期刊文献+

结合证据理论的代价敏感加权故障诊断 被引量:2

Research on Weighted Cost-sensitive Fault Diagnosis via Fusing Evidence Theory
原文传递
导出
摘要 为了在故障诊断中合理引入代价敏感机制来降低故障误诊断的代价,提出了一种结合证据理论的代价敏感加权故障诊断方法。该方法通过误诊断代价矩阵获取各故障模式误诊断的危害度,赋予不同的代价权重,并对证据理论的概率分配函数进行代价加权,将故障误诊断的代价作为权重合理融入诊断结果,从而实现了代价敏感机制在故障诊断中的有效应用。实验结果表明,结合证据理论的代价敏感加权处理能够使得故障诊断结果更倾向于高代价故障,所提方法可以有效降低故障误诊断的代价。 To reduce the cost of failure mistaken diagnosis by properly introducing the cost-sensitive mechanism, a weighted cost-sensitive fault diagnostics via fused evidence theory is proposed. It obtains the damage degree of false diagnosis for each failure mode by the error diagnosis cost matrix, and confers different cost weight for probability distribution function of the evidence theory, and the cost of failure error diagnosis used as the weight is fused into the diagnostic result, by which effectively apply the cost-sensitive mechanism into the failure diagnosis. The experimental results show that the weighted cost-sensitive diagnosis via fusing evidence theory make the diagnose results tend to diagnose the high-cost fault, and the proposed method can effectively decrease the cost of fault diagnosis.
出处 《机械设计与研究》 CSCD 北大核心 2015年第4期16-19,共4页 Machine Design And Research
基金 国家自然科学基金(51475049) 湖南省自然科学基金资助项目(2015JJ2015) 湖南省"十二五"重点建设学科及湖南省教育厅资助科研项目(12A016 11C0117 14C0094) 校人才引进科研基金项目(12004)
关键词 证据理论 代价敏感 故障诊断 代价矩阵 加权 evidence theory cost sensitivity fault diagnosis cost matrix weight
  • 相关文献

参考文献14

  • 1Rasmussen C E, Williams C K I. Gaussian processes for machine learning[ M]. Cambridge/London: The MIT Press, 2006.
  • 2吴薇,胡静涛.基于代价敏感直推式学习的故障诊断方法[J].仪器仪表学报,2010,31(5):1023-1028. 被引量:3
  • 3Dempster A P. Upper and lower probabilities induced by a multiple valued mapping[ J ]. The Annals of Mathematical Statistics, 1967, 38 (2) : 325 - 339.
  • 4Shafer G. A mathematical theory of evidence [ M ]. Princeton : Princeton University Press, 1976.
  • 5Sevastianov P, Dymova L, Bartosiewicz P. A framework for rule- base evidential reasoning in the interval setting applied to diagno- sing type 2 diabetes[ J]. Expert Systems with Applications, 2012, 39(4) : 4190 N4200.
  • 6Mokhtari K, lien Jun, Roberts C. Decision support framework for risk management on sea ports and terminals using fuzzy set theory and evidential reasoning approach[ J]. Expert Systems with Appli- cations, 2012, 39(5): 5087-5103.
  • 7姜万录,吴胜强.基于SVM和证据理论的多数据融合故障诊断方法[J].仪器仪表学报,2010,31(8):1738-1743. 被引量:58
  • 8尹金良,朱永利,郑晓雨,王国强.代价敏感VBGP在变压器故障诊断中的应用[J].电工技术学报,2014,29(3):222-227. 被引量:11
  • 9Saitta L. Machine learning: a technological roadmap [ R ]. The Netherlands : Univ. of Amsterdam, 2000.
  • 10唐勇波,桂卫华,彭涛.代价敏感核主元分析及其在故障诊断中的应用[J].中南大学学报(自然科学版),2013,44(6):2324-2330. 被引量:6

二级参考文献93

共引文献156

同被引文献30

引证文献2

二级引证文献4

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