您目前所在的位置:首页 - 期刊简介 - 详细页面

铁道科学与工程学报

JOURNAL OF RAILWAY SCIENCE AND ENGINEERING

第9卷    第6期    总第50期    2012年12月

[PDF全文下载]    [Flash在线阅读]

    

文章编号:1672-7029(2012) 06-0107-06
基于D-S 证据理论信息融合的轨道电路故障诊断方法研究
李娜1,董海鹰1,2

(1.兰州交通大学自动化与电气工程学院,甘肃兰州730070;
2.兰州交通大学光电技术与智能控制教育部重点实验室,甘肃兰州730070
)

摘 要: 在闭塞区间主流设备越来越多的采用ZPW-2000A 型无绝缘轨道电路的背景下,针对单一故障诊断方法的诊断精度偏低问题,提出基于信息融合的故障诊断模型和故障诊断方法。该方法分别用BP 神经网络和模糊综合评判对轨道电路进行故障诊断,然后将这2 种方法的诊断结果作为D-S 证据理论的证据体,利用神经网络输出和模糊综合评判输出来构造D-S 证据理论中的概率分配,最后利用D-S 证据理论将BP 神经网络和模糊综合评判对轨道电路的故障诊断结果在决策级进行融合,诊断轨道电路是否有故障并判断故障的模式。仿真结果表明:该诊断方法具有较高的故障诊断精度,诊断结论的可信度有明显提高。

 

关键字: 故障诊断;信息融合; D-S 证据理论;神经网络;模糊综合评判

Research on track circuit fault diagnosis method based on D-S evidence theory information fusion
LI Na1,DONG Hai-ying1,2

1.School of Automation & Electrical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China;
2.Key Laboratory of Opto -Electronic Technology and Intelligent Control of Ministry of Education,Lanzhou Jiaotong University,Lanzhou 730070,China

Abstract:Based on the fact that there are more and more mainstream equipment using ZPW-2000A track circuit,and the single fault diagnosis method shows low precision,the fault diagnosis method based on the module of information fusion was proposed.This method works as follows: Firstly,the fault is diagnosed by using the BP neural network and fuzzy comprehensive evaluation,then the diagnostic results of these two methods are seen as the evidence body in D-S evidence theory,and the probability assignment of D-S evidence theory is structured by the output of the neural network and the fuzzy comprehensive evaluation.At last by the D-S evidence theory,the diagnosis result through using BP-neural network and fuzzy comprehensive evaluation is then fused on the decision-level so as to judge whether the track circuit has fault and the type of the fault.The simulation result indicates that this diagnostic method has a high accuracy of fault diagnosis,and the credibility of diagnostic result has been obviously improved.

 

Key words: fault diagnosis; information fusion; D-S evidence theory; neural network; fuzzy comprehensive evaluation

ISSN 1672-7029
CN 43-1423/U

主管:中华人民共和国教育部 主办:中南大学 中国铁道学会 承办:中南大学
湘ICP备09001153号 版权所有:《铁道科学与工程学报》编辑部
------------------------------------------------------------------------------------------
地 址:湖南省长沙市韶山南路22号 邮编:410075
电 话:0731-82655133,82656174   传真:0731-82655133   电子邮箱:jrse@mail.csu.edu.cn