期刊文献+

神经网络和证据理论融合的管道泄漏诊断方法 被引量:20

A Pipeline Leakage Diagnosis for Fusing Neural Network and Evidence Theory
下载PDF
导出
摘要 针对传统管道泄漏诊断方法存在的准确率不高的问题,结合无线传感器网络与信息融合技术,提出一种神经网络和证据理论有机结合的管道泄漏诊断方法.在普通节点处建立2个子神经网络模型来简化网络结构,分别以负压波和声发射信号中的泄漏特征参数作为输入向量进行初始泄漏诊断;然后将神经网络的识别结果作为证据的基本概率分配,从而实现了赋值的客观化;采用改进的证据组合规则,在普通节点和汇聚节点处进行两级证据合成,充分利用了网络中各种冗余和互补的泄漏信息.实验结果表明,该方法显著提高了管道泄漏诊断的准确率,降低了识别的不确定性. For reasons of low accuracy of traditional leakage, a pipeline leakage diagnosis method based on neural networks and evidence theory is presented by introducing wireless sensor networks and infor- mation fusion theory. Two sub-neural networks are established at normal node to simplify network structure. The leakage characteristic parameters of negative pressure wave and acoustic emission sig- nals are used as input eigenvector respectively for primary diagnosis. Through making preliminary fu- sion results as the basic probability assignment of evidence, the impersonal valuations are realized. Fi- nally, all evidences are aggregated at normal and sink node respectively by using the improved combi- nation rules. The method makes full use of redundant and complementary leakage information. Numerical example shows that the proposed improves the leakage diagnosis accuracy and decreases the recognition uncertainty.
出处 《北京邮电大学学报》 EI CAS CSCD 北大核心 2009年第1期5-9,共5页 Journal of Beijing University of Posts and Telecommunications
基金 国家“863计划”项目(2006AA01Z222) 北京市教育委员会共建项目
关键词 泄漏诊断 神经网络 证据理论 leakage diagnosis neural networks evidence theory
  • 相关文献

参考文献7

  • 1Stoianov I, Nachman L, Madden S, et al. PIPENET. a wireless sensor network for pipeline monitoring [ C ] // 2007 International Symposium on Information Processing in Sensor Networks. Massachusetts. ACM Press, 2007: 264-273.
  • 2Feng D C, Dias P J M. Study on information fusion based on wavelet neural network and evidence theory in fault diagnosis [ C ] //2007 International Conference on Electronic Measurement and Instruments. Xi' an: IEEE Press, 2007: 3522-3526.
  • 3Luis E O, Beatriz M T. A method to estimate emission rates from industrial stacks based on neural networks[J]. Chemosphere, 2004, 57(7): 691-696.
  • 4葛艳,王薇,闫传军,吴鹏,任志考.基于模糊神经网络的CDMA网络故障诊断方法[J].北京邮电大学学报,2007,30(1):123-126. 被引量:3
  • 5Denoeux T, Masson M. EVCLUS: evidential clustering of proximity data[J]. IEEE Systems, Man and Cybernetics B, 2004, 34(1). 95-109.
  • 6Laha A, Pal N R, Das J. Land cover classification using fuzzy rules and aggregation of contextual information through evidence theory[J]. IEEE Transaction on Geoscience and Remote Sensing, 2006, 44(6) : 1633-1041.
  • 7Zhao Wentao, Fang Tao, Jiang Yan. Data fusion using improved Dempster-Shafer evidence theory for vehicle detection[C]//2007 International Conference on Fuzzy Systems and Knowledge Discover. Haikou: IEEE Press, 2007: 487-491.

二级参考文献5

  • 1纪晓东,周继成,王德隽.基于前馈神经网络的交换网络路径选择控制器[J].北京邮电大学学报,1996,19(3):89-92. 被引量:2
  • 2李士勇.模糊控制、神经控制和智能控制论[M].哈尔滨:哈尔滨工业大学出版社,2004.
  • 3Koivo H.Artificial neural networks in fault diagnosis and control[J].Control Eng Practice,1994,2(1):89-101.
  • 4He Jiazhou,Zhou Zhihua,Zhou Xuri,et al.Using neural networks for fault diagnosis[C]∥Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks.Como:[s.n.],2000:217-220.
  • 5王月珍,陈庆年.CDMA系统的网络优化[J].移动通信,2003,27(8):58-61. 被引量:2

共引文献2

同被引文献180

引证文献20

二级引证文献281

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部