期刊文献+

一种基于DS证据理论的电网故障诊断方法 被引量:18

A power system fault diagnosis method based on DS evidence theory
下载PDF
导出
摘要 提出的基于DS证据理论的电网故障诊断方法可解决由不知道所引起的不确定性。确立电网故障诊断的识别框架后,基于贝叶斯方法实现DS证据的表达,应用Dempster法则得到合成的信度函数,以此判断电网故障元件。基于Matlab编程实现了该算法,分析了单重故障且保护与断路器工作正常,单重故障伴有保护误动与断路器拒动,多重故障伴有保护、断路器误动与拒动三种典型故障情况。算例测试结果表明该方法能够有效地识别故障元件。 A power system fault diagnosis method based on DS evidence theory is proposed, which can deal with uncertainty brought by Unknown. After constructing frame of discernment, DS evidences are expressed based on Bayesian method, and a combined belief function is obtained in terms of Dempster Rule, in accordance with which, the fault elements are recognized. The algorithm is realized by programming based on Matlab, and three typical fault conditions which are single fault with protection and circuit breaker working normally, single fault with misoperation of protection and refuse of circuit breaker, multiple faults with misoperation and refuse of protection and circuit breaker are analyzed. The testing results demonstrate that this method can recognize the fault elements efficiently.
出处 《继电器》 CSCD 北大核心 2008年第9期5-10,共6页 Relay
基金 国家自然科学基金(No.50407009) 四川省杰出青年基金项目(No.06ZQ026-012) 教育部优秀新世纪人才支持计划项目(NCET-06-0799)~~
关键词 电网故障诊断 DS证据理论 信息扩散 信息融合 贝叶斯 power system fault diagnosis DS evidence theory information diffusion information fusion Bayesian
  • 相关文献

参考文献15

  • 1Tan J C, Crossly P A, Goody J, et al. Fault Section Identification on a Transmission Network Using Action Factors and Expert System Technology[A]. In:13th Power Systems Computation Conference (PSCC'99)[C]. Trondheim (Norway): 1999. 被引量:1
  • 2刘青松,夏道止.基于正反向推理的电力系统故障诊断专家系统[J].电网技术,1999,23(9):66-68. 被引量:32
  • 3Navarro V D, Silva A L, de Carvalho L A V, et al. Artificial Neural Networks for Power Systems Diagnosis[A].In: IEEE International Conference on Neural Networks[C]. 1994. 3738-3743. 被引量:1
  • 4Aygen Z E, Seker S, Bagnyanik M, et al. Fault Section Estimation in Electrical Power Systems Using Artificial Neural Network Approach[A].In: IEEE Transmission and Distribution Conference[C]. 1999.466-469. 被引量:1
  • 5Narendra K G, Sood V K, Khorasani K, et al. Application of a Radial Basis Function(RBF) Neural Network for Fault Diagnosis in a HVDC System[J]. IEEE Trans on Power Systems, 1998,13( 1): 177-183. 被引量:1
  • 6Yang Hong-tzer, Chang Wen-yeau, Huang Ching-lien. Power System Distributed On-line Fault Section Section Estimation Using Decision Tree Based Neural Nets Approach[J]. IEEE Trans on Power Delivery, 1995,10(1):540-546. 被引量:1
  • 7束洪春,孙向飞,司大军.基于粗糙集理论的配电网故障诊断研究[J].中国电机工程学报,2001,21(10):73-77. 被引量:109
  • 8张池平,张英俊,苏小红,马培军.一种基于神经网络和证据理论的信息融合算法[J].计算机工程与应用,2006,42(1):174-176. 被引量:16
  • 9Foucher S, Germain M, et al. Multisource Classification Using ICM and Dempster-Shafer Theory[J].IEEE Trans on Instrumentation and Measurement,2002,51 (2). 被引量:1
  • 10许丽佳.DS理论在信息融合中的改进[J].系统工程与电子技术,2004,26(6):717-720. 被引量:24

二级参考文献22

共引文献242

同被引文献132

引证文献18

二级引证文献160

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