Fault Diagnosis Methodology in Three-Phase Inverters for PMSM Drive Systems [J].
Cai, Baoping ;
Zhao, Yubin ;
Liu, Hanlin ;
Xie, Min .
IEEE TRANSACTIONS ON POWER ELECTRONICS, 2017, 32 (07) :5590-5600
[4]  
A real-time fault diagnosis methodology of complex systems using object-oriented Bayesian networks[J] . Baoping Cai,Hanlin Liu,Min Xie.Mechanical Systems and Signal Processing . 2016
[5]   Towards a Fuzzy Bayesian Network Based Approach for Safety Risk Analysis of Tunnel-Induced Pipeline Damage [J].
Zhang, Limao ;
Wu, Xianguo ;
Qin, Yawei ;
Skibniewski, Miroslaw J. ;
Liu, Wenli .
RISK ANALYSIS, 2016, 36 (02) :278-301
[6]  
A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks[J] . W. Chine,A. Mellit,V. Lughi,A. Malek,G. Sulligoi,A. Massi Pavan.Renewable Energy . 2016
[7]   Robust Model-Based Fault Diagnosis for PEM Fuel Cell Air-Feed System [J].
Liu, Jianxing ;
Luo, Wensheng ;
Yang, Xiaozhan ;
Wu, Ligang .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2016, 63 (05) :3261-3270
[8]  
Fault propagation behavior study and root cause reasoning with dynamic Bayesian network based framework[J] . Jinqiu Hu,Laibin Zhang,Zhansheng Cai,Yu Wang,Anqi Wang.Process Safety and Environmental Protection . 2015
[9]  
Fault diagnosis of automobile hydraulic brake system using statistical features and support vector machines[J] . R. Jegadeeshwaran,V. Sugumaran.Mechanical Systems and Signal Processing . 2015
[10]  
A Survey of Fault Diagnosis and Fault-Tolerant Techniques - Part I: Fault Diagnosis With Model-Based and Signal-Based Approaches[J] . Zhiwei Gao,Carlo Cecati,Steven X. Ding.IEEE Trans. Industrial Electronics . 2015 (6)