基于改进FP-Growth算法的CRHX型动车组牵引系统关联失效模型研究  

Research on Correlation Failure Models of CRHX EMU Traction System Based on the Improved FP-Growth Algorithm

作　　者：王艳辉[1,2,3] 王淑君[1,2,3] 李曼[1,2,3] 林帅[1,2,3] 

机构地区：[1]北京交通大学轨道交通控制与安全国家重点实验室,北京100044 [2]北京交通大学交通运输学院,北京100044 [3]北京交通大学北京市城市交通信息智能感知与服务工程技术研究中心,北京100044

出　　处：《铁道学报》2016年第9期72-80,共9页Journal of the China Railway Society

基　　金：轨道交通控制与安全国家重点实验室自主研究课题(RCS 2016ZZ002)

摘　　要：基于CRHX型动车组牵引系统运营过程中的故障数据,分析故障数据的特征,研究设备之间的关联失效关系。依托课题组前期对故障信息特征词提取的研究,本文结合故障信息特征词的特点优化经典的关联规则挖掘算法,提出改进的FP-Growth算法,并进行算法性能测试,结果表明该算法准确高效;基于改进的FPGrowth算法分析设备的故障信息特征词,挖掘设备关联失效规则,建立设备的关联失效模型。最后,以CRHX型动车组牵引系统为例进行研究,验证了改进FP-Growth算法的有效性和实用性。Based on the failure data of CRHX EMU traction system in the process of its operation, the features of these data were analyzed, and the correlation failure relationships between equipment were investigated. Based on the earlier study of the extraction of the fault information feature words, the improved FP-Growth al- gorithm was obtained through optimizing the classical correlation rule mining algorithm combined with the characteristics of fault information feature words. The results of the performance test of the algorithm proved the accuracy and efficiency of the algorithm. After the improved FP-Growth algorithm was used to analyze the fault information feature words of the equipment and to extract equipment correlation failure rules, an equipment correlation failure model was established. At last, a case study of the CRHX EMU traction system veri- fied the effectiveness and practicability of the improved FP-Growth algorithm.

关 键 词：故障信息 改进FP-Growth算法 关联规则 关联失效模型 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]