摘要
为了提高地铁车辆牵引系统典型故障诊断准确性,提出基于知识图谱的地铁车辆牵引系统典型故障分析和诊断方法。构建地铁车辆牵引系统故障知识图谱,分析地铁车辆牵引系统存在典型故障问题,使用TransH模型向量化处理系统故障信息知识图谱,把离散符号变换成低维度的实值向量,采用主成分分析方法提取故障特征,采用分布式深度神经网络进行地铁车辆牵引系统典型故障诊断。实验结果表明:所提方法对牵引系统典型的电压暂降故障分析和诊断后,诊断结果与实际状态相同,可通过知识图谱分析地铁车辆牵引系统典型故障问题,准确诊断故障级别。
In order to improve the accuracy of typical fault diagnosis of metro vehicle traction system,a typical fault analysis and diagnosis method of metro vehicle traction system based on knowledge map is proposed.It builds the fault knowledge map of the metro vehicle traction system,analyze the typical fault problems of the metro vehicle traction system,uses the TransH model to vectorize the system fault information knowledge map,transforms the discrete symbols into low dimensional real value vectors,uses the principal component analysis method to extract the fault characteristics,and uses the distributed deep neural network to diagnose the typical faults of the metro vehicle traction system.The experimental results show that after the proposed method analyzes and diagnoses the typical voltage sag fault of the traction system,the diagnosis results are no different from the actual state,and the typical fault problems of the traction system of metro vehicles can be analyzed through the knowledge map to accurately diagnose the fault level.
作者
肇北
ZHAO Bei(College of Mechanical and Electrical Engineering,North China University of Technology,Beijing 100144 China)
出处
《自动化技术与应用》
2024年第9期16-20,共5页
Techniques of Automation and Applications
关键词
知识图谱
地铁车辆
牵引系统
典型故障
故障诊断
故障级别
knowledge map
metro vehicles
traction system
typical fault
fault diagnosis
fault level
