【摘要】 针对动车组受电弓维护决策和智能诊断中知识多源异构以及维修记录缺失不完整和语义冲突等问题,提出异构信息融合和模糊智能诊断算法。针对受电弓诊断知识的多源异构特性及其不足,提出采用本地数据库资源描述框架(RDF)到全局RDF的转换和通过霍尔(Horn)逻辑刻画概念属性间的等价、包含或冲突关系,得到受电弓故障知识RDF(S)本体合并。基于知识融合结果和对受电弓系统的FMEA分析,建立受电弓故障树模型,并结合T-S模糊理论对其进行改进,引入模糊乘和最大/最小算子建立T-S模糊门,推理计算得到不完整缺失数据条件下故障树中各底事件的状态重要度及其对顶事件影响重要度排序。最后结合动车组实际运用中受电弓的故障诊断数据,证明了本文所提算法的合理性和有效性。更多还原

【Abstract】 Focusing on the multi-source heterogeneous,incompleteness and semantic ambiguity of the fault domain knowledge in the maintenance of the CRH2 EMU train,a fuzzy intelligent diagnosis algorithm based on multi-source heterogeneous knowledge fusion is proposed. Aiming at the deficiencies of multi-source heterogeneous,Resource Description Framework( Schema) of the local database is transferred into local ontology model and finally transferred into global ontology. Then horn logic rules are adopted to describe relations such as equivalence,inclusion and collision. RDF( S) ontologies of the fault domain knowledge are merged into a unified whole. Based on the global ontology of the knowledge,the failure mode and effect analysis of the pantograph type current collector,the fault tree of the pantograph is established together with the T-S fuzzy theory. The sort of the importance degree of basic events is calculated by importing the fuzzy multiplication and max / min operator. Finally,combined with the application of fault diagnosis example of the pantograph,the proposed method is proved reasonable and effective.更多还原